To develop an Artificial Intelligence (AI) / Machine Learning (ML) based system for identification, classification, and prediction of different tropical cyclone patterns using multi-source satellite data.
Ministry of Earth Sciences (MoES) · Smart Education · Software
Excellent labelled data and a genuinely dramatic demo, but the description is just the title and it bundles three problems — pick intensity classification, do it against published baselines, and treat track prediction as a stretch rather than a claim.
What it actually is
Forecasters judge how strong a cyclone is largely by looking at its satellite picture and matching the cloud pattern to a reference scheme, which is expert work and somewhat subjective. The ask is a system that reads the satellite imagery itself and identifies the cyclone, classifies its pattern and intensity, and says where it is going.
What to build
A three-stage system over satellite imagery: detection and centre-fixing locating a cyclonic system and its centre in a full-disk image; a classification stage assigning intensity and cloud pattern type against an established grading scheme, trained on imagery paired with best-track intensity so the labels come from an authoritative archive rather than your own reading; and a short-range track and intensity projection compared honestly against both a persistence baseline and the operational forecast for the same case, presented as a case viewer where a stored historical cyclone can be stepped through frame by frame with the model's classification and projected track shown against what actually happened.
Smallest thing that wins the room
Step through a real historical cyclone frame by frame, showing your intensity classification tracking the best-track record it never saw, and the projected path against the track the storm actually took.
How crowded this one gets
A guess, projected from the 2025 statements — the last year where both the submission counts and the winners were published.
Quieter than 30% of the 226 · #158 of 226 by expected field
A normal-sized field. Your idea has to be good, not miraculous.
Why: central ministry statements sat below the average.
This is a guess, not a fact
Nobody has published 2026’s numbers yet. This is an analysed estimate from last year’s pattern, so please do not take it as the truth — check the live counter on the SIH portal before you decide anything. The range covers the middle half of likely outcomes, so one statement in two lands outside it. Entry closes at 500 ideas per statement, so no range goes past that — a statement that reaches the cap fills and shuts rather than drawing an unlimited crowd. The model reads only three things a team can see before choosing — software or hardware, the theme, and what kind of body posted it — and those explain about a quarter of the variation in last year’s field sizes (R² 0.25 on held-out statements). Trust the band more than the number, and the ordering more than either. It cannot see how good your idea is, which is the part that actually decides it.
The scores
The number is the shorthand. The line under it is the reason.
Acceptance potential
3/5The data and validation situation is excellent and the demo is strong, but satellite cyclone intensity estimation is a well-published problem with established benchmarks, and the prediction half is where operational numerical models are genuinely hard to beat — so be clear which of the three tasks you are actually claiming.
Feasibility
4/5The data position is genuinely strong — the global best-track archive gives authoritative intensity labels going back decades, geostationary satellite imagery covering the Indian Ocean basins is freely distributed, and the pairing of imagery to labelled intensity is exactly what a supervised model needs.
Innovation scope
4/5The description is the title repeated verbatim, so nothing whatsoever is prescribed about architecture, basin, satellite source, lead time or output format, and you define the entire problem.
Clarity
1/5The description is a word-for-word copy of the title — there is no background, no requirement, no data source, no lead time and no success criterion, so the statement contains no information beyond its own name.
Effort
HeavyAssembling and aligning a satellite imagery archive with best-track records, training detection and classification stages, building a track projection and constructing an honest baseline comparison is four workstreams, with the imagery-to-track alignment quietly the most tedious.
Demo-ability
EasyA cyclone spinning across a satellite loop with your intensity classification updating and a projected track drawn against the real one is dramatic, self-explanatory and verifiable against a historical record everyone can check.
In its favour
- Green flag: The best-track archive provides authoritative, expert-assigned intensity labels for decades of storms, which is an unusually clean supervised learning setup for a geophysical problem
- Green flag: Validation is against a historical record anyone can look up, so your claims are checkable in the room rather than self-reported
- Green flag: Because the description is the title repeated, you define the scope entirely — narrowing to intensity classification in the North Indian Ocean and doing it rigorously is fully responsive and far more achievable than all three tasks
- Green flag: The Smart Education theme label buries a cyclone forecasting statement where nobody looking for disaster management will find it
Against it
- Red flag: Identification, classification and prediction are three different problems and the statement gives them equal billing in one sentence — a team that attempts all three will do none convincingly, and prediction is the one you are least likely to win at
- Red flag: Track prediction is what operational numerical weather models exist to do, and an image-based model that claims to beat them without a rigorous baseline comparison will not be believed by a meteorological panel
- Red flag: Satellite cyclone intensity estimation has an established published literature with reported skill figures, so quote and compare against them rather than presenting your number in isolation
- Red flag: The most intense storms are the rarest, so a model trained on the full record will be accurate on average and weakest exactly at the intensities that matter — report performance by category, not overall
What you will be writing
- CNN intensity regression on geostationary IR imagery
- IBTrACS best-track intensity labels
- INSAT-3D / Himawari full-disk imagery ingestion
- cyclone centre-fixing via spiral pattern matching
- persistence and climatology baseline comparison
- case replay viewer with track overlay
- Tropical meteorology
- Satellite image analysis
- Severe weather forecasting
Prior art to read before you start
cyclone intensity estimation from satellite imagery · storm track prediction and validation · pattern classification against expert grading scheme
Analysed by Claude Opus. Every score above is a judgment call with its reasoning attached — kindly cross-check this against the official statement on the SIH portal before your team commits to it.