List all Tracks

ABSTRACT

Apple is one of the most produced fruit crops in the world. Recent advances in Artificial Intelligence and the Internet of Things can reduce production costs and improve crop quality by providing prompt detection of dangerous parasites. This paper presents an effective solution to automate the detection of the Codling Moths. The system takes pictures of trapped insects in the orchard, analyzes them through a DNN algorithm, and sends alarms to the farmer in case of a positive detection. The system is fully autonomous and can operate unattended for the entire crop season. Detection reports are used for optimizing the treatment with chemicals only when threats are identified. The prototype is designed with an embedded platform powered by a small solar panel to achieve an energy-neutral balance.

PRESENTER

Matteo Nardello
University of Trento, Italy

ABSTRACT

In precision farming, a very promising scenario is represented by a connected and autonomous vehicle (CAV) moving in a cultivated field and collecting high-resolution videos and hyperspectral images, requiring both localization and broadband communication. An effective approach to provide both localization and wideband communication exploits unmanned aerial vehicles (UAVs) that may act as relays to ensure seamless connectivity with a base station (BS). In this paper, we propose a reinforcement learning (RL)-based algorithm to find the best spatial configuration of a swarm of UAVs to localize a CAV in an unknown environment and assist the communication with a BS. The UAVs cooperate to estimate the position of the CAV exploiting only the received signal strength (RSS). A reward function, based on the distance between the UAVs and the CAV, and the estimated geometric diluition of precision (GDOP), is designed. Numerical results show how the proposed multi-agent Q-learning allows the UAVs to reach low root mean square error (RMSE) in the target localization, even without previous knowledge about the environment.

PRESENTER

Enrico Testi
Università di Bologna, Italy

ABSTRACT

Measuring fruit growth can be useful not only to estimate its final weight but this information, in conjunction with environmental data and weather forecasts, can be used to estimate the water and nutrients requirement of an orchard. This paper describes the design of a very low cost system capable to measure sub-millimeter changes in the size of a fruit during its entire growth cycle. This solution overcomes any need of relocating the measuring unit, a severe limitation of other existing devices, without compromising the measurement resolution. The proposed solution uses low cost, easily available components, while maintaining the ability to measure changes in size higher than 30 um and keeping a measuring range between 1:5 and 12 cm.

PRESENTER

Lorenzo Mistral Peppi
University of Bologna, Italy

ABSTRACT

The demand for modular, robust, and uninterrupted weather stations has increased as climate change is strongly affecting agriculture. Internet of Things (IoT) based weather stations is a promising solution to achieve uninterrupted operation of the weather station which is affected by constrained energy availability. This research provides ideas to overcome the energy challenge of a weather station and also the insights to develop an energy-neutral weather station. The primary requirements of a weather station for precision agriculture are explored and each component level challenges are presented. A novel development life cycle of an IoT based energy-neutral weather station is also presented for the developers. Finally, the best practices for developing an energy-autonomous weather station are presented.

PRESENTER

Padma Balaji Leelavinodhan
University of Trento, Italy

ABSTRACT

This paper describes the preliminary design of an innovative concept rotary-wing Unmanned Aircraft System (UAS) for precision agriculture and aerial spraying applications. Aerial spraying of plant protection products and pesticides shows open challenges in terms of performance and regulatory requirements. In particular, the focus here is on highlighting the advantages of the proposed solution in performing precise and expeditious interventions, coping with the spray drift problem (i.e. minimization of drift). Flight performances and agronomists' requirements are combined to define the mission and the aerial vehicle and spray system design.

PRESENTER

Nicoletta Bloise
Politecnico di Torino, Italy

ABSTRACT

Measuring at high frequency soil fluxes of carbon dioxide (CO2), and nitrous oxide (N2O) in agricultural soils requires appropriate technology. With this aim, a prototype was developed and tested in agricultural soils for 5 months, within the framework of the LIFE project AGRESTIC. The prototype is composed by two automatic GHG stations for measuring CO2 (LI-COR LI-850) and N2O (Teledyne GFC-7002TU) fluxes from soil and an IT infrastructure for data management. The two GHG stations were installed one in Ravenna, Italy, (Cà Bosco farm) and the other in Foggia, Italy, (Caione farm), where two different cropping systems were compared. Along the period going from January 1st to May 31st, 2020 the two GHG stations proved to be robust to field conditions (e.g. wind, rain, freeze etc.). The quality of the measurements was different in the two sites, with more than 90% of good measurements in Ravenna and more than 60% in Foggia.

PRESENTER

Iride Volpi
Scuola Superiore Sant'Anna, Italy

ABSTRACT

An increase in the irrigation demand has been projected in Europe, especially in the countries with the highest proportion of irrigated agricultural areas, such as Italy and Spain. This has led to advances in the field of irrigation systems, as center pivot systems which have facilitated the labor of farmers because of their automation. However, the monitoring of these systems together with the early detection of problems in their operation has become a key aspect during a farmer campaign. To answer this need, different solutions have been proposed from the ICT area and the Precision Agriculture field. In this work, the main communication and sensor technologies used for monitoring irrigation with pivots are analyzed. Two low-cost systems based on IoT technologies, GPS and LoRaWAN are proposed for the monitoring of this type of irrigation systems. Finally, the results obtained after its installation in two maize crops are presented and the conclusions obtained after the use of both systems are discussed.

PRESENTER

Álvaro Lozano Murciego
University of Salamanca, Spain

ABSTRACT

Spatial variability represents a challenge for viticulture. Variable-rate fertilization is a promising technology to manage different vigor and yield zones within the. In this study, on-the-go variable rate fertilization system was implemented and tested, based on commercial spectral sensors. GreenSeeker Normalized Difference Vegetation Index (NDVI) sensor was mounted in front of a tractor and connected to the electronic control unit of a variable rate spreader. Fertilizer rate was based on threshold values of NDVI, calibrated previously in ten sampling points by a GreenSeeker handheld sensor. The sampling points were selected according to the agronomist expertise on vineyard variability. A couple of GreenSeeker sensors carried by tractor and connected to the fertilizer electronic control unit were used for fertilizer dosage definition. Fertilizer application was evaluated comparing the amount of fertilizer distributed in the sample points with the prescribed dose. Results showed good accuracy of distribution compared with the prescribed amount of fertilizer. Similarly, the fertilizer distribution showed a significant correlation (R2 = 0.65, p-value < 0.01) with the Leaf Area Index collected in the sampling points. The effects of variable rate fertilizer application on vine vigor were preliminary assessed measuring vine shoot length the day when fertilizer was applied and 14 days after fertilizer application. Linear regression for vine shoots growth rate based on applied fertilizer showed an R2 of 0.6, suggesting a positive effect of the on-the-go variable rate fertilizer application on vines growth. Fertilization effects on field variability were then assessed considering three variability coefficients of NDVI (σ, Gini, and CV). The comparison between variability coefficients of the years before and after the fertilizer application showed a reduction of 37%, 43%, and 40% for σ, Gini, and CV, respectively. The results highlight the potential of proximal spectral sensors for on-the-go variable rate fertilization and reduction of in-field variability in vineyards.

