Ali Moghimi presented a webinar "Artificial intelligence and hyperspectral imaging for high-throughput plant phenotyping" on Tuesday, September 24, 2019, at 8:30 am PDT (UTC -7). The edited video is is available through YouTube, viewing on our page here, and download as .mp4 [175MB].
Ali Moghimi is from the University of California, Davis, USA.
Abstract:
Graphic illustrating the concepts for Ali Moghimi's webinar on September 24, 2019.
For our indoor setup, we developed a sensor-based framework for analysis of hyperspectral images to assess the difference between the salt tolerance of four wheat lines. We were able to attain a quantitative ranking as early as one day after applying salt treatment. In addition, we developed an ensemble feature selection pipeline to identify the most informative spectral bands associated with the desired trait in plant phenotyping. I present the results of testing the developed feature selection pipeline in finding the most prominent bands for salt stress assessment and Fusarium head blight detection in wheat.
For our field setup, we mounted the hyperspectral camera on an unmanned aerial vehicle to collect aerial imagery in two consecutive growing seasons from three experimental yield fields composed of hundreds of experimental wheat lines. We trained a deep neural network with fully connected layers for yield prediction. While conventional harvesting of plots for yield measurement relies on demanding, extremely laborious, and time-consuming tasks, our automated framework could predict the yield of wheat plots in a fast, cost-effective manner. In addition, our framework offers a unique insight for breeders to investigate the yield variation at sub-plot scale - a valuable new index in breeding programs to nominate high-yielding cultivars that are capable of producing a uniform yield across the plot. The results revealed that the proposed framework can also serve as a valuable tool for remote visual inspection of the plots and optimizing the plot size to investigate more lines in a dedicated field each year.
Supplementary Materials
Spectral band selection for plant phenotyping: 1, 2
Presenter Biography
Ali is currently a postdoctoral research associate working in the Digital Agriculture lab at the University of California, Davis. He is passionate about conducting interdisciplinary research centered at the food-water-energy nexus. Ali's current research focuses on applying innovative technologies (LiDAR and multispectral/hyperspectral imaging), automation (UAVs), and artificial intelligence (machine learning and deep learning algorithms) in agriculture to facilitate the digital revolution in agriculture. He completed his Ph.D. at the University of Minnesota in February 2019. His Ph.D. research focused on developing sensor-based, automated frameworks for high-throughput phenotyping in wheat.
Ali Moghimi, webinar speaker on September 24, 2019.
Ali is currently working on the following projects at the University of California, Davis:
Project 1: prediction of nitrogen status in table grape using aerial multispectral imagery
Project 2: developing a canopy profile mapping technique using UAV-based LiDAR data for almond orchards
Project 3: developing a low-maintenance system to reduce spray drift without limiting the spray and air delivery