Singapore's National Environment Agency runs a peer-reviewed machine-learning system that forecasts dengue cases up to three months ahead. In the 2013 outbreak …
Singapore, Singapore
Good practice
Evidence: Descriptive / self-reported
Top 13%80/100
Since 2020, Google Research's machine-learning flood model — which forecasts river levels even in ungauged basins — has combined with Bangladesh Water …
Dhaka, Bangladesh
Good practice
Evidence: Descriptive / self-reported
Top 44%74/100
Researchers at the University of Sussex and Kenya's RCMRD built machine-learning models forecasting NDMA's official VCI3M drought indicator up to 6 weeks …
Nairobi, Kenya
Good practice
Evidence: Descriptive / self-reported
Top 50%60/100
FAO and Timor-Leste's government built an XGBoost-corrected seasonal drought index that triggered the country's first Anticipatory Action protocol in October 2023, matching …
Dili, Timor-Leste
Good practice
Evidence: Observational / pre–post
Top 66%53/100
Mozambique's INGD and INAM are piloting machine-learning forecasts atop a multi-hazard early-warning system that helped cut Cyclone Freddy's 2023 death toll to …
Maputo, Mozambique
Good practice
Evidence: Descriptive / self-reported
Top 83%40/100
Melbourne and Tribhuvan universities, with Nepal's disaster authority, pilot SAFE-RISCCS, AI fusing rainfall, ground-movement and satellite data to flag landslide risk weeks …
Kathmandu, Nepal
Good practice
Evidence: Descriptive / self-reported
Top 100%7/100