Title: Data-Driven Approaches for Agriculture
Dr. Naira Hovakimyan is currently a W. Grafton and Lillian B. Wilkins Professor of Mechanical Science and Engineering at the University of Illinois Urbana-Champaign. Hovakimyan is a Fellow and life member of AIAA, a Fellow of IEEE, and a member of SIAM, AMS, SWE, ASME, and ISDG. Hovakimyan is also cofounder and chief scientist of IntelinAir, which has been recently recognized as one of the fastest growing companies in USA. Her research interests are in control and optimization, autonomous systems, machine learning, game theory, and their applications in aerospace, robotics, mechanical, agricultural, electrical, petroleum, biomedical engineering and elderly care.
With the increase in the amount of data generated by agricultural machinery in fields and off fields, and with the ongoing democratization of data science tools, comprehensive and versatile models can be built to characterize the crop conditions and predict the yield early in season, which can then be leveraged to optimize the crop management. In this talk, Hovakimyan will present crop yield prediction using multi-stream convolutional neural network (CNN) models and illustrate how these models can be used to improve crop agronomic management. She will also introduce Agriculture-Vision, a large aerial image database for agricultural pattern analysis, which is used for early-season weed detection by the AGMRI app of Intelinair.