The data for this challenge was collected using the Smart Indigenous Weather App, a custom-built mobile app for data collection, available on the Google Play Store. Data was collected from local farmers in the Pra River Basin of Ghana.

N.B. If you would like to explore this app, please list your community as ‘Zindi’ on the app, so RAIL can easily identify which data points are experimental values.

Key steps in data collection included:

• Rain Gauge Deployment: Calibrated garden rain gauges were installed on the properties of 25 local farmers across three regions (Central, Eastern, and Ashanti).
• Farmer Training: Farmers were trained to record daily rainfall observations and to submit their indigenous weather and climate forecasts using the Smart Indigenous Weather App.
• Use of Indigenous Ecological Indicators (IEIs): Farmers made forecasts based on traditional signs such as cloud formations, sun position, wind, moon, heat, and specific tree or animal behaviors.

The following variables were and continue to be collected are:

• Daily rainfall amounts (measured using the rain gauges.
• Forecast type (e.g., prediction of heavy, medium, small, or no rainfall)
• Ecological indicators used (e.g., cloud, sun, moon, heat, wind)
• Prediction time frame (12-hour and 24-hour forecasts)
• Accuracy of prediction (hit/miss rate, compared with actual rainfall)

The objective of this challenge is to predict the type of rain to be expected in the next 12 to 24 hours.

Tip: run the starter notebook to achieve a score on the leaderboard.