Skip to content
SIH Buddyby Ganeev Singh
Dev
All problem statements
SIH26085Proceed with cautionacceptance 2/5

Urban Flood Nowcasting System (Drainage and Rainfall Coupling)

Ministry of Earth Sciences (MoES) · Disaster Management · Software

The abstraction is elegant and the specification is excellent, but the drainage graph it depends on is not public for any Indian city — if you take it, get a real network from one municipal ward or accept that you are modelling a drainage system you made up.

What it actually is

Knowing how much rain will fall on a city does not tell anyone which junctions will go under, because that depends on the shape of the streets and the state of the drains beneath them. The ask is a system that routes forecast rainfall across the actual terrain and through a model of the storm drain network to say which streets flood, how deep, and within the next three hours.

What to build

A coupled surface-and-network flood nowcaster as the statement specifies: rainfall nowcasts routed across a high-resolution surface terrain model accounting for the imperviousness that makes urban runoff so fast, coupled to a directed graph of the stormwater system with manholes and inlets as nodes and pipes and canals as edges, each edge carrying a hydraulic capacity so the model computes where the network surcharges and water backs up onto the street; outputs as street-level inundation with depth estimates over a zero-to-three-hour window on a live GIS dashboard, plus a routing API returning flood-safe alternatives for emergency vehicles and commuters.

Smallest thing that wins the room

Feed the rainfall from a documented flood day into the coupled model and show your predicted flooded junctions and depths against the locations that were actually reported waterlogged that day.

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.

Moderate140–330 teams expectedroughly 1 in 119–275 wins it

Quieter than 40% of the 226 · #137 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.

What you will be writing

  • SWMM-style hydraulic network solver
  • directed graph drainage model with capacity constraints
  • 2D surface routing over high-resolution DEM
  • imperviousness-weighted runoff coefficients
  • radar rainfall nowcast coupling
  • flood-aware routing API over road network
  • Urban hydrology
  • Flood modelling
  • Municipal emergency response

Prior art to read before you start

coupled surface and drainage flood modelling · street-level inundation depth prediction · flood-safe routing for emergency services

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.