DEEP LEARNING FOR SUSTAINABLE PRECISION AGRICULTURE
Embedded Files
ABSTRACT
In recent years, precision agriculture has pushed the boundaries of technology to optimize crop production, improve the efficiency of farming operations, and reduce waste.
Deep learning techniques have shown great potential for enhancing precision agriculture by analyzing large volumes of data and providing insights into crop health, soil quality, and environmental factors. Besides extracting relevant crop information, visual-based algorithms are increasingly developed for autonomous navigation tasks in crops.
One of the main advantages of deep learning in precision agriculture is its ability to analyze data from multiple sources, allowing for large-scale, high-resolution monitoring of crops, which can provide detailed information for both human and robotic agents. The most recent advancements in deep learning provide competitive advantages such as fast inference, model optimization for low-power embedded hardware, and generalization from synthetic to real data.
Agriculture is a highly energy-intensive industry, and there is a pressing need to address the challenges faced by the energy sector. Improving farming practices is important to making agriculture more sustainable, e.g., integrating renewable energy into the agriculture sector, reducing waste, improving farm efficiency, etc. Artificial Intelligence and deep learning are expected to play an important role in improving sustainability in agriculture.
THE WORKSHOP
The workshop will take place in conjunction with this year's European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases.
It is designed for researchers, practitioners, and students interested in leveraging deep learning techniques for precision and sustainable agriculture. It will provide a platform for participants to network and collaborate with experts in the field and gain insights into the latest trends and advancements in deep learning for precision agriculture.
The workshop will cover topics like crop segmentation, plant disease detection, yield prediction, fruit counting, weed remotion, soil moisture monitoring, renewable integration, and energy management using AI using deep learning techniques.
Participants will be introduced to real-world problems in precision and sustainable agriculture and the application of deep learning models to solve them. They will also learn about the challenges and limitations of this approach and explore potential solutions.
The workshop will be a bridge between the academic world and companies in the field of precision agriculture that will present the latest applications of deep learning in their research and development projects.
CALL FOR PAPERS
TARGET PARTECIPANTS
Computer scientists and engineers
Data scientists and statisticians
Robotic engineers
Remote sensing and Geographic Information Systems experts
Professionals working in precision agriculture and agribusiness
Agricultural scientists and engineers
GUIDELINES
We invite researchers and practitioners to submit papers on deep learning for precision/sustainable agriculture. The papers will be reviewed by the workshop organizers, and the authors of the selected papers will be invited to briefly present the works and take part in the following poster session.
Demos associated with posters will also be encouraged by the workshop organizers to promote the participants' practical first-person involvement. Demos will be held in the second part of the workshop schedule and organized according to the requests received in parallel with the poster session.
DEADLINES
Paper Submission Deadline: June 30th, 2023!
Paper Author Notification: 12 July 2023
SUBMISSIONS
We welcome theoretical or empirical contributions describing ongoing projects or completed work. The papers should be prepared and submitted using the conference template. The maximum length of papers is 10 pages excluding references.
Electronic submissions will be handled via CMT:
https://cmt3.research.microsoft.com/ECMLPKDDworkshop2023/
Before submitting, please select the track "Deep Learning for Precision Agriculture" (see the top of the page). The track of choice can be indicated in the submission form.
PROCEEDINGS
The accepted papers will be included in a Post-Workshop proceeding published by Springer Communications in Computer and Information Science.
Papers authors will have the faculty to opt-in or opt-out. More information at CCIS web page.
