Droughts severely affect water resources, exacerbating food insecurity and economic instability. Drought impacts are influenced by environmental and socio-economic factors but their link is not always clearly understood. This study examines the relation between drought hazard and impacts under different socio-economic vulnerability factors in 21 counties in Kenya. Impacts considered are household distance to water (HWD), livestock distance to water (LDW), milk production (MPR), and child malnutrition. Using Random Forest models, we linked these drought impacts for the period 2013-2022 and drought indices by pooling counties with similar characteristics. We then used these models to hindcast drought impacts for 1984-2014 and determine average annual loss (AAL) for each impact. The results revealed spatial variability in AAL between counties: northwestern counties experience high HDW risks, while eastern and southeastern counties face elevated LDW, MPR, and malnutrition risks. Both environmental (particularly aridity) and socio-economic factors (particularly access to improved sanitation) were found to be important vulnerability factors affecting all four risks in the counties. PML curves showed some more underlying differences, with some counties having a resilient situation (e.g. Makueni w.r.t HDW), a constant but worrying level of drought impacts (e.g. Mandera w.r.t HDW), or a gradual increase of impact with return periods (e.g. malnutrition impacts in Tana River double between once in 2 and 10 year droughts). These findings emphasize the importance of socio-economic and environmental factors in shaping drought risk, and can be used as entry points for interventions. Particularly addressing aridity and sanitation infrastructure seem to be important.

The Horn of Africa region has frequently been affected by severe droughts and food crises over the last several decades, and this will increase under projected global-warming and socio-economic pathways. Therefore, exploring novel methods of increasing early warning capabilities is of vital importance to reducing food-insecurity risk. In this study, we present the XGBoost machine-learning model to predict food-security crises up to 12 months in advance. We used >20 datasets and the FEWS IPC current-situation estimates to train the machine-learning model. Food-security dynamics were captured effectively by the model up to three months in advance (R2 > 0.6). Specifically, we predicted 20% of crisis onsets in pastoral regions (n = 84) and 40% of crisis onsets in agro-pastoral regions (n = 23) with a 3-month lead time. We also compared our 8-month model predictions to the 8-month food-security outlooks produced by FEWS NET. Over a relatively short test period (2020–2022), results suggest the performance of our predictions is similar to FEWS NET for agro-pastoral and pastoral regions. However, our model is clearly less skilled in predicting food security for crop-farming regions than FEWS NET. With the well-established FEWS NET outlooks as a basis, this study highlights the potential for integrating machine-learning methods into operational systems like FEWS NET.