PRESENTER

Marco Sozzi
University of Padova, Italy

ABSTRACT

Controlling and forecasting environmental variables (e.g., air temperature) is usually a key and complex part in a greenhouse management architecture. Indeed, a greenhouse inner micro-climate, which is the result of an extensive set of interrelated environmental variables influenced by external weather conditions, has to be tightly monitored, regulated, and, sometimes, forecast. Nowadays, Wireless Sensor Networks (WSNs) and Machine Learning (ML) are two of the most successful technologies to deal with this challenge. In this paper, we discuss how a Smart Gateway (GW), acting as a collector for sensor data coming from a WSN installed in a greenhouse, could be enriched with a Neural Network (NN)-based prediction model allowing to forecast a greenhouse’s inner air temperature. In the case of missing sensor data coming from the WSN, the proposed prediction algorithm, fed with meteorological open data (gathered from the DarkSky repository), is run on the GW in order to predict the missing values. Despite the model is especially designed to be lightweight and executable by a device with constrained capabilities, it can be adopted either at Cloud or at GW level to forecast future air temperature’s values, in order to support the management of a greenhouse. Experimental results show that the NN-based prediction algorithm can forecast greenhouse air temperature with a Root Mean Square Error (RMSE) of 1:50 °C, a Mean Absolute Percentage Error (MAPE) of 4:91%, and a R2 score of 0:965.

PRESENTER

Gaia Codeluppi
University of Parma, Italy

ABSTRACT

The use of dense 3D point clouds to obtain agricultural crop dimensions in the place of manual measurement is crucial for enabling high-throughput phenotyping. To achieve this goal, this paper proposes an adaptive k-means algorithm based on dynamic perspectives, which first performs segmentation in order to separate the wheat spikes. We also propose a method to fit the shape of each spike and measures the dimensions of each spike with the help of the Random Sample Consensus algorithm. The experimental results show that the proposed method can be applied in a complex environment where multiple wheat spikes are grown densely and that it can fit the size of most wheat spikes accurately.

PRESENTER

Fuli Wang
University of Essex, United Kingdom

ABSTRACT

PRESENTER

Bouazza Fekkak
University of Sciences and Technology Houari Boumediene, Algeria

ABSTRACT

This work presents the results of experimental activities carried out during a 3-years research program, to assess the effects of infesting reed beds on the mean and turbulent hydrodynamic features of vegetated reclamation channels at field scale. The devices and methodologies employed in the experiments represent an innovation in the study of vegetative flow resistance directly at field. Different management scenarios of the vegetated cover were evaluated, with the aim to assess the optimal strategy for balancing the need for an effective hydraulic conveyance and the need to preserve the environmental quality of the vegetated water bodies.

PRESENTER

Giuseppe Francesco Cesare Lama
University of Napoli Federico II, Italy

ABSTRACT

Hyperspectral imaging technology has its origins in the mid-1980s: from hyperspectral cameras developed for remote sensing by aerial vehicles or satellites, the technology has moved to proximal sensing applications on a lab-scale under controlled conditions. In the agri-food sector, hyperspectral imaging technology emerged in the non-destructive measurement of food quality parameters. In recent years, due to the miniaturization of hyperspectral cameras and the increase in computational and data storage capabilities, there is growing interest towards the in-field application of proximal remote sensing hyperspectral cameras mounted on airborne or unmanned aerial vehicles or ground vehicles. As example of the application of the hyperspectral imaging in the agri-food sector, quality attributes (soluble solids content, flesh firmness) of apricots, kiwifruits and grape were monitored by means of a hyperspectral camera, in order to observe their evolution during storage and directly in field.

PRESENTER

Alessandro Benelli
Alma Mater Studiorum - University of Bologna, Italy

ABSTRACT

The beer is a widely consumed drink, appreciated for its sensory characteristics. Beer also contains beneficial compounds for health derived from its raw materials. In recent years there is an expansion of craft breweries in many countries, with a growing market share. Consumers are more and more attracted by craft beers that are perceived as higher quality and with a more complex flavour profile than commercial ones. Drawbacks are the difficulty to standardize method used for their production causing variability in some quality parameters. In this study the results of the main physico-chemical parameters used for the characterization of beer are reported with the aim to highlight as the type of recipe affect the quality of three styles of craft beer: Session India Pale Ale, Dark Ale and Blonde Ale.

PRESENTER

Loredana Liguori
University of Salerno, Italy

ABSTRACT

In this work, the development of an impedimetric label-free immunosensor for the detection of Ochratoxin A in food products is reported. Two different immobilization schemes of a monoclonal antibody for OTA detection were investigated and compared, with the aim to develop an analytical device able to detect an OTA amount equal to the maximum levels imposed by European legislation for food products. activated ferrocene as electron – transferring mediator, improved the electrical properties of the immunosensor, which showed a limit of detection equal to 0.25 ng/mL. This immunosensor was used to analyze wine and beer samples spiked with known OTA amounts.

PRESENTER

Francesca Malvano
Università degli Studi di Salerno

ABSTRACT

The measurement of pH is widely used in a number of sectors and applications to evaluate the alkaline or acidic level of aqueous solutions. Among the measurement methods, pH strips are widespread and affordable, although they have a limited accuracy compared to the pH meters. In this work, a method to evaluate the pH value of a test strip, based on image analysis, is presented. The proposed method exploits the color analysis to simplify the use and to improve the nominal accuracy of the test strips. The tests have taken into account the typical pH range in the production of beer, but the method can be extended on the whole range of pH values.

PRESENTER

Salvatore Dello Iacono
Università degli studi di Salerno, Italy

ABSTRACT

Crop water use estimation at high geospatial resolution is critical for site-specific irrigation management of perennial specialty crops. This study aims to map actual evapotranspiration (ETa) of a commercial apple orchard using unmanned aerial system (UAS) based thermal and multispectral imagery and a widely adopted METRIC (Mapping Evapotranspiration at High Resolution with Internalized calibration) energy balance model (UASM). Four imaging campaigns were conducted during the 2020 growth season and weather data for pertinent days was downloaded from the nearest WSU-AgWeatherNet network station. 24-h ETa was also calculated from the soil water balance (SWB) approach that used soil moisture data from sensors installed at three locations and down to depth of 111 cm. A high linear correlation (r) of 0.84 and non-significant difference (p = 0.5) was observed between UASM derived ETa (5.05 ± 0.8 [Mean ± Std. Dev.] mm day-1) and SWB calculated ETa (5.44 ± 1.81 mm day-1). Notable differences in spatiotemporal water use and crop-coefficients were observed within the orchard. A moderately strong correlation was also observed between the UASM derived crop-coefficients and multispectral imagery derived Normalized Difference Vegetation Index (r = 0.69) that may also be used for estimating actual crop water use. Overall, approach presented in this study may help identify under or over-irrigated areas within the orchard. It may also assist in developing site-specific irrigation prescription maps and schedules.

PRESENTER

Abhilash Chandel
Washington State University, United States

ABSTRACT

This study discusses development and field validation of an abiotic stress-monitoring system, i.e. crop physiological sensing system (CPSS) for perennial speciality crops. In current form, CPSS acquires and processes the thermal-RGB imagery as well as site-specific weather data through field sensing nodes and predicts apple and cherry crop specific abiotic stress indicators. The system processes the data on a single board computer to perform real-time prediction of the fruit surface temperature (FST, ºC), a prominent indicator for sunburn susceptibility in apple and the fruit wetness (%) that is related to cracking susceptibility in sweet cherry. The developed system was validated in the field condition and results indicate that imagery derived apple FST (Ti) had strong correlation (R2 = 0.64) with ground truth measured FST (Tg) with no significant difference. Cherry FST data as a predictor variable also had a strong correlation between actual and predicted wetness (R2 = 0.80). Overall, developed CPSS could be reliably utilized for sunburn and wetness prediction in respective apple and sweet cherry.

