Hey! I'm Shrey, an undergrad at UT Dallas studying Computer Science.
In high school, I conducted original computational geoscience research, built software to automate political activism at the Grassroots Democrats HQ, and and worked on historical research on topics such as Operation Condor. I also helped run AYSI, mentoring for science research and CS/AI related topics. In my free time I love lifting and meditating.
I'm currently working on AI tools for researchers under the umbrella org Cognition Labs, as well as recruiting for SWE/MLE roles for the spring/summer. I'm interested in interdisciplinary AI research and in research/entrepreneurship in general. If you're working on something cool and need a collaborator, don't hesitate to reach out.
Shrey Joshi*, Ishaan Javali*, Dr. Ellen Rathje
ISEF 1st grand prize, $10k won, Accepted & published to 2021 MIT URTC
We introduce GLAS: a scalable, low-latency, Global Landslide Analytics System, along with the first publicly available dataset of Global Landslide Incidents and Features (GLIF). GLIF consists of elevation, climate, lithology, forest change, and human infrastructure data for tens of thousands of landslide and non-landslide locations/times around the world whereas GLAS consists of Random Forest (RF) models trained on GLIF for three tasks: landslide forecasting (binary), landslide severity assessment (categorical), and landslide date estimatation (categorical). A new data-driven susceptibility mapping approach is derived using a weighted sum of static features and RF feature importances. Lastly, we demonstrate that historical multispectral LANDSAT-8 satellite data can be used to detect sudden changes in bare-earth exposure (Red Band: 655nm) and soil moisture (SWIR: Bands 5 & 7) in order to detect unreported rainfall-induced landslides, which could serve as additional training data by adding to GLIF's repository of landslide instances.
(click image to expand)
sorted by most recent