Building AI foundation model for subseasonal climate forecasting using spatiotemporal and multimodal data

Advisor: Prof.Judy Hoffman

Exploring synthetic-to-real generalization of computer vision applications for aerial imagery and analyzing model sensitivity to intra domain shifts using synthetic data and GenAI applications

Developed a cost-effective, globally accessible solution for field boundary detection by designing and implementing an image transformer-based image super-resolution algorithm on Sentinel-2 satellite imagery, bypassing the need for expensive high-resolution images.

Advisor: Prof. Arthi Rao

Developed a statistical metric integrated as an ArcGIS decision support tool to suggest safe freight infrastructure development locations that will quantify growth towards social, environmental, and economic resilience in Henry County.

Led the development of a various computer vision projects including facial spoof detection and infrastructure change detection system using geospatial data.

Conducted a comprehensive analysis of the smart city landscape in India, performing market research on cloud and AI services adoption, and suggesting a growth-maximizing roadmap targeting industry leaders

Advisor: Prof.Nibaran Das

Designed a computationally efficient deep learning-based semantic segmentation algorithm for self- driving cars that achieved 10x faster speed, 5x less memory consumption, and 224x fewer parameters with similar accuracy compared to the state-of-the-art segmentation algorithms.

Expanded NATS-Bench with hardware-specific latency data and developed a latency predictor that generalizes to new hardware and architectures. without sample measurements on the critical inference path.

Analyzed the importance of different VQA components and designed an easy to use lightweight framework that is able to achieve results comparable to state of the art on VQA-RAD dataset

As a member of UC, San Diego, Engineers for Exploration collaborated with San Diego Zoo to develop a real-time machine learning system to monitor and analyze behavioral cues in Aye-Aye for early detection of health issues.

Identified the advantage of trust-region based exploration-exploitation provided by Turbo and the superior candidate selection method (TPE) used by Hyperopt to design a hybrid approach.

Trained neural networks that are robust to post-hoc pruning using Targeted Dropout. The idea was to cut off the snow-ball effect of error buildup in the network’s activations by removing the impact of most weights.

Attempt at developing an automated system to monitor shifting shoreline trends in high-impact regions of the world using satellite imagery (Landsat, SPOT) and deep learning based segmentation techniques.