PRESENTER

Rakesh Ranjan
Washington State University, United States

ABSTRACT

The development of reliable fruit detection and localization systems has been approached with remote sensing methods aimed at optimizing the orchard management to obtain high crop quality and economically improved harvesting practice. This work presents a new technique that uses a light detection and ranging (LiDAR) laser scanner to detect and localize apple fruits in the orchard. In a 1 ha apple orchard (Malus x domestica 'Gala') two trees were defoliated before harvest period. A LiDAR scanner emitting at 905 nm, with a real time kinematic global navigation satellite system to geo-reference the data and an inertial measurement unit to acquire orientation data were mounted on a tractor (0.2 km/h) to produce the 3D tree point cloud before and after defoliation. Subsequently, the apples of each tree were harvested and classified in four size classes according to height (Hmanual) and diameter (Dmanual). An intensity analysis of tree elements was performed, obtaining mean intensity values of 28.9%, 29.1%, and 44.3% for leaves, branches and trunks, and apples, respectively. These results suggested that the intensity parameter can be useful to detect apples. A four-step fruit detection algorithm was developed to localize and estimate the height (HLiDAR) and diameter (DLiDAR) of fruits. A mean detection success of 92.5% was obtained in relation to the total amount of fruits on the defoliated trees during the stages of fruit development. A mean correlation of R2 = 0.83 was obtained for Hmanual and HLiDAR, whereas a less pronounced relation was observed between DLiDAR and Dmanual (R2 = 0.62) during fruit development. The mean detection success was decreased to 70.5% when the fruit detection algorithm was applied in the foliated trees. From the experimental results, it can be concluded that LiDAR-based technology and, particularly, its intensity information has potential for remote apple detection and 3D localisation.

PRESENTER

Nikos Tsoulias
ATB Leibniz Institute of Agricultural Engineering and Bio-economy, Germany

ABSTRACT

This paper describes a method to estimate the fruit bearing capacity of individual apple trees aimed at the production of targeted average fruit sizes. The approach utilizes the total leaf area per individual tree, mapped in the orchard with a terrestrial LiDAR, leaf gas exchange, daily fruit carbon requirements and the seasonal curse of climate data in a carbon balance model.

PRESENTER

Martin Penzel
Leibniz Institute for Agricultural Engineering and Bioeconomy/ ATB, Germany

ABSTRACT

Powdery mildew (PM) in apples is a critical fungal disease that adversely affects yield and fruit quality. Conventional PM identification techniques are laborious. This study evaluated the suitability of non-destructive low altitude imaging in the visible (RGB) and multispectral domain for PM detection in apple orchards. Imagery snapshots were acquired at known locations of PM infestation in apple trees using two small unmanned aerial systems (UAS). One UAS employed a consumer grade RGB camera while other UAS had a five-band multispectral imaging sensor. Custom image processing algorithms were developed for RGB and multispectral imagery analysis. The RGB images were classified using k-means and resulted in PM detection accuracy of 76.4%. A strong agreement was also observed between the number of actual PM clusters and clusters that were classified (R2 = 0.94). Seven vegetation indices (VIs) were extracted from the multispectral imagery as the potential chlorophyll variation indicators. Such indices showed significant difference (p < 0.05) for PM infected leaves and the healthy leaves. Modified Simple Ratio-Red, Modified Simple Ratio-Blue and Optimized Soil Adjusted Vegetation Index were the key differentiators showing low values for PM (Mean: 0.01–0.05) and high values for healthy leaves (Mean: 0.51–0.84). Overall, results showed the potential to detect and quantify PM infestation in apple orchards at high spatial resolution. Additional efforts are needed to translate these results to map PM infestation at the orchard block level that could aid in site-specific remedial measures.

PRESENTER

Abhilash Chandel
Washington State University, United States

ABSTRACT

This study evaluates a tablet computer-enabled miniature thermal-RGB imager to map the crop water stress index (CWSI) in grapevines. Imagery data were acquired in a commercial grapevine block irrigated at four different rates (100, 80, 60, and 40% of replacement evapotranspiration [ET]). The latter three were the subsurface irrigation treatments. A custom image analysis algorithm was developed and CWSI was estimated using empirical baseline equations. RGB imaging refined the segmentation of the target canopy from background objects. Canopy-air temperature difference had significant and strong relationships with the vapor pressure deficits as per local conditions (R2: 0.72–0.85, p < 0.05). CWSI estimates for grapevines irrigated at 40% of ET were consistently the highest and were followed by for those irrigated at 60, 80, and 100% of ET rates. Study findings highlight the potential to develop a smartphone-enabled imaging and integrated application for real-time crop water stress assessment under field conditions. Our future efforts will refine these computing algorithms and develop a smartphone application for growers to assess treelevel crop water demands for site-specific irrigation management.

PRESENTER

Basavaraj Rajkumar Amogi
Washington State University, United States

ABSTRACT

At present, technological support may specifically contribute to develop and to improve the aquaculture production, and in particular the fish production in offshore pens. Estimating live-fish biomass is extremely relevant to optimize the whole growth cycle, therefore the availability of portable and reliable scale is very important. We present here the detail of a smart scale suitable to be used over a rolling and pitching ship either on lakes or seas.

PRESENTER

Carlo Bibbiani
University of Pisa, Italy

ABSTRACT

The study presents the objectives, methodologies and technical features of a monitoring system designed in the context of a national research project proposing innovative technical solutions for smart dairy farming in order to increase the herd productivity. The main objective of the project was to improve environment conditions and animal welfare of dairy cows and consequently enhance reproduction and production. To this regard, the system described here has a fundamental role operating as a tool for a more efficient management of the herd and of the herd housing. In fact, in the last years, animal control techniques and farm environmental monitoring have been developed, with increasing intensity, through the integration of Information Communication Technology (ICT) systems and models for the analysis and interpretation of the data collected. In this field, the Smart Monitoring System (SMS) described here could be effectively implemented in order to increase the animal welfare but at the same time increase the animal production. The integration of different type of sensors, different type of data and different type of models is at the base of the modern techniques for herd management and of the tools aiming to increase the dairy sector sustainability. The system integrates specifically designed sensor networks in a customized system architecture. It allows the acquisition of big data time series about physical and environmental conditions of the facilities hosting the cow herds starting from the collection of both indoor and outdoor environmental features, enabling a smart control of the facility, a diagnosis of the operating conditions, and early alerts in case of anomalies. The system has been developed to work in several environmental situations and is able to make the data remotely available in real time in a cloud.

PRESENTER

Stefano Benni
University of Bologna - DISTAL

ABSTRACT

The cow’s individual feed intake and, consequently, feed efficiency are traits with a high economic value for the livestock farmer. Feeding behavior and feed intake have traditionally been determined by labour-intensive procedures such as human visual inspection and determination of feed refusals. However, the difficulty in manually collecting data at the time of feeding limits the extent of this type of monitoring. In order to overcome such limitations, optical techniques have been proposed in the last years as a fast-noncontact approach for feed weight/volume estimation. The present paper discusses the potential application of RFID (Radio-Frequency IDentification) technology for indirect estimation of the quantity of feed-ration present in the cow-feed alley. Experimental tests were carried out taking advantage of different amounts of feed ration for lactating cows (51.8% DM) composed by corn silage, alfalfa silage, hay, molasses, and concentrate. Preliminary results highlighted an interesting correlation (R²=0.90) between the minimum power demand for reading the RFID tags positioned on the feed-alley and the quantity of feed-ration to analyze. As the quantities of feedration increased, the power demand increased, providing an indirect indication of the variation in quantity. Moreover, the evaluation of the height of the distributed feed-ration showed a high positive correlation (R² = 0.96) with the minimum power requirement for reading the RFID tags positioned on the feedalley. The use of RFIDs on the feed-alley represents an interesting solution to define both the quantity of ration to distribute and the evaluation of the residual feed-ration in the feed-alley.

