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.

The receipts 🧾

Every red flag on this statement, in full. These are the four places it bites.

1. Exhibit A

   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

2. It gets worse

   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

3. Still reading?

   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

4. And the finisher

   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

The damage report 📉

Every score this statement earned, and what each one actually costs you.

• Feasibility

  4/5

  Actually buildable, which on this slate is rarer than it sounds. Do not squander it on scope.

  The 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

  4/5

  There is something genuinely new here. Do not bury it under another dashboard.

  The 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

  1/5

  Nobody is sure what is being asked, quite possibly including the people who asked it.

  The 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.

• Acceptance potential

  3/5

  Middle of the pack. This statement will not win the room for you — you will have to.

  The 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.

• Effort

  Heavy

  Heavy. Somebody on this team is not sleeping in week three. Pick who, on purpose.

  Assembling 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

  Easy

  Easy to demo — and so is everyone else's. Working is the floor here, not the achievement.

  A 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.

• Data

  None supplied

  No dataset comes with this one, so every accuracy figure you quote is a number about labels you invented.

  Nothing is provided with the statement. You are sourcing, cleaning and labelling it yourself, and that work is invisible in the demo but very visible in the questions.

The demo they will have already seen 🪞

Somewhere around 150–360 teams are heading here, and the description is doing the choosing for most of them. They will read the same brief, reach the same architecture, and build a version of the same demo you are planning. Being correct is the floor. If your five minutes could be swapped with the team before you and nobody in the room would notice, you have not picked badly — you have built predictably, which costs exactly the same and hurts more.

What survives 🛡️

The ground worth standing on when the questions start.

• 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
• Validation is against a historical record anyone can look up, so your claims are checkable in the room rather than self-reported
• 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