Skip to content
SIH Buddyby Ganeev Singh
Dev
All problem statements
SIH26025Strong pickacceptance 4/5

Development of an AI-enabled Low Cost Real Time Mine Subsidence Monitoring, Prediction and Early Warning System for Underground Coal Mines in India

Ministry of Coal · Disaster Management · Hardware

The rare hardware statement with a genuinely student-scale bill of materials, a near-complete spec and a physically honest demo — just be candid that you are showing deformation detection rather than validated subsidence prediction, because the sponsor has told everyone what to build and execution will decide it.

What it actually is

When coal is mined underground the ground above it slowly sinks, and that can crack houses, roads and farmland with no warning. Right now it is checked by surveyors visiting periodically, which usually means the damage is found after it happens. The ask is a cheap network of sensors spread over the surface that watches the ground continuously and raises an alarm early.

What to build

A wireless surface mesh of low-cost sensor nodes over an underground panel, each node carrying the sensing the statement names — tilt and inclination, vibration, displacement or stretch, crack initiation, with optional positioning — running on ESP32-class hardware with solar or long-life battery power, linked by a LoRa or Zigbee mesh so nodes relay through each other without cellular coverage, feeding a server that tracks inter-node relative distance and tilt drift over time, runs anomaly detection over the deformation field to flag abnormal patterns and estimate progression, renders a live GIS deformation map with risk zones, and dispatches SMS and app alerts, with local buffering and periodic cloud sync.

Smallest thing that wins the room

Lay the mesh across a sand tray, lower one section of the base to simulate ground settlement, and watch tilt drift propagate node to node through the mesh into a deformation map that shades red and fires an alert.

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.

Quiet65–150 teams expectedroughly 1 in 53–122 wins it

Quieter than 88% of the 226 · #27 of 226 by expected field

Few teams are likely to go here. The best odds on the board come from statements like this.

Why: central ministry statements sat below the average; hardware halves the field a software statement gets.

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

  • ESP32 + MPU6050 tilt and inclination nodes
  • LoRa mesh via Meshtastic or RadioHead
  • strain gauge crack initiation sensing
  • isolation forest / autoencoder deformation anomaly detection
  • Leaflet GIS deformation heatmap
  • solar node power with deep sleep duty cycling
  • Mine safety and geotechnics
  • Wireless sensor networks
  • Structural deformation monitoring

Prior art to read before you start

wireless mesh sensor network deployment · ground deformation and tilt monitoring · low-cost IoT early warning system

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.