How many people lightning really kills in tropical Africa, and whether new satellite lightning data can give rural people a warning in time
- Good it would do
- 3 / 5
- Can AI help
- 4 / 5
- How neglected
- 4 / 5
- Can we check it
- 3 / 5
Why it's stuck
Lightning deaths are counted properly in only about 24 countries. Malawi, one of the few African countries with good records, reports 84 deaths per million people each year, many times the rate elsewhere, and many populous equatorial African countries have no figures at all.
What we'd try
Use the new Meteosat Third Generation Lightning Imager to estimate deaths and injuries country by country, and to train short-range lightning forecasts that could be sent by text message. Check death estimates against countries with good records, and score forecasts against the satellite's own later observations.
What could stop us
Lightning death records are thin and underreported, so checks against the few well-recorded countries may be too weak, and the forecasting half is already being worked on.
Do you know the answer?
One reply from someone in the field can settle what our AI can't.