Mapping land, water, and energy across Tamil Nadu — using satellite data and open-source tools.
Geospatial data scientist based in India with 3.5+ years of hands-on experience in satellite remote sensing, land-use classification, and climate-focused spatial analytics. Trained as a chemical engineer — transitioned into geospatial science through a deep interest in how land, water, and energy systems interact at scale.
Most of my work centers on Tamil Nadu: processing thousands of Sentinel-2 scenes, building multi-criteria suitability models, and producing maps that feed directly into state-level planning decisions. I work end-to-end — from raw satellite imagery to policy-ready outputs.
Currently seeking fully remote roles in geospatial AI, climate analytics, or earth observation at research organizations, think tanks, or climate-tech companies.
Auroville Consulting × Tamil Nadu State Planning Commission · 2024–ongoing
Regional-scale geospatial analysis to map and prioritize Blue-Green Networks (forests, wetlands, rivers, farmlands) for flood regulation, carbon storage, and biodiversity across Tamil Nadu.
- Processed 15,000+ Sentinel-2 scenes across the full state extent
- Integrated 40+ geospatial layers — hydrology, topography, climate vulnerability, biodiversity
- Built an 18-criteria ecosystem services prioritization model
- Produced district-level intervention maps from nano to mega scale
- Outputs embedded into Tamil Nadu's spatial planning framework
Personal Research · 2024–ongoing · View Repository →
Deep learning pipeline (U-Net) for built-up area extraction from Sentinel-2 imagery, applied to Chennai for urban heat island and climate risk analysis.
- Semantic segmentation on 10m Sentinel-2 bands using U-Net
- Custom training label generation and validation workflow
- Designed for urban heat island mapping and climate vulnerability assessment
Personal Research · 2025 · View Repository →
Deep learning pipeline for coconut plantation mapping from Sentinel-2 imagery using U-Net semantic segmentation, based on Descals et al. (2023) training labels.
Auroville Consulting · Aug 2022 – Oct 2023
Research and spatial analytics supporting Tamil Nadu's net-zero energy transition.
- Land suitability assessment for distributed solar across Villupuram district
- Time-of-Use tariff modelling for clean energy incentives
- Policy analytics for grid-connected solar in agriculture
- Published Report →
Tamil Nadu State Planning Commission · Feb – Dec 2023 · View Repository →
Multi-use suitability mapping of unused land for forestation, agriculture, water harvesting, housing, industry, and solar.
- LULC classification and change detection (2019–2023) using Sentinel-2 and Landsat
- Ground truthing and field validation across the district
- Delivered an interactive online map for state and local departments
- Conducted awareness sessions with district-level government stakeholders
| Project | Description | Link |
|---|---|---|
| Sentinel-2 Built-Up Pipeline | End-to-end ML pipeline for built-up area identification from Sentinel-2 imagery | Repository → |
| Lila CRS Converter | Full-stack geospatial web app (FastAPI + Streamlit), Dockerized with CI/CD | Repository → |
| Bill Calculator | 25-year economic analysis tool for Solar + Storage systems | Repository → |
| Domain | Tools |
|---|---|
| GIS & Remote Sensing | QGIS · ArcGIS · Google Earth Engine · Sentinel-2 · Landsat |
| Machine Learning | Python · Scikit-Learn · PyTorch · TensorFlow · Random Forest · U-Net · CNN |
| Geospatial Libraries | GeoPandas · Rasterio · GDAL · Pandas · NumPy |
| Database | PostgreSQL · PostGIS |
| Backend & Web | FastAPI · Streamlit · REST APIs |
| DevOps & Infra | Docker · GitHub Actions · Linux · Bash · Self-hosted VPS |
Open to collaborations in geospatial AI, climate analytics, and open-source environmental tools.
