Prof. Fuentes is the leader of the Digital Agriculture, Food and Wine Sciences Group (DAFW) and his main research and teaching interests are related to the use of state-of-the-art instrumentation for plant physiology and agricultural research, such as short range, airborne, satellite remote sensing, robotics and unmanned aerial vehicles (UAV). Recent advances made by Prof. Fuentes are in the area of artificial intelligence (AI) applied to Digital Agriculture through the development of computer programs for agricultural research and practical applications, development of new methodologies to assess plant physiology and growth using computer vision and machine learning (ML). He is the international coordinator for The Vineyard of The Future Initiative (VoF), which is a multinational collaboration to establish a fully instrumented model vineyard for climate change research (www.vineyardofthefuture.com).
The Digital Agriculture, Food and Wine Sciences group (DAFW) belonging to The Faculty of Veterinary and Agricultural Sciences (FVAS) from The University of Melbourne have been working on the implementation of Digital tools in Agriculture. These tools include remote sensing using satellite and unmanned aerial vehicles (UAVs); short range and proximal remote sensing using computer applications (Apps), robotics, biological (trained dogs) and digital sensor technology and sensor networks to monitor the Soil-Plant-Atmosphere (SPA) interactions; implementation of the Internet of things (IoT) for data gathering, storage and communication (Figure 1). Data analysis is performed mainly through signal analysis, computer vision and Machine Learning (ML) to obtain supervised and unsupervised learning models for data analysis and decision making. Model accuracies obtained by the DAFW group and published in peer-reviewed journals are higher than 85%, with many over 90% in the prediction of many important factors that are critical for decision-making from the farm to the consumer’s palate.
An important aspect of this system is that targeted consumers can be assessed using AI systems developed (Bio-sensory App and ML modelling) to obtain liking and sensory analysis of specific produces. These results can be used as feedback to the farm production to assist management related to for example irrigation scheduling, canopy management and fertilization to obtain a consistent produce for a specific market (Figure 1).
Figure 1: Implementation and integration of digital tools from the farm to the consumer’s palate developed by the Digital Agriculture, Food and Wine group (DAFW). University of Melbourne. Ground truthing is important (left) using state of the art technology such as infrared thermal imagery (IRTI), near infrared spectroscopy (NIR), gas chromatography-mass spectrometry (GCMS) and physiological assessment. Remote sensing and applications developed using biological and digital sensor technology (up). Information from the bio-Sensory App (right) can be used as feedback to the farm to manage produce quality based on targeted consumer appreciation and liking.
The most important and relevant applications developed by the DAFW group can be summarized as follows:
VitiCanopy App: A smartphone and tablet PC application (iOS and Android systems) that uses upward-looking photography from canopies of grapevines and fruit and forestry trees to assess leaf area index (LAI) and other canopy architecture parameters through computer vision algorithms (Figure 1) [1-5]. This App has been used around the world for research, management and teaching purposes.
Object Analyser App: A computer code based on computer vision and machine learning to assess morpho-colorimetric and fractal analysis to assess the complexity of objects. This code has been applied to grapevine leaves and medicinal plant leaves to classify them according to varieties. It can be used to other objects, such as dry fruits, nuts, rice and olives among others to extract information for classification purposes or quality assessment using machine learning [6,7].
Water Stress Mapping: Implementation of infrared thermal and multispectral imaging from proximal and Unmanned Aerial Vehicles (UAV) remote sensing to assess plant water status for irrigation purposes using computer vision and machine learning modelling [8,9].
Smoke Contamination and Taint in Wines: Digital tools to assess the effect of bushfires and smoke contamination in grapevine canopies and smoke taint in wines using remote sensing and machine learning [10-12].
Big Data for Grape and Wine Quality: Assessment of big data from vertical vintages to determine wine quality. Big data was assessed from weather and vineyard water management to predict aroma profiles, sensory of wines and chemometrics with high accuracy (>95%) for determined vineyards [13].
Sniffer Dogs with Inspector Paw App: Development of a smartphone application for dogs to detect pest and diseases and to map detection within crop fields. This app uses sensor information from mobile phones and GPS location to detect and map detection gestures from dogs trained for specific stimuli using machine learning modelling.
Robotic Pourers for Sparkling Wine and Beer: Development of Robotic pourers coupled with computer vision and machine learning to assess morpho-chemometrics of sparkling wine and beer for quality assessment and consumer preference [14,15].
BioSensory App Algorithms: Computer application to detect non-invasive physiological changes in humans (heart rate, blood pressure, body temperature, posture, emotional response through facial recognition) and animals (heart rate, body temperature, startle, respiration rate). This App has been applied to sensory analysis of food, beverages and packaging for humans and detection of stress and welfare assessment for farm and small animals, such as pets and zoo animals [16-18].
Low-cost Electronic Nose (e-nose): Development of low-cost e-nose for applications on beverages and smoke contamination in vineyards and smoke taint in wines [19]. Future research will be based on this e-nose to assess the presence of pests and diseases in crops.
References
1. Carrasco-Benavides, M.; Mora, M.; Maldonado, G.; Olguín-Cáceres, J.; von Bennewitz, E.; Ortega-Farías, S.; Gajardo, J.; Fuentes, S. Assessment of an automated digital method to estimate leaf area index (lai) in cherry trees. New Zealand Journal of Crop and Horticultural Science 2016, 44, 247-261.
