# IIT Bombay AI decodes satellite images with plain language prompts

2026-08-16T11:23:47+00:00 | Technology | Indian Opinion Desk

Corroboration: 1 independent outlet

Researchers at IIT Bombay have developed an artificial intelligence model that can interpret satellite and drone images using everyday language. The model, called Adaptive Modality-guided Visual Grounding (AMVG), was created by a team led by Professor Biplab Banerjee. Users can give prompts like "find all damaged buildings near the flooded river" and get results in minutes. The system uses a Multi-stage Tokenised Encoder and Attention Alignment Loss, which acts like a virtual coach to help the machine focus on relevant image regions, said lead author and PhD researcher Shabnam Choudhury. The team envisions applications in disaster response, surveillance, urban planning, and agriculture. Professor Banerjee said AMVG has not yet been tested in real-world disaster scenarios, but collaborations with ISRO are likely to start shortly. The researchers have open-sourced the AMVG code on GitHub to encourage transparency.

## Coverage

- thehindu.com <https://www.thehindu.com/news/cities/mumbai/iit-bombay-develops-ai-model-to-decode-satellite-images-using-natural-language/article70011132.ece>

This story was synthesised by AI from the source linked above.

Tags: Biplab Banerjee, IIT Bombay, ISRO, Shabnam Choudhury
Canonical: https://indianopinion.org/iit-bombay-ai-decodes-satellite-images-with-plain-language-prompts/
License: Summary and commentary (c) Indian Opinion, reusable with attribution. Facts belong to the linked sources.
Cite: https://indianopinion.org/iit-bombay-ai-decodes-satellite-images-with-plain-language-prompts/#story-in-brief

Review state: restored archive article, accurate at time of publication, not offered to search indexes.

How this brief was made: an AI model read the report linked above and wrote this summary and analysis, which were published automatically. Published briefs are sampled every hour by an automated quality check; the editor verifies its findings and approves corrections, and corrected briefs carry a dated correction line. We do no original reporting. Methodology: https://indianopinion.org/ai-use-policy/
