Home › Hard problems › India

India: hard problems at India's scale

Crop yield and stress for small farms

Solo: possibleOne person can test a narrow slice of it.

small plots, with the satellite's 10-metre pixels drawn on topone pixel covers several farmers' plotsOne pixel, one colourrice + wheat + bare soilblended togetherwhich plot isstressed? no ideaGround truthhow much did this plotreally yield? few recordsthe check onthe answeris scarce
Satellite pixels are 10 metres across, bigger than many Indian plots, so one pixel blends several farms, and there is little ground truth to check against.

Why it is still open

Satellite pixels (10 metres) are bigger than many Indian plots, and ground truth is scarce.

An experiment one person can run in 8 weeks

Use free Sentinel-2 images for one district with published yield data. Compare yield prediction from pixels against plot boundaries.

Verdict: Solo: possible

Ground truth is the hard part, so pick a district with good records.

The solo test behind the verdict

  1. Can it be measured? There is a number that shows you did better, such as an error rate, a catch rate or a cost per answer.
  2. Is it cheap to try? It runs on a laptop, free open models and open data, or under about ₹50,000 of rented GPU time.
  3. Is there a public yardstick? A benchmark or dataset others use, so your result can be compared and believed.
  4. Would a small win get noticed? A lab, a funder or a customer would care about a 10% improvement, not only a full solution.

Four yeses means Solo: strong. Two or three means Solo: possible. Fewer means Follow, don't build.

PreviousHyperlocal monsoon and flood forecastsNextGroundwater running out

All 79 hard problems · Working on this, or know of a result we missed? basant@cleandataengineering.ai