PRESENTER

Andrea Pezzuolo
Università degli Studi di Padova, Italy

ABSTRACT

The Integrated Smart Monitoring and Control System (ISMaCS) is designed to allow the acquisition of large physical and environmental features in an agriculture and aquaculture integrated context and make data available for checking, assistance and analysis. The system is able to work in different environments, to collect data and make them available remotely in real time. It is designed to operate in the structures of the PRIMA project where aquaculture and plant cultivation are integrated in indoor and outdoor environments. This system allows the diagnosis of the operating conditions of the monitored plants.

PRESENTER

Alberto Barbaresi
University of Bologna, Italy

ABSTRACT

In the last decade, the interest on instrumentation for three-dimensional (3D) reconstruction has increased, in particular for the possibility of characterizing phenology and physical characteristics of agricultural products. The present work evaluates the suitability of a low-cost instrument for fast generation of three-dimensional digital models: focus of the present study is the evaluation of accuracy of 3D point clouds. The instrument relies on an IR-depth sensing camera and an RGB camera, both allowing rapid digital reconstruction of scanned objects. The evaluation has been carried on a bunch of grapes under different operating parameters (e.g. scanning speed, distances of the target from the instrument) reproduced in laboratory conditions.

PRESENTER

Domenico Giora
University of Padova, Italy

ABSTRACT

This paper presents a data-driven approach allowing the insurance companies operating in the agricultural sector to assess the accumulation risk related to harmful meteorological events. The approach is based on the idea that the crucial piece of information necessary to consistently evaluate the accumulation risk is given by the knowledge of the characteristic spatial extension of the potentially harmful events. A procedure for estimating this quantity using historical weather time series is proposed.

PRESENTER

Andrea Marini
Idea-Re S.r.l., Italy

ABSTRACT

Effectiveness of a simple Time Domain Reflectometry instrumental chain was tested by using different sodium chloride concentration. The layout is quite simple and economic, the software user friendly and the measurements rapid. An innovative approach for the statistical analysis of these kind of signals was implemented, accounting for multivariate analysis of the waveform, replacing the traditional mathematical theory. Good results in terms of coefficient of determination for sodium chloride estimation were obtained with R2 0.942 (RMSE 0.18 g/100ml) for simple linear regression and R2 0.983 (RMSE 0.10 g/100ml) for PLS analysis. The results obtained show how a cheap, rapid, and easy to use instrumental chain can be very promising for determinations of foodstuff parameters.

PRESENTER

Eleonora Iaccheri
University of Bologna, Italy

ABSTRACT

Monitoring the quality attributes of grapes is a practice that allows to check the grapes’ state of ripeness and to decide when it is appropriate to proceed with the harvest. In the present study, a non-destructive method based on hyperspectral imaging (HSI) technology was developed. Analyses were carried out directly in the field using a Vis/NIR (400–1000 nm) hyperspectral camera (HSC) between the rows of ‘Sangiovese’ (Vitis vinifera L.) vineyard destined for wine production. One vineyard row was analyzed on 13 different days. During the trials, 33 berries were collected and the soluble solids content (SSC) expressed in terms of °Brix (°Bx) was measured by a portable digital refractometer. The mean spectra of the selected berries were extracted from each hyperspectral (HS) image. The pre-treated mean spectra were used to predict the SSC of the berries by means of partial least squares (PLS) regression, obtaining a value of R2 = 0.75 in cross-validation, with RMSECV = 0.84 °Bx. The present study shows the potential of the use of HSI technology directly in the field through proximal measurements under natural light conditions for the prediction of the SSC quality attribute of grapes.

PRESENTER

Alessandro Benelli
Alma Mater Studiorum - University of Bologna, Italy

ABSTRACT

Biochemical reactions and microbiological activity are responsible of fresh fish short shelf life. The deterioration processes involve a series of changes in the product quality affecting its appearance, odor and taste. The present work aims at discriminating samples of sardines during the shelf life at 4°C by means of a Vis/Nir HyperSpectral Camera (HSC) camera. After preprocessing techniques, Principal Component Analysis (PCA) was used to evidence spectral differences related to the deterioration processes. By analyzing the score plot of the first two principal components (PC1 = 94.1%; PC2 = 3.0 %), a distribution according to time was observed, showing that hyperspectral data could be a good indicator of fish freshness and decay state progress.

PRESENTER

Leonardo Franceschelli
Department of Electrical, Electronic and Information Engineering “Guglielmo Marconi”, Alma Mater Studiorum, University of Bologna.

ABSTRACT

Information technologies can introduce important innovation in human life and daily activities. Among the most important innovations developed in recent years, those concerning the agriculture are particularly relevant even from an economic point of view. The main advantage is the cross-analysis of environmental, climatic, and cultural factors, which allows establishing the irrigation and nutritional needs of crops, preventing pathologies, identifying weeds before they proliferate. Specifically, the main contribution of this work consists in the use of three convolutional neural networks previously trained on a similar problem, which, starting from an image of a tomato leaf, using a transfer learning method, identify if the plant is sick and the type of disease. The proposed networks show a high precision and accuracy coefficient, demonstrating how the application of convolutional neural networks for this type of problem is very effective.

PRESENTER

Martina Iammarino
University of Sannio

ABSTRACT

Drying is one of the most viable and effective preservation technologies to improve the shelf-life of foods. Carrots are among the most consumed vegetables, owing to their nutritional profile as well as their wide use in dried foods, readyto- eat and ready-to-use convenience products like snacks, meals, and soups. As for the dried products, the quality of produce depends on the timely recognition of the dehydration state. Traditional off-line analyses in combination with drying rates to identify the end-time of the process can fail in identifying process discrepancies and avoiding product degradation. The use of computer vision (CV) as a Process Analytical Technology (PAT) tool in the drying system can be of interest to monitor the drying process and product quality. The objective of this study was to study the drying behavior of carrot slices during drying at 35 °C for 36 h using a smart dryer augmented with computer vision system and load cell. The system developed was effective in measuring the weight, size, and color of the untreated (control) and pre-treated (blanched) carrot slices along the drying time. The image analysis and the weight loss of the slices enabled the prediction of relative moisture content (MC) using linear and thinlayer (Newton-Lewis) models in comparison. The applicability of the models was further evaluated by use of different pretreatments (i.e. blanched at 90 °C for 2 min or not blanched). The results showed promising prediction capability for the linear models, which was independent of time with a Root Mean Square Error (RMSE) similar to the thin-layer models, an adj. R2 > 0.99 as well as both Mean BIAS Error (MBE) and reduced χ2 tending towards zero. The blanching treatment affected the model parameters but negligibly affected the model performances.

PRESENTER

Swathi Sirisha Nallan Chakravartula
University of Tuscia, Italy

ABSTRACT

We present a ground robotic platform suited to agriculture applications. The design is specifically targeted for small/medium farms and it is characterized by marked features in terms of flexibility, reconfigurability and robustness. We present the tracked vehicle design concept as well as the mechanical model by emphasizing some aspects that make the platform particularly suited to operate in "all-terrains". We also present experimental results to validate the model.

PRESENTER

Roberto Tazzari
University of Bologna, Italy

ABSTRACT

This work presents a new survey system for the assessment of diseases and missing plant in vineyards. The data analysis is based on LiDAR and NDVI data classification, collected by sensors mounted on a tracked all-terrain vehicle. After this classification, a thematic map representing the vegetative status of the whole row is accomplished. The first results obtained from preliminary tests, carried out on portions of row (transepts), are shown in this work.

