Shrey Joshi

About

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.

currently:

previously:

Research

AI-Driven Landslide Risk Assessment using Geophysical and Metereological Data

 /  /  /

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)

Projects

sorted by most recent

Cognition Labs

(June 2023-Present) Contracting org [WIP]

landingpage.dev

This domain is for sale. Email if interested.

BioConceptXplorer

(June 2023) Exploring biological hypotheses at scale with PubMed concept embeddings. Featured on the Codon Digest.

Rusty [WIP]

(Feb 2023-Present) A blazing-fast chess (& anti-chess) engine built in rust. 4M moves/second single-threaded.

Maze-gen with Disjoint Sets

(May 2023) A maze-generation algorithm in Rust using the disjoint-set (union-find) ADT.

WolfreeAlpha

(April 2023) Reverse-engineering WolframAlpha's API to provide free step-by-step solutions for everyone.

Super Mario in MIPS assembly

(April 2023) CS 2340 project: a controllable & animated mario sprite in the MARS MIPS bitmap display.

AutoBuild [WIP]

(March 2023-Present) Fully autonomous code-gen for full-stack apps using natural language.

Surfa Club

(December 2022) Find a dorm to crash for conferences, hackathons, and other events.

pairprogram.app

(December 2022) Minimalistic collaborative code editing in the cloud.

Chess Engine

(July 2022) A simple chess AI using minimax + alpha-beta pruning. Can you beat it?

AI-Generated Photography

(July 2022) Inspired by thispersondoesnotexist.com.

BirdWatch

(November 2020) Combat species extinction through computer vision & crowdsourcing.

RetnoScan

(October 2020) AI-driven retinopathy diagnosis with your smartphone camera.

Stats:

  • Current Age: 19
  • Number of page visits: web counter
  • Number of unique page visitors: web counter
  • Website last updated: