Speaker: Saba Dadsetan

Title: Detection and Prediction of Nutrient Deficiency Stress using Longitudinal Aerial Imagery and Make it Efficient with Superpixels and Graph Convolutional Neural network

Abstract: Advances in remote sensing technology have led to the capture of massive amounts of data. Increased image resolution, more frequent revisit times, and additional spectral channels have created an explosion in the amount of data that is available to provide analyses and intelligence across domains, including agriculture.
With this in mind, we collect sequences of high-resolution aerial imagery and construct semantic segmentation models to detect and predict NDS across the field; We construct our proposed spatiotemporal architecture, which combines a U-Net with a convolutional LSTM to accurately detect regions of the field showing NDS; Finally, we show that this architecture can be trained to predict regions of the field which are expected to show NDS in a later flight- potentially more than three weeks in the future depending on how far in advance the prediction is made.
In the next step, we seek to identify nutrient-deficient areas from remotely sensed data to alert farmers to regions that require attention in a real-time fashion so they can quickly respond to struggling areas to protect their harvests. we propose a much lighter graph-based method to perform node-based classification. We first use the Simple Linear Iterative Cluster (SLIC) to produce superpixels across the field. Then, to perform segmentation across the non-Euclidean domain of superpixels, we leverage a Graph Convolutional Neural Network (GCN). This model has 4-orders-of-magnitude fewer parameters than a CNN model and trains in a matter of minutes.