PROGRAM
TIME
TIME
8.30 - 9.00
9.00 - 9.25
9.25 - 9.50
9.50 - 11.00
11.00 - 11.30
11.30 - 11.55
11.55 - 12.20
11.20 - 12.40
12.40 - 13.00
EVENT
EVENT
Introduction
Keynote 1
Keynote 2
Poster Session
Coffee Break
Keynote 3
Company
Presentation 1
Company
Presentation 2
Conclusive Speech
SPEAKER
SPEAKER
Karl Mason
Mauro Martini (PoliTo)
Matteo Matteucci (PoliMi)
Selected Authors
-
Karl Mason (University of Galway)
Fabrizio Romanelli (CNR)
Andrea Magnano (Nabu)
Workshop Organizers
TITLE
TITLE
-
Deep Learning for a Complete Autonomous
Navigation Pipeline in Row-based Crops
Agricultural Robotics at Politecnico di Milano
Artificial Intelligence and Robotics Lab
-
-
Integrating Renewables Within the Dairy Farming Sector
Synthetic Sensor Data Generation for Precision Agriculture:
a Deep Learning Approach
Revolutionizing Precision and Variable Rate Approach
to Agriculture: Nabu's IoT and Satellite Data Integration
-
ACCEPTED PAPERS
"Plant Disease Detection using Deep Learning: A Proof of Concept on Pear Leaf Disease Detection", Gianni Fenu (University of Cagliari), Francesca Maridina Malloci (University of Cagliari), Marcello Onorato (Agenzia LAORE Sardegna), Marco Secondo Gerardi (Agenzia LAORE Sardegna).
"Lavender Autonomous Navigation with Semantic Segmentation at the Edge", Alessandro Navone (Politecnico di Torino), Fabrizio Romanelli (University of Rome Tor Vergata), Marco Ambrosio (Politecnico di Torino), Mauro Martini (Politecnico di Torino), Simone Angarano (Politecnico di Torino), Marcello Chiaberge (Politecnico di Torino).
"Modelling Solar PV Adoption in Irish Dairy Farms using Agent-Based Modelling", Iias Faiud (National University of Ireland Galway), Karl Mason (University of Galway), Michael Schukat (National University of Ireland Galway).
"Deep Networks based Approach for Automatic Counting Panicles on UAV captured Paddy RGB Imagery", Tejasri Nampally (Indian Institute of Technology Hyderabad Telangana India), Sam Mathew Betson (Indian Institute of Technology Hyderabad), Rajalakshmi Pachamuthu (Indian Institute of Technology Hyderabad), Balram Marathi (P.J.T.S. Agricultural University). Uday B. Desai (Indian Institute of Technology, Hyderabad, India).
"The ACRE Crop-Weed Dataset for Benchmarking Weed Detection Models on Maize and Beans Fields", Riccardo Bertoglio (Politecnico di Milano), Eli Spizzichino (Università di Bologna), Anne Kalouguine (LNE), Giuliano Vitali (Università di Bologna), Matteo Matteucci (Politecnico di Milano).
"Integrating Renewable Energy in Agriculture: A Deep Reinforcement Learning-based Approach", Abdul Wahid (University of Galway), Iias Faiud (University of Galway), Karl Mason (University of Galway).
WORKSHOP COMMITTEE
MARCELLO CHIABERGE
MARCELLO CHIABERGE
Marcello Chiaberge is an Associate Professor of the Department of Electronics and Telecommunications at Politecnico di Torino (Turin, Italy). At the same university, he is also the Mechatronics Lab (LIM) Co-Director and Director and Principal Investigator of the Interdepartmental Center for Service Robotics (PIC4SeR). He has authored over 100 articles accepted in international conferences and journals and co-authored nine international patents. His research interests include the hardware implementation of neural networks and fuzzy systems and the design and implementation of reconfigurable real-time computing architectures.
MATTEO MATTEUCCI
MATTEO MATTEUCCI
Matteo Matteucci is a full professor of the Department of Electronics, Information, and Bioengineering at Politecnico di Milano, Italy. He got a Ph.D. in Computer Engineering and Automation at the same university in 2003. His main research topics are pattern recognition, machine learning, machine perception, robotics, computer vision, and signal processing. His main research interest is developing, evaluating, and applying practical techniques for adaptation and learning to autonomous systems that interact with the physical world. He has co-authored more than 150 international scientific publications. He has been the principal investigator in national and international research projects on machine learning, autonomous robots, sensor fusion, and benchmarking of autonomous and intelligent systems.