PRESENTER

Gabriele Daglio
Libera Universitá di Bolzano, Italy

ABSTRACT

Improvement of productivity and efficiency in the agriculture sector points towards the necessity of developing autonomous vehicles. Here, the detection and classification of objects plays a major role, which can be achieved by using camera sensors and convolutional neural networks (CNNs). In order to train CNNs to perform correctly, good datasets are required. However, especially for the case of agriculture, datasets that contain relevant objects and are labeled (i.e. annotated with ground truth information) are not only scarce but also difficult to generate as this entails a high cost in resources and human labor. Therefore, we propose a different approach: using 3D simulation technology to generate relevant simulated sensor data which are implicitly labeled and a cost efficient solution to train neural networks. In this contribution, we assess the viability of training a CNN with simulated sensor data by comparing the achieved performance to a network trained with real sensor data. In addition, we evaluate the benefits of combining simulated data with real data for training CNNs, including complementary as well as Transfer Learning approaches. Finally, we show that using simulated sensor data for training CNNs is viable yet less accurate than using comparable real datasets and propose ways to improve simulations in this regard. To this end, we analyze various simulation factors in terms of their impact on the CNN performance and introduce further benefits of using simulated scenarios in general.

PRESENTER

Jorge Luis Jimenez Aparicio
RWTH Aachen University, Germany

ABSTRACT

Precision agriculture comprises a set of technologies that combines sensors, information systems, enhanced machinery, and informed management to optimize production by accounting for variability and uncertainties within agricultural systems. Autonomous ground and aerial vehicle can lead to favorable improvements in management by performing in-field tasks in a time-effective way. Greater benefits can be achieved by allowing cooperation and collaborative action among Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs). A multi-phase approach is here proposed, where each unmanned vehicle involved has been conceived and will be designed to implement innovative solutions for automated navigation and infield operations within a complex irregular and unstructured scenario as vineyards in sloped terrains.

PRESENTER

Martina Mammarella
IEIIT-CNR, Italy

ABSTRACT

With the increase of population in the world, the demand for quality food is increasing too. In recent years, increasing demand and environmental factors have heavily influenced the agricultural production. Automation and robotics for fruit and vegetable production/monitoring have become the new standard. This paper discusses an autonomous Unmanned Aerial Vehicle (UAV) able to navigate through rows orchard rows. The UAV is comprised of a flight controller (AP stack), a microcontroller for analog reading of different sensors, and an On-Board Computer (OBC). Pictures are taken through a camera and streamed through WiFi to a Ground Control Computer (GCC) running a convolution neural network model. Based on prior training, the model outputs three directions: RIGHT, LEFT and STRAIGHT. A moving average of multiple frames per second is extracted and sent to a build-in Proportional-IntegralDerivative (PID) controller on the UAV. After error correction from this feedback, controller sends the direction to the flight controller using MAVLink protocol’s radio channel overrides, thus performing autonomous navigation.

PRESENTER

Kushtrim Bresilla
University of Bologna, Italy

ABSTRACT

Agriculture needs to optimization for satisfying the rising demands of food due to world population growth. An approach to this problem is digitization of agriculture through IT tools by creating digital twins. However, in the digital twin creation the uniqueness of the plant is lost, therefore, plant based agricultural cultivation cannot be performed. Hence, this paper proposes a methodology to assign an identification marker to plants in a crop using an image analysis pipeline. To show the effectiveness of the algorithm the proposed method is evaluated on the Rovitis robotic platform and compared with the crop ontology. The outcome of this work can be used in robotic agricultural platforms to address plants singularly thus optimizing their cultivation.

PRESENTER

Matteo Pantano
Siemens AG, Germany

ABSTRACT

We present an autonomous ground robotic platform for agriculture application. The design is specifically targeted for small/medium farms with orchards and in this paper we propose a new vehicle concept as well as the sensor suite and software architecture to accomplish the implementation of the navigation algorithm designed to autonomously operate within the rows of an orchard. In this context, we also show how to exploit the structure of the orchard to optimize the Hough Transform algorithm to detect tree rows. Simulations and experimental results are presented.

PRESENTER

Roberto Tazzari
University of Bologna, Italy

ABSTRACT

Image processing has recently been adopted for fruit damage detection in post-harvest operations. Through the implementation of hard-coded feature extraction algorithms, high accuracy has been found. The present study tested the fast and operational convolution neural networks with “YOLO v3” architecture using the online platform Supervise.ly to detect on pear fruit ‘Abbé Fétel’ physiological disorders such as superficial scald. Two different models were trained: I) one to detect the individual pear fruits within the batches; II) one to detect superficial scald or senescence scald on pear skin. Preliminary statistics show that the model to count the fruit inside the batches reaches an accuracy of 64.70% with a 0.5 of Intersection of Units. The second one has less accuracy (up to 20% of true positive) but maintains a good level of average precision (0.6) with different confidence thresholds (0.4 and 0.2). Further research is needed to improve the accuracy of both models and to map quality pre- and post-harvest. These results will help the packing house to manage fruit batches and to ensure good fruit quality for consumers.

PRESENTER

Alessandro Bonora
University of Bologna, Italy

ABSTRACT

A key point to decrease water usage in agriculture is to employ precision agriculture by adopting technologies such as the Internet of Things (IoT). Many solutions using the IoT rely on the use of soil moisture sensors to gather data, in realtime, from the plant’s root zone. This study presents a linear calibration curve, obtained by the thermogravimetric method, for a capacitive soil moisture sensor for a silty clay soil sampled at the FEI University Center. The curve obtained has an adjusted R2 of 0.86 and a residual standard error of 2.8%. The soil sensor was tested in the field during the end of February revealing that the sensor is capable of indicating changes in soil moisture within the error obtained from the calibration procedure and that it can be used to indicate changes by rain or irrigation procedures.

PRESENTER

Brenno Tondato de Faria
Centro Universitário FEI, Brazil

ABSTRACT

A new type of soil moisture sensor has been developed that uses gamma-rays emitted by the soil to determine the soil moisture content. Natural radionuclides emit radiation that is detected by this gamma Soil Moisture Sensor (gSMS). Gamma-rays are attenuated by moisture in the soil and therefore the flux of gamma photons could act as a proxy for the amount of moisture present in the soil. Preliminary results show that the total gamma flux seen by the sensor is also influenced by variations in atmospheric radon concentrations. Therefore, the total gamma count cannot be used as a proxy for soil moisture and spectral analysis is needed to filter out the radoninduced noise and correlate the 40K and 232Th concentration with the soil moisture content. Static measurements have been initiated to determine the accuracy needed for establishing the soil moisture content variation over time.

PRESENTER

Steven van der Veeke
University of Groningen (RUG), Medusa Radiometrics, The Netherlands

ABSTRACT

We present a study of the performances of a proximal gamma-ray ground station based on a 7 months continuous acquisition, including 42 rain episodes and 16 irrigations. In particular, we demonstrate the reliability of the station in discriminating irrigations and rains through their peculiar gamma signals fingerprint. This proof of concept experiment shows that proximal gamma-ray spectroscopy can potentially fill the spatial gap between punctual and satellite soil water content measurements, as well as provide an unbiased approach for producing comprehensive irrigations maps.

PRESENTER

Andrea Serafini
University of Ferrara, Italy

ABSTRACT

Cosmic-ray neutron sensing (CRNS) has been established as a reliable method to estimate non-invasively field average soil moisture. Most of the detectors are, however, based on expensive or toxic materials providing some limitations for a wider application of the method. In this study we further test and develop a new neutron detector based on composite scintillators specifically designed for agro-hydrological applications called CRNS-Finapp. It is shown that the probe is very sensitive to the temperature, however, the effect can be easily compensated by the high voltage module embedded in the probe. Field experiments conducted at a vineyard also support the capability of this new detector to be integrated in long-term observation networks. Further developments will focus on improving the efficiency of the neutron counting rate, on the reduction of the power consumption and on the communication protocols for the transmission of the data.