2. Poblete-Echeverría, C.; Fuentes, S.; Ortega-Farias, S.; Gonzalez-Talice, J.; Yuri, A.J. Digital cover photography for estimating leaf area index (lai) in apple trees using a variable light extinction coefficient. Sensors 2015, 15.
3. Fuentes, S.; Palmer, A.R.; Taylor, D.; Zeppel, M.; Whitley, R.; Eamus, D. An automated procedure for estimating the leaf area index (lai) of woodland ecosystems using digital imagery, matlab programming and its application to an examination of the relationship between remotely sensed and field measurements of lai. Functional Plant Biology 2008, 35, 1070-1079.
4. De Bei, R.; Fuentes, S.; Gilliham, M.; Tyerman, S.; Edwards, E.; Bianchini, N.; Smith, J.; Collins, C. Viticanopy: A free computer app to estimate canopy vigor and porosity for grapevine. Sensors 2016, 16.
5. Fuentes, S.; Chacon, G.; Torrico, D.D.; Zarate, A.; Gonzalez Viejo, C. Spatial variability of aroma profiles of cocoa trees obtained through computer vision and machine learning modelling: A cover photography and high spatial remote sensing application. Sensors 2019, 19, 3054.
6. S., F.; E., H.-M.; JM., E.; J., B.; C., G.V.; C., P.-E.; E., T.; H., M. Automated grapevine cultivar classification and water stress assessment based on machine learning using leaf morpho-colorimetry, fractal dimension and near-infrared spectroscopy. Computers and Electronics in Agriculture 2018.
7. Xue, J.; Fuentes, S.; Poblete-Echeverria, C.; Viejo, C.G.; Tongson, E.; Du, H.; Su, B. Automated Chinese medicinal plants classification based on machine learning using leaf morpho-colorimetry, fractal dimension and. International Journal of Agricultural and Biological Engineering 2019, 12, 123-131.
8. Fuentes, S.; De Bei, R.; Pech, J.; Tyerman, S. Computational water stress indices obtained from thermal image analysis of grapevine canopies. Irrigation Science 2012, 30, 523-536.
9. Romero, M.; Luo, Y.; Su, B.; Fuentes, S. Vineyard water status estimation using multispectral imagery from an uav platform and machine learning algorithms for irrigation scheduling management. Computers and electronics in agriculture 2018, 147, 109-117.
10. Fuentes, S.; Tongson, E.J.; De Bei, R.; Gonzalez Viejo, C.; Ristic, R.; Tyerman, S.; Wilkinson, K. Non-invasive tools to detect smoke contamination in grapevine canopies, berries and wine: A remote sensing and machine learning modeling approach. Sensors (Basel) 2019, 19, 3335.
11. S., F.; R., D.B.; E., T.; R., R.; S., T.; K., W. Detection of smoke contamination in grapevine canopies and berries using infrared thermography, near infrared spectroscopy and machine learning. In GiESCO Group of international Experts for Cooperation on Vitivinicultural Systems, Mendoza, Argentina, 2017.
12. S., F.; E., T. Advances in smoke contamination detection systems for grapevine canopies and berries. Wine and Viticultural Journal 2017, 32, 36-39.
13. Fuentes, S.; Gonzalez Viejo, C.; Wang, X.; Torrico, D.D. In Aroma and quality assessment for vertical vintages using machine learning modelling based on weather and management information, Proceedings of the 21st GiESCO International Meeting, Thessaloniki, Greece, 2019; pp 23-28.
14. Condé, B.C.; Fuentes, S.; Caron, M.; Xiao, D.; Collmann, R.; Howell, K.S. Development of a robotic and computer vision method to assess foam quality in sparkling wines. Food Control 2017, 71, 383-392.
15. Gonzalez Viejo, C.; Fuentes, S.; Li, G.; Collmann, R.; Condé, B.; Torrico, D. Development of a robotic pourer constructed with ubiquitous materials, open hardware and sensors to assess beer foam quality using computer vision and pattern recognition algorithms: Robobeer. Food Research International 2016, 89, 504-513.
16. Jorquera-Chavez, M.; Fuentes, S.; Dunshea, F.R.; Warner, R.D.; Poblete, T.; Jongman, E.C. Modelling and validation of computer vision techniques to assess heart rate, eye temperature, ear-base temperature and respiration rate in cattle. Animals 2019, 9, 1089.
17. Jorquera-Chavez, M.; Fuentes, S.; Dunshea, F.R.; Warner, R.D.; Poblete, T.; Morrison, R.S.; Jongman, E.C. Remotely sensed imagery for early detection of respiratory disease in pigs: A pilot study. Animals 2020, 10, 451.
18. Fuentes, S.; Gonzalez Viejo, C.; Torrico, D.; Dunshea, F. Development of a biosensory computer application to assess physiological and emotional responses from sensory panelists. Sensors 2018, 18, 2958.
19. Gonzalez Viejo, C.; Fuentes, S.; Godbole, A.; Widdicombe, B.; Unnithan, R.R. Development of a low-cost e-nose to assess aroma profiles: An artificial intelligence application to assess beer quality. Sensors and Actuators B: Chemical 2020, 127688.