MARCO PIRAS
MARCO PIRAS
Marco Piras is a full professor in Geomatics at Politecnico di Torino, Deputy of the Department in Environment, Land and Infrastructure Engineering at Politecnico, and Director of the second-level specialization master in Climate change at Politecnico di Torino. He is a member of the National Center for Agricultural Technologies (Agritech). He has been part of several scientific committees at national and international conferences, and he has organized several summer schools and scientific workshops. He teaches several geomatics, positioning, photogrammetry, remote sensing, and statistics courses. He is the author of more than 130 scientific papers and is involved in several national and international projects, even concerning smart farming and AI.
RENATO FERRERO
RENATO FERRERO
Renato Ferrero is an Associate Professor of the Department of Control and Computer Engineering at Politecnico di Torino, Italy. His research interests concern ubiquitous computing, focusing on RFID systems and wireless sensor networks. He is involved in research activities and projects on precision farming concerning designing smart systems for crop monitoring and image processing to compute plant health indices. He is a member of the National Research Centre for Agricultural Technologies (Agritech).
KARL MASON
KARL MASON
Karl Mason is a tenured Assistant Professor in the School of Computer Science at the University of Galway, Ireland. He is the Principal Investigator on multiple projects and leads a research group of 9 funded researchers in Galway. His research focuses on machine learning and encompasses a range of topics, such as neural networks, evolutionary computing, reinforcement learning, multi-agent systems, and swarm intelligence. He is also interested in the application of machine learning methods to solve problems related to renewable energy, smart homes, infrastructure planning, smart grid, robotics, and agriculture.
ABDUL WAHID
ABDUL WAHID
Abdul Wahid is a Postdoctoral Researcher at the School of Computer Science, University of Galway, Ireland. Prior to his appointment at Galway, he held positions as a Research Engineer at the UHA, France, and a Postdoctoral Fellow in the INFRES department at Telecom Paris, IP Paris, France. His research interests focus on AI, ML, and their applications in various domains. Apart from his research activities, he is actively organizing several academic events. He is currently organizing a workshop at ECAI 2023 in Poland, a special track session at the RTIP2R 2023 at the University of Derby, UK, and a special track at the BESC 2023 in Cyprus. In addition, he is a guest editor for many journals and served as a PC member at many reputed conferences.
SIMONE ANGARANO
SIMONE ANGARANO
Simone Angarano is a Ph.D. student in Electrical, Electronics, and Communications Engineering and a member of the Interdepartmental Center for Service Robotics at Politecnico di Torino (PIC4SeR). At the same university, he achieved a Bachelor's Degree in Electronic Engineering in 2018 and a Master's Degree in Mechatronic Engineering in 2020. His research topic is efficient deep learning models for robot perception and control, particularly highlighting key aspects of real-world applications like generalization and robustness.
MAURO MARTINI
MAURO MARTINI
Mauro Martini is a Ph.D. student in Electrical, Electronics, and Communication Engineering at Politecnico di Torino. He received from the Politecnico di Torino a Master's Degree cum laude in Mechatronic Engineering in 2020, with the thesis "Visual-based local motion planner with Deep Reinforcement Learning". He is now researching with the Interdepartmental Center for Service Robotics (PIC4SeR). His research interests currently involve machine learning for autonomous navigation in service robotics, focusing on perception and deep reinforcement learning based on planners.
CONTACTS
Please contact us for any questions or doubts regarding the submission process and participation in the workshop.
Simone Angarano, Ph.D. student, Politecnico di Torino: simone.angarano@polito.it
Mauro Martini, Ph.D. student, Politecnico di Torino: mauro.martini@polito.it
Page updated
Google Sites
Report abuse