PRESENTER

Gabriele Baroni
University of Bologna, Italy

ABSTRACT

Accurate near-surface soil moisture (θ; ~ 5 cm) estimation is one of the most crucial challenges in agricultural management and hydrological studies. This study aims to map θ at high spatiotemporal resolution (17 m grid size, satellite overpass of 6 days) in a small-scale agroforestry experimental site (~ 30 ha) in southern Italy. The observation period is from November 2018 until March 2019. We employed an ensemble machine-learning method based on Random Forest (RF) to map θ. This RF method is based on three input data types: i) Sentinel-1 (S1) Synthetic Aperture Radar (SAR) measurements, ii) terrain features, and iii) supporting values of sparse point-scale θ simulated in HYDRUS-1D. We propose two different approaches to obtain supporting θ simulations via inverse modeling in HYDRUS- 1D. The first approach is based on θ simulated in HYDRUS- 1D, which was calibrated on soil moisture data monitored at two soil depths of 15 cm and 30 cm over 20 positions belonging to the SoilNet wireless sensor network installed in the experimental site. The second approach is based on the downscaling of field-scale θ simulated in HYDRUS-1D which was calibrated on Cosmic-Ray Neutron Probe (CRNP) data. The field-scale θ was downscaled in order to obtain sparse point-scale supporting θ over the same 20 positions by using the physical-empirical Equilibrium Moisture from Topography (EMT) model. The CRNP-based approach performed similarly to the one based on SoilNet data. Therefore, this study highlights the enormous potential for modeling reliable θ maps by integrating soft data such as S1 SAR-based measurements, topographic information, and CRNP data, having the advantage of being non-invasive and easy to maintain.

PRESENTER

Aida Taghavi Bayat
University of Würzburg, Germany

ABSTRACT

While the world’s population rises, demand for food grows accordingly. Smart agriculture emerges as a viable solution to increase the quality and efficiency of crops. Irrigation plays an essential role in the grade and productivity of harvests, while also being a crucial factor in the costeffectiveness of food production. Smart irrigation uses technology to improve watering, such as the Internet of Things (IoT) applications and Machine Learning algorithms. The correct functioning of irrigation nozzles is critical to ensure that the hydration plan is deployed correctly to the crop field. This paper presents a Machine Learning algorithm that can automatically recognize water from aerial footage of irrigation systems. This automatic recognition can help in the irrigation system inspection, potentially reducing time and cost in system maintenance. Initial results show that it is possible to identify water on image frames captured by an Unmanned Aerial Vehicle (UAV) using the Mask R-CNN Neural Network. The goal is to identify malfunctioning irrigation systems that can lead to under or overwatering, compromising the irrigation plan's correct implementation.

PRESENTER

Caio Koenigkom Galdino de Albuquerque
Federal University of ABC - UFABC, Brazil

ABSTRACT

This research aims at understanding and analyzing the possible effect of climate change on the seasonal rainfall regime over Italy. First, rainfall patterns are identified by applying a clustering procedure based on the Self-Organizing Map, by adopting and comparing the results of different gridded datasets describing current climate (1981-2010). Second, for the identified clusters the impact of climate change in the near (2021-2050) and the far future (2051-2080) is assessed by employing an ensemble of bias-adjusted EURO-CORDEX climate projections under the Representative Concentration Pathways (RCP) 2.6, 4.5 and 8.5. The results of this study show that, for the considered models’ ensemble, a significant decrease in cumulative rainfall values should be expected in the future, reflecting in a decrease in monthly values across all the seasons.

PRESENTER

Giuseppe Francesco Cesare Lama
University of Napoli Federico II, Italy

ABSTRACT

Water availability is strongly variable in space and time, also due to the climate change. Agriculture is a sector specially affected by the water scarcity problem considering that is one of the main users. Irrigation scheduling simulation models play an important role in this context by estimating plant water requirements and supporting best water management practices. Representative model parameters and input data are however fundamental to achieve good model performances. The objective of this work was to assess the sensitivity of the agrohydrological model CRITERIA-1D to the leaf area index (LAI) parameter, commonly used to characterize the plant status and to represent its developing stages. The model has been set up using, on the one hand, literature LAIMAX and LAIMIN values and, on the other hand, ground measured values, obtained by means of a ceptometer. Results show significant differences between the irrigation water requirements estimated between the two scenarios. For this reason, the study underlines the need to adopt accurate crop parameters and to integrate real-time crop measurements for the estimation of the irrigation water requirement. Smaller differences are quantified, however, when looking at the deep percolation estimated by the model highlighting the importance of considering multiple outputs for a comprehensive assessment of the model.

PRESENTER

Tamara Ricchi
University of Bologna, Italy

ABSTRACT

This study explored the possibility to optimize irrigation scheduling through the integrated use of crop data derived from multispectral satellite imagery and an agrohydrological model. The study was conducted with reference to an industrial tomato crop in an irrigated open field. Three methods for estimating irrigation needs were compared: estimates obtained with a calibrated AquaCrop model; estimates obtained by applying the AquaCrop model with sequential assimilation of crop cover retrieved from multispectral images; estimates obtained with the IRRISAT irrigation advisory service, based only crop state parameters retrieved from satellite multispectral images. The results confirm the usefulness of integrating agro-hydrological models and satellite observations to improve the prediction of crop water requirements. The agro-hydrological model offers more reliable estimates of the water irrigation requirements in the early stages of crop development, being able to simulate the effect of evaporative losses from the soil, when the canopy cover is still small. On the other hand, satellite data allows reducing model simulation errors in the most advanced stages of crop development and during senescence.

PRESENTER

Giovanni Battista Chirico
University of Naples Federico II, Italy

ABSTRACT

Agriculture represents one of the most water demanding sectors and its role is central on defining water saving policies. In this work, we propose an improved approach to the irrigation scheduling problem, reducing water wastage while satisfying farmers’ demands and crops’ water needs. For water distribution system managed with on-demand distribution approach, the efficiency of irrigation relies on the ability of the network manager (i.e., gatekeeper) to guarantee a proper service, consisting in: the irrigation scheduling, the definition of the volume of water passing through the channels at a given time, and the operations on gates and sluices to make the water reach the farms. Consequently, the irrigation scheduling inefficiencies might be limited by: i) reducing the water wastage, ii) minimizing the gatekeeper work and iii) maximizing the satisfaction of the farmers’ requirements. We propose an improved mixed-integer linear optimization formulation that adds the possibility to store water in the channels and takes seepage into account. This new formulation is able to better represent the physical behavior of the water flow in the channels network, also avoiding the presence of flooding. The proposed optimization solution is embedded within a wider monitoring framework with the intent to fully exploit the availability of a complex network of models, repositories and sensors installed in the field. The resulting problem is solved by one of the most used optimization solvers (IBM ILOG Cplex) and tested on a synthetic benchmark. Furthermore, we validate the results on a digital copy of the network that performs a hydraulic simulation of the irrigation system. The scheduling is accepted if the water introduced in the system can satisfy farmers’ requests with the considered timing and does not produce flooding.

PRESENTER

Vittorio Latorre
University of Bologna, Italy

ABSTRACT

In smart agriculture, the Internet of Things (IoT) makes it possible to analyze and manage agricultural yield to increase productivity, reduce wasted resources, and decrease irrigation costs. In IoT systems, if data management is entirely performed in the cloud, the system may not work correctly due to connectivity problems, which is common in some remote regions where the agribusiness thrives. A fog computing solution enables the IoT system to process data faster and deal with intermittent connectivity. However, a high number of packets sent from the fog to the cloud can cause link congestion with mostly useless data traffic. Dealing with fog data filtering is a challenge because it requires knowing which data is essential to send to the cloud. This paper proposes an approach to collect and store data in a smart agriculture environment and two different methods filtering data in the fog. We designed an experiment for each filtering method, using a real dataset containing temperature and humidity values. In both experiments, the fog filters the data using the k-Nearest-Neighbors (kNN) algorithm, which classifies data into categories according to their value ranges. In the first experiment, the fog classifies the data and generates an output of the number of data categories. In the second experiment, data is classified and also compressed based on the previously obtained categories using the run-length encoding (RLE) technique to preserve the data time series nature. Our results show that data filtering reduces the amount of data sent by the fog to the cloud.

