Remote Sensing and Hyperspectral Image Semantic Segmentation
The methods we develop improves precision prediction and big data analysis in hyperspectral images (HSI) which are a relatively new remote sensing scheme in forestry and climate change sciences. In addition, my lab has proposed a new framework Adversarial Discriminator Ensemble Network (ADE-Net) which focuses on attack type detection and adversarial robustness under a unified model to preserve per data-type weight optimally while robustifiying the overall network in the present of multiple attacks on HSIs. This project has a strong impact on agricultural innovations relevant to climate change. One long-term impact of this project is to innovate integrated, sustainable, and climate-smart AI models that not only bring the science from the laboratory to growing fields and crops but also secure US food production through disease detection, weeding automation, resilience toward climate-change risks and environmental stresses.