Forecasting transitions in the state of food security with machine learning using transferable features.
Forecasting transitions in the state of food security with machine learning using transferable features.
Joris J L Westerveld,Marc J. C. van den Homberg,3 Authors,S. Stuit
2021 · DOI: 10.1016/j.scitotenv.2021.147366
Science of the Total Environment · 53 Citations
TLDR
An extreme gradient-boosting machine learning model is introduced to forecast monthly transitions in the state of food security in Ethiopia, at a spatial granularity of livelihood zones, and for lead times of one to 12 months, using open-source data.