Talk Abstract:

AI and Machine Learning: Key Roles in the Transformation of American Agriculture

Food and agricultural enterprise today is facing colossal challenges. By 2050, agriculture needs to produce 70% more food over current levels, while minimizing its impact on environment. Not only is the demand for food is growing, but so is the complexity of demand. To meet these grand challenges, transformative changes are occurring in agriculture. The changing face of agriculture includes many components- people, places, products, technology, and data. The agriculture of the future will be enabled by automated and remote technologies as well as smart use of data. What is the role of AI and machine learning in the future of US food and agricultural systems? Considering the increasing need for predictive analytics across the agricultural supply chain from input industries to consumers, AI-based tool development is becoming an increasing sector in the US agriculture. NIFA provides funding for research, education, and extension projects on AI applications in agriculture from accelerated breeding of crops to precision agriculture to engineering. Examples of research and outlook for the future applications of AI in the US agricultural sector will be presented.

Organisation: National Institute of Food and Agriculture (NIFA), United States Department of Agriculture (USDA)

Position: Deputy Director

Bio: As a Deputy Director at the National Institute of Food and Agriculture (NIFA) of US Department of Agriculture, Dr. Chitnis leads NIFA’s Institute of Food Production and Sustainability, which invests ~$860M in research and extension activities on agricultural technologies, social and economic sciences and production systems involving plants and animals. He also leads NIFA activities related agricultural data and represents USDA in the Prior to joining NIFA, he was the Director for the Division of Molecular and Cellular Biosciences at the National Science Foundation (NSF). In his academic career, Dr. Chitnis was a professor in the Department of Biochemistry, Biophysics, and Molecular Biology at Iowa State University, and was an assistant professor in the Division of Biology at Kansas State University. As a researcher, he received more than $7 million in research and training grants from federal and private sources including funding from NIFA, NSF, and NIH. He has authored over 110 peer-reviewed or invited publications and has mentored over 50 undergraduate students, MS and PhD students, post-doctoral fellows, and AAAS fellows. Dr. Chitnis has a B.S. in plant breeding from the Konkan Agricultural University in India, an M.S. in genetics from the Indian Agricultural Research Institute, and Ph.D. in biology from the University of California at Los Angeles.

Talk Abstract:

Machine Learning for Plant Phenotyping

Machine learning has seen tremendous successes in applications ranging from face analysis to speech understanding over the last few years. However, concerted large-scale efforts of machine learning in agriculture have been falling behind, and there is a need to explore the potential of machine learning in cyber-agriculture. Plant phenotyping is an important task where machine learning can be effectively used. This talk will present various possibilities as well as challenges of using machine learning for plant phenotyping, and also highlight our recent research on using deep learning for cyber-agriculture.

Keywords: Deep Learning, Machine Learning, Plant Phenotyping

Organisation: Indian Institute of Technology (IIT), Hyderabad

Position: Associate Professor, Department of Computer Science and Engineering .

Bio: Vineeth N Balasubramanian is an Associate Professor in the Department of Computer Science and Engineering at the Indian Institute of Technology, Hyderabad. His research interests include deep learning, machine learning, computer vision, non-convex optimization and real-world applications in these areas. He has around 60 research publications in premier peer-reviewed venues including CVPR, ICCV, KDD, ICDM, IEEE TPAMI and ACM MM, 5 patents under review, and an edited book on a recent development in machine learning called Conformal Prediction. His PhD dissertation at Arizona State University (completed in 2010) on the Conformal Predictions framework was nominated for the Outstanding PhD Dissertation at the Department of Computer Science. He was also awarded the Gold Medals for Academic Excellence in the Bachelors program in Math in 1999, and for his Masters program in Computer Science in 2003. He is an active reviewer/contributor at many conferences such as ICCV, IJCAI, ACM MM and ACCV, as well as journals including IEEE TPAMI, IEEE TNNLS, Machine Learning and Pattern Recognition. He is a member of the IEEE, ACM and currently serves as the Secretary of the AAAI India Chapter.

Talk Abstract:

Current status and future perspective for high-throughput crop field phenotyping

While genotyping has become high-throughput, dramatically enriching genomic information, crop phenotyping is still left behind. Thus, crop phenomics, studies on phenotyping is now one of the hot topics in crop science, proposing several new approaches of phenotyping with new tools such as image pattern recognition, new IoT sensors, drones and machine learning. This presentation will report current status and future perspective of high-throughput crop phenotyping, particularly focusing on outdoor fields.

Keywords: Image Analysis, Artificial Intelligence, Data Platform, Image Sensors

Organisation: International Field Phenomics Research Laboratory, The University of Tokyo

Position: Project Professor, Emeritus professor.

Bio: Prof. Ninomiya originally majored plant breeding and applied genetics at Laboratory of Plant Breeding of U. Tokyo. After receiving his PhD on genetic background of circadian rhythms of soybean, he became an assistant professor at Laboratory of Biometrics of the same university in 1983 where he started studies on applications of image analysis for crops. In 1991, he moved to National Institute of Agro-environmental Sciences and became the leader of the national ICT project in agriculture which lasted for 10 years until 2005. In 2006, he was appointed as the Director of the Department of Information Science and Technology, National Agricultural and Food Research Organization. In 2010, he moved back to U. Tokyo as a professor when the Institute of Sustainable Agro-ecosystem Services was founded. Currently, his research Interests are high-throughput phenotyping, machine learning, ICT for sustainable agriculture and sustainable rural development using ICT.