Back home
Adithya SN
Selected work — 01/052026Python / LightGBM / SHAP / Google Earth Engine / FastAPI / Next.js / Leaflet / LLM Agents

Amazon
Fire
Intelligence

End-to-end fire prediction & early-warning platform for the Brazilian Amazon — 7 ML models trained on 200K satellite records, physics-based fire spread simulation, and a 5-agent LLM response system. Built as an IEEE journal internship project.

IEEE Journal Internship — Solo, end-to-endMajor project — IEEE evaluation completeScroll
Screenshot soon
Amazon Fire IntelligencePythonLightGBMSHAPGoogle Earth EngineFastAPINext.jsLeafletLLM Agents2026Amazon Fire IntelligencePythonLightGBMSHAPGoogle Earth EngineFastAPINext.jsLeafletLLM Agents2026Amazon Fire IntelligencePythonLightGBMSHAPGoogle Earth EngineFastAPINext.jsLeafletLLM Agents2026Amazon Fire IntelligencePythonLightGBMSHAPGoogle Earth EngineFastAPINext.jsLeafletLLM Agents2026
01.1Overview

A production-grade fire intelligence platform covering the entire Brazilian Amazon, built solo as my IEEE journal internship and major project. An 8-step pipeline fuses INPE fire detections, ERA5 weather reanalysis and Google Earth Engine satellite features into a 200K-row dataset, on which 7 models Random Forest, XGBoost, LightGBM, CatBoost, TabNet, ANN and a stacked ensemble are trained on GPU, reaching 0.987 ROC-AUC. Every prediction is explained live with SHAP, fire spread is simulated with the full Rothermel physics model (the same family used by FARSITE), and a GIS module scores ecological risk to protected areas, indigenous territories and settlements. It all runs behind a FastAPI backend and a real-time Next.js + Leaflet dashboard with NASA FIRMS active fires, live weather heatmaps and an admin panel plus a 5-agent DeepSeek LLM system that autonomously coordinates fire-crew interceptions, saving up to 30% of burn area in IEEE evaluation scenarios for under a cent per run.

Role
IEEE Journal Internship — Solo, end-to-end
Stack
Python, LightGBM, SHAP, Google Earth Engine, FastAPI, Next.js, Leaflet, LLM Agents
Year
2026
Status
Major project — IEEE evaluation complete
Next project
© 2026 Adithya SNBack home