PRESENTER

Franklin Magalhães Ribeiro Junior
Federal University of ABC - UFABC, Brazil

ABSTRACT

Smart agriculture is increasingly seen as a solution to global sustainability problems such as global warming, waste of water resources, excessive use of pesticides, and low economic activity. The core of this technology is the acquisition of data from the soil, crop, and climate to act in the production. Several solutions exist, but many are proprietary, high cost, hard to install, maintain, and integrate with third-party solutions. This paper presents an IoT technology set applied to the acquisition of agricultural data using open source solutions such as FIWARE and LoRaWAN, which allow extensive customization and integration with advanced weather forecasting, Machine Learning, and real-time dashboard services. The results obtained by the combination of different tools and platforms in pilots located in Brazil and Europe reveal a high versatility of the IoT technology applied to smart agriculture.

PRESENTER

Alexandre Heideker
Federal University of the ABC, Brazil

ABSTRACT

As LoRaWAN has been increasingly used in the Internet of Things (IoT) smart agriculture, efficacious deployments of this technology need a clear understanding of its performance and scalability tradeoffs. This paper proposes a two-step methodology to evaluate the performance of LoRaWAN based on simulation for understanding the behavior of the air interface and measurement for understanding the behavior of the IoT Platform. We conducted a performance analysis study in a smart irrigation scenario, varying the distance from sensors to the gateway, the sensor density (number of sensors), and the LoRaWAN spreading factor. Our results show that the LoRa air interface poses the most stringent scalability limits, mainly related to the number of sensors actively transmitting from a farm parcel to the gateway. The IoT Platform adds some delay but does not notably interfere with the overall performance of the solution.

PRESENTER

Carlos Kamienski
Federal University of ABC, Brazil

ABSTRACT

Smart farming is an emerging and important application of the Internet of Things (IoT) technology. This paper describes a multi-depth and multi-parameter probe for soil data collection utilized to on-farm research by the SWAMP project. The probe is based on LoRaWAN communication and has sensors for soil moisture, temperature, and electrical conductivity. The network infrastructure to deliver data to a cloud platform is also discussed. The combined solution was deployed in two pilots in Brazil to assess smart irrigation in drip and center pivot systems. The initial data collection shows the effectiveness of the solution, which is suitable to other smart farming processes.

PRESENTER

Jeferson Rodrigues Cotrim
Federal University of ABC, Brazil

ABSTRACT

The emergence of concepts such as Internet of Things, Cloud Computing has been adding improvements in different sectors of human life activity. The agricultural sector is no exception, and it begins to appear the first systems that use these new concepts, as is the case of, use of drones and associated technology applied to fighting pests or the use of sensor networks to monitor productions. However, the technological gap between urban and rural areas is becoming ever wider, and the arrival of these new concepts in rural areas is taking place very slowly. In order to accelerate this technological transformation, it’s necessary to find tools that reduce these differences, leveraging these rural regions in terms of technology and, at the same time, providing access to new markets. In this article is proposed, a solution to the problem of the lack of production flow, allowing producers in low-density regions to access markets that until now would be impossible to reach, while providing an solution to the problem of shortage of labour and the increase in abandoned land in Portugal.

PRESENTER

Rui Alves
IPB, Portugal

ABSTRACT

Smart agriculture requires new hardware and software solutions in order to achieve its goals of improved productivity. The SWAMP project develops a platform for smart water management using IoT, cloud and fog computing, and machine learning, among other technologies. This paper presents the SWAMP Farmer App for water status monitoring and irrigation control. The app improves farmer’s situation awareness regarding water status by showing current and past moisture data from the fields, including map and charts views. The app also includes irrigation planning and drone capabilities.

PRESENTER

Milton Gama Neto
Universidade Federal de Pernambuco, Brazil

ABSTRACT

This paper describes an application for the context aware tuning of the data rate of a battery powered LoRaWAN multi-sensor node equipped with sensors measuring soil features like water content, temperature, conductivity, moisture and water table depth. The application aims at saving as much power as possible, granting at the same time the detection and accurate profiling of events localized in time and space (e.g., due to sudden heavy rain). The tuning rules are based on the interplay between the context heterogeneous actors (sensor data, forecasts, current season, irrigation requests) mediated by a Linked Data distribution platform interconnected to multiple private and public networks. An interoperable application is provided, whose components can be easily extended and reused.

PRESENTER

Simone Sindaco
ARCES - University of Bologna, Italy

ABSTRACT

Emerging technologies, such as Digital Platforms, Internet of Things, remote sensing and Big Data, are going to significantly influence the achievement of the 17 Sustainable Development Goals (SDGs) targets, pursued by all United Nations Member States starting from 2015. As the whole agricultural sector is transforming in a more knowledgeintensive system, precision agriculture could play a significant role to achieve the SDGs, by reducing environmental impacts of agriculture and farming practices, increasing the profitability of the farm and thus improving the quality of life for farmers Based on these premises, the aim of this article is to present VITIS, a digital platform, for the management of vineyard water and nitrogen stress, developed by the Operational Group SMART VITIS and tested in 4 pilots located in Marche Region. All the functions and modules of the platform were built by following a Design Thinking approach. This approach started from the analysis of the needs of the winegrowers, the end-user of the solution. While a focus group, made of agri-experts was conducted to receive feedback from the test phase of the platform. This study illustrates how this approach can be a useful tool to develop targeted digital solutions for farmers with low digital skills.

PRESENTER

Giorgia Bucci
Università Politecnica delle Marche, Italy

ABSTRACT

Knowledge on the effect of behavior and welfare on dairy cattle’s health and production has been increasing, highlighting the need of satisfactory animals’ living conditions. Among others, the lying time represents a signal for health and welfare status as well as for milk production. In this study, a one-year test on primiparous cows on a dairy cattle farm in Northern Italy was carried out in order to evaluate the effect of lying time on other variables and vice versa. Accelerometers and environmental sensors were installed on animals and in the barn. Weather data were collected from a data station on farm. Statistical analyses were carried out to identify the effect among the monitored variables, showing interesting results on behavior and production of dairy cattle. In particular, the behavior in the first weeks of the lactation period affects the behavior and milk production during the whole lactation.

PRESENTER

Daniela Lovarelli
University of Milan, Italy

ABSTRACT

Irrigation advisory services (IAS), as well as decision supports systems (DSS) designed for irrigation support, are powerful management instruments used to improve efficiency in irrigation water use. In this context, a preliminary research was conducted in an open field asparagus crop in order to: evaluate Ploovium, a DSS based on IoT, artificial intelligence and machine learning, for a predictive optimization of irrigation. This study was carried out in collaboration with LAORE (Agricultural Development Regional Agency of Sardinia Region), and AGRIS Research Centre, on an asparagus in a farm in Villasor (CA). Experimental activities were carried out from August 01 2018 to July 24 2019. Ploovium is an innovative cloud-based solution, able to produce provisional data on the soil’s water behaviour by the following equipment: i) a weather station for measuring rain, air temperature and humidity; ii) a datalogger with soil water sensors at two different depths (30 cm and 80 cm). Ploovium allowed to optimize water consumption and, consequently, to manage the crop in a more efficient way, and to prevent any possible risk with a degree of reliability normally higher than 99%. Ploovium has proved to be a low cost and know-how solution to support the users to save water and irrigation-related costs and to provides precise hints about the texture of the soil.

