Center for Research in Computer Vision, UCF
Post-Doctoral Scholar
Dr. Gaurav Kumar Nayak is a postdoctoral researcher at the Center for Research in Computer Vision, University of Central Florida, with a Ph.D. from the Department of Computational and Data Sciences at the Indian Institute of Science. He completed his M.Tech at Jawaharlal Nehru University and his B.Tech at VIT University. Dr. Nayak was a recipient of a research fellowship from UCG-JRF (2017 - 2022) and was a finalist for the Qualcomm Innovation Fellowship (QIF) India in 2020. He was also selected for the Doctoral Consortium at WACV 2022. His research focuses on developing data-efficient algorithms for deep learning in areas like Knowledge Distillation, Unsupervised Domain Adaptation, Continual Learning, Adversarial Robustness, and Geo-localization. Dr. Nayak has authored several publications in reputed machine learning and computer vision top-tier venues and is an active reviewer for peer-reviewed venues such as NeurIPS, AAAI, WACV, BMVC, and various journals. His primary interests lie in Artificial Intelligence at the intersection of Computer Vision, Machine Learning, and Deep Learning.
Talk:
AgroAI: Smart Crop Selection with Soil Insights and Location Intelligence
Abstract:
Agriculture is an important sector in the United States, contributing ~1 trillion dollars and ~10.5% of employment. However, the current food demand is higher than the food production, which is further expected to exponentially increase in the future. Consequently, there is an urgent need to maximize crop yield to meet this increasing demand, which is implicitly dependent on the crop type. We propose a deep learning based technique for crop selection to help the farmers in making an informed decision. Our method utilizes soil images and their corresponding GPS locations to determine the best crop that is most suitable to grow in the specified location to attain maximum yield. Unlike existing methods, we additionally model the GPS coordinates whose features are extracted by our intelligently designed GPS network that has shown great success in our recent work of geo-localization. The integration of location intelligence in determining crop selection can help make better decisions. Our method of crop recommendation can benefit agricultural companies (B2B) to increase their revenue as well as farmers (B2C) to make informed choices in the usage of fertilizers and irrigation to maximize crop yield. In the future, we also plan to add other factors such as temperature, season, rainfall, etc. to further refine and improve our crop recommendation.