Mihir Bulsara profile photo 1 on Tal

Mihir Bulsara

Software Engineer at SAC, ISRO | Python Developer | Machine Learning | Data Science Enthusiast

Bharuch

3+ years of work experience

Space Applications Centre, ISRO
Sep 20242 yrsPresent

Ahmedabad, Gujarat, India

ISRO Space Applications Centre (SAC)
Sep 20242 yrsPresent

• Architected CNN-based deep learning pipeline for urbanization detection from Sentinel-2 multispectral imagery achieving 85%+ accuracy across Gujarat metropolitan regions for Spatio-Temporal Building Probability Mapping project • Engineered automated pre-processing workflows with OpenCV for pixel-level geometric alignment and deployed on cloud infrastructure handling 500GB+ satellite datasets • Developed full-stack Vue.js and Python modules for Fasal 2.0 and Krishi Decision Support System Dashboard serving 15+ Indian states with real-time crop analytics for national agricultural monitoring • Optimized PostgreSQL database queries reducing page load times by 40% for 100+ concurrent users and implemented interactive Chart.js visualizations with drill-down capabilities • Built real-time Bihar Flood Alert Dashboard integrating Sentinel-1 SAR data with automated threshold alerts and geospatial heatmaps covering 40+ districts • Built GeoChat Agentic AI GIS Dashboard using Ollama LLM API and ChromaDB vector database enabling natural language queries over 500+ satellite imagery layers (Sentinel-2, MODIS, AWiFS) • Implemented RAG-based semantic search pipeline with SentenceTransformers embeddings: pre-check regex, vector search narrowing 500 to top-10 candidates, Ollama LLM disambiguation, and map command execution; supported composite selection (1-day, 5-day, 10-day, 30-day), geocoding with Nominatim and PostgreSQL fallback, and multi-layer batch operations via natural language • Integrated WMS tile streaming from VEDAS satellite services with dynamic parameter templating for band indices, time ranges, and composite windows • Trained UNet CNN on 10,000+ Sentinel-2 multispectral samples achieving 88% accuracy in forest and non-forest classification across 5000+ sq. km for Forest and Deforestation Change Detection System • Implemented bi-temporal change detection pipeline comparing Sentinel-2 imagery across time periods to identify deforestation hotspots and forest c
Space Applications Centre, ISRO
Jun 202311 mosApr 2024

Ahmedabad, Gujarat, India

ISRO Space Applications Centre (SAC)
Jun 202311 mosApr 2024

• Enhanced climatology datasets by reconstructing missing coastal pixels using machine learning algorithms, Ferret visualization software, and GrADS data analysis tools • Processed 10+ years of NetCDF satellite data improving data quality and coverage for climate analysis and environmental monitoring applications
Mood Indigo IIT Bombay
Jul 20221 yr 7 mosJan 2024

GitHub
@mihirisro17

Mihir’s AI Stack

antigravity
antigravity
codex
codex
claudecode
claudecode

Education

Dharmsinh Desai University

Master of Technology, Computer Engineering

Dharmsinh Desai University

20222 yrs2024

Bachelor of Engineering, Information Technology

SHRI SADVIDHYA MANDAL INSTITUTE OF TECH., BHARUCH 045

20184 yrs2022

Join Mihir and 10k+ other professionals on

Tal Boss

Tal is the app where bosses meet engineers & builders directly, without middlemen

Download Tal Boss

Mihir Bulsara on Tal

Headline

Software Engineer at SAC, ISRO | Python Developer | Machine Learning | Data Science Enthusiast

About

Looking for a challenging role in a reputed company to utilize my engineering skills that can contribute to the company’s growth as well as enhance my knowledge by exploring new things.

Location

Bharuch

AI stack

antigravity

codex

claudecode

Work experience

Software Engineer at Space Applications Centre, ISRO, Sep 2024 - Present · 2 yrs, Ahmedabad, Gujarat, India

Software Engineer at ISRO Space Applications Centre (SAC), Sep 2024 - Present · 2 yrs, • Architected CNN-based deep learning pipeline for urbanization detection from Sentinel-2 multispectral imagery achieving 85%+ accuracy across Gujarat metropolitan regions for Spatio-Temporal Building Probability Mapping project • Engineered automated pre-processing workflows with OpenCV for pixel-level geometric alignment and deployed on cloud infrastructure handling 500GB+ satellite datasets • Developed full-stack Vue.js and Python modules for Fasal 2.0 and Krishi Decision Support System Dashboard serving 15+ Indian states with real-time crop analytics for national agricultural monitoring • Optimized PostgreSQL database queries reducing page load times by 40% for 100+ concurrent users and implemented interactive Chart.js visualizations with drill-down capabilities • Built real-time Bihar Flood Alert Dashboard integrating Sentinel-1 SAR data with automated threshold alerts and geospatial heatmaps covering 40+ districts • Built GeoChat Agentic AI GIS Dashboard using Ollama LLM API and ChromaDB vector database enabling natural language queries over 500+ satellite imagery layers (Sentinel-2, MODIS, AWiFS) • Implemented RAG-based semantic search pipeline with SentenceTransformers embeddings: pre-check regex, vector search narrowing 500 to top-10 candidates, Ollama LLM disambiguation, and map command execution; supported composite selection (1-day, 5-day, 10-day, 30-day), geocoding with Nominatim and PostgreSQL fallback, and multi-layer batch operations via natural language • Integrated WMS tile streaming from VEDAS satellite services with dynamic parameter templating for band indices, time ranges, and composite windows • Trained UNet CNN on 10,000+ Sentinel-2 multispectral samples achieving 88% accuracy in forest and non-forest classification across 5000+ sq. km for Forest and Deforestation Change Detection System • Implemented bi-temporal change detection pipeline comparing Sentinel-2 imagery across time periods to identify deforestation hotspots and forest c

Researcher at Space Applications Centre, ISRO, Jun 2023 - Apr 2024 · 11 mos, Ahmedabad, Gujarat, India

Research Intern at ISRO Space Applications Centre (SAC), Jun 2023 - Apr 2024 · 11 mos, • Enhanced climatology datasets by reconstructing missing coastal pixels using machine learning algorithms, Ferret visualization software, and GrADS data analysis tools • Processed 10+ years of NetCDF satellite data improving data quality and coverage for climate analysis and environmental monitoring applications

Indigo Squad Member at Mood Indigo IIT Bombay, Jul 2022 - Jan 2024 · 1 yr 7 mos

Education

Master of Technology, Computer Engineering, Dharmsinh Desai University

Bachelor of Engineering, Information Technology, SHRI SADVIDHYA MANDAL INSTITUTE OF TECH., BHARUCH 045

Public links

github: https://github.com/mihirisro17