PRESENTER

Andrea Martelli
Soonapse s.r.l

ABSTRACT

The world-wide development and spread of water-saving techniques and new rice genotypes to reduce water consumption and increase water productivity (i.e. the amount of rice produced per unit of water) is crucial for maintaining or even increasing rice production area in several regions. The utilization of varieties adapted to aerobic conditions and the application of precision agriculture technologies could maintain yield levels and optimize water use. Rice cultivation under drip-irrigation could represent an opportunity for farmers but needs to be assessed in field experiments. A field experimentation trial comparing the growth, yield and water use efficiency of rice (Oryza sativa L.) varieties under drip irrigation was established in Maremma Toscana, Italy. The results of the first year of experiment at the Grosseto (GR) site showed that the drip irrigation technique could maintain high production level for most of the varieties evaluated, but with significant differences in terms of milling yield. The assessed farm water consumption for rice cultivation seems high and water use could be optimized through water balance assessment.

PRESENTER

Stefano Monaco
CREA, Italy

ABSTRACT

The present study investigates the microclimatic effect of trees in agroforestry systems in Dodoma region, Tanzania. A pixel-based analysis of Land Surface Temperature (LST) and Tree Canopy Cover (TCC) was performed on aerial imagery obtained with an Unmanned Aerial Vehicle (UAV) and on satellite data. UAV orthomosaic maps and satellite scenes were elaborated with a suite of Geographical Information Systems and the resulting data were statistically analyzed through linear regression, the Kruskall-Wallis test and the Dunn test. Results showed that the TCC of the surveyed areas was 5,1%, and a significant decrease in LST of 1,32 °C (p<0,01) was only found in areas with the highest TCC, during the late dry season. From these preliminary analyses, we suggest that a threshold of 10% TCC should be reached to have an ameliorated microclimate, in terms of temperature, in this agroecological zone. Considering the average plant phenotype characteristic to the area, it corresponds to a tree density of 50 trees per hectare.

PRESENTER

Lorenzo Villani
University of Florence, Italy

ABSTRACT

During the manure storage, ammonia (NH3) and methane (CH4) emissions play an important role in the optimization of manure management of a farm. Different cover types were studied over the years: natural or composite materials; permanent or not. Quite recently, there has been a growing interest in biochar cover application on the storage tanks. Differently from other types of organic cover, biochar is able to capture target nutrients; nevertheless, more studies are needed to understand the mechanism of release when applied to the field together with manure as fertilizer. The aim of this study was to assess biochar absorbing capability while reducing ammonia (NH3) and methane (CH4) emissions simulating storage conditions. Results show that biochar is a promising floating cover for manure storage, which reduces emissions acting as a physical barrier.

PRESENTER

Ester Scotto di Perta
University of Naples Federico II, Italy

ABSTRACT

Several gases contribute to air pollution and most of all to the formation of secondary particulate matter (PM2.5), which is recognized as a source of severe risk to human health. Even if huge steps forward have been done worldwide, traffic, industrial activities, and the energy sector are mostly responsible for the release of NOx and SOx, while the agricultural sector is mainly responsible for the emission of NH3 deriving from the barn, the manure storage, management and final field application. In this study, the emission of PM2.5, NOx and NH3 is analyzed in the main provinces of the Lombardy region in which livestock activities are carried out, comparing emissions of 2016-2019 and those of 2020 during the lockdown determined by the spread of Covid-19 disease. The aim is to understand if and how a change in air emissions can be identified. The results show that PM2.5 and NOx reduced, most of all in urban areas, whereas NH3 maintained the same trend of previous years. From the statistical analysis emerges also that NH3 has a different behavior respect to PM2.5 and NOx, these latter being much more correlated between each other than NH3. However, further studies should be carried out on a bigger spatial and temporal scale.

PRESENTER

Daniela Lovarelli
University of Milan, Italy

ABSTRACT

Digestate is an important source of nutrients for crops but if not properly managed its use can cause environmental problems, mainly caused by nitrogen losses. Appropriate techniques are required for its field application in order to reduce nitrogen losses and increase the nitrogen use efficiency (NUE). Under the ARIMEDA project (LIFE16 ENV/ES/000400), two different fertigation techniques (drip and pivot irrigation systems) were assessed on maize by using the digestate liquid fraction. A two-year field test was carried out in Lombardy, testing fertigation with pivot or drip systems compared to reference fields irrigated using the same systems and fertilized with digestate applied at base dressing with broadcast spreader. Both pivot and drip irrigation systems were suitable for fertigation of maize with digestate. The obtained results reveal the feasibility and the positive effect on nitrogen use efficiency and nitrogen emissions of this technique, if digestate is properly managed, adequately filtered according to the fertigation technique and combined with appropriate spreading technique in pre-sowing fertilisation.

PRESENTER

Alberto Finzi
Università degli Studi di Milano - DiSAA, Italy

ABSTRACT

Agriculture is the cause of almost the 95% of total ammonia (NH3) emissions in Europe, where livestock manure and fertilizers are the main emitters. In Italy, manure management represents about the 46% of the total NH3 losses from the agricultural activities. The environmental impacts are greater in areas with high livestock density, where nutrient application rates on fields often exceed the crop uptakes. Mechanical separation of slurry into its solid and liquid components is widely used to ease the transport of nutrients surplus outside livestock dense areas towards livestock-free plantations. However, mechanical separation may increase greenhouse gases (GHG) and NH3 emission mainly due to high emissions during the solid fraction storage. The main objective of this research has been evaluating the effect of acidification by adding elementary sulfur (S) before slurry mechanical separation. Ammonia and GHG emissions were monitored during storage of raw slurry, solid and liquid fraction.

PRESENTER

Elio Dinuccio
DISAFA - University of Turin, Italy

ABSTRACT

Mitigating ammonia emissions from the livestock sector offers the opportunity to combine environmental protection with resource recovery through emerging circular bioeconomy approaches. In this work, we tested the potential of low-rate stripping techniques to enable techno-economically feasible nitrogen recovery and valorization from buffalo manure digestate. The proposed process achieved more than 80% ammonia stripping at mild temperatures (35-55 °C) and without the need of caustic agents to increase pH. Coupling such low-rate ammonia stripping with innovative biological resource valorization processes could offer interesting future perspectives.

PRESENTER

Silvio Matassa
University of Cassino and Southern Latium, Italy

ABSTRACT

Manure spreading is one of the main source of ammonia (NH3) emissions in the livestock sector, which is responsible of the 75 % of anthropogenic NH3 losses. For liquid manure, the most effective distribution technique to abate NH3 emissions is direct injection, which allows for a NH3 emission abatement up to 90 %. Nonetheless, direct injection has been shown to potentially increase, under certain environmental conditions, nitrous oxide (N2O) emissions from soil after slurry spreading. The aim of this study is to assess the effect of the commercial nitrification inhibitor N-LockTM (CORTEVATM agriscience) on NH3 and N2O emissions after spreading of two different slurry types. The product was tested in a field trial on two different soils (loam and sandy-loam) and in combination with two different types of manure (cattle slurry and digestate). The N-LockTM product appears to have a good potential for N2O emission reduction from fields after slurry spreading with direct injection techniques. Nonetheless, proper emission abatements (up to 79 %) were obtained only in one of the two soils included in the study and N-LockTM efficiency differed depending also on slurry type.

PRESENTER

Jacopo Maffia
University of Turin, Italy