• Energy Research
• 13. Climate action close
• BE close
• Netherlands close

Food insecurity is a growing concern due to man-made conflicts, climate change, and economic downturns. Forecasting the state of food insecurity is essential to be able to trigger early actions, for example, by humanitarian actors. To measure the actual state of food insecurity, expert and consensus-based approaches and surveys are currently used. Both require substantial manpower, time, and budget. This paper introduces an extreme gradient-boosting machine learning model 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. The transition in the state of food security, hereafter referred to as predictand, is represented by the Integrated Food Security Phase Classification Data. From 19 categories of datasets, 130 variables were derived and used as predictors of the transition in the state of food security. The predictors represent changes in climate and land, market, conflict, infrastructure, demographics and livelihood zone characteristics. The most relevant predictors are found to be food security history and surface soil moisture. Overall, the model performs best for forecasting Deteriorations and Improvements in the state of food security compared to the baselines. The proposed method performs (F1 macro score) at least twice as well as the best baseline (a dummy classifier) for a Deterioration. The model performs better when forecasting long-term (7 months; F1 macro average = 0.61) compared to short-term (3 months; F1 macro average = 0.51). Combining machine learning, Integrated Phase Classification (IPC) ratings from monitoring systems, and open data can add value to existing consensus-based forecasting approaches as this combination provides longer lead times and more regular updates. Our approach can also be transferred to other countries as most of the data on the predictors are openly available from global data repositories.

Food insecurity is a growing concern due to man-made conflicts, climate change, and economic downturns. Forecasting the state of food insecurity is essential to be able to trigger early actions, for example, by humanitarian actors. To measure the actual state of food insecurity, expert and consensus-based approaches and surveys are currently used. Both require substantial manpower, time, and budget. This paper introduces an extreme gradient-boosting machine learning model 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. The transition in the state of food security, hereafter referred to as predictand, is represented by the Integrated Food Security Phase Classification Data. From 19 categories of datasets, 130 variables were derived and used as predictors of the transition in the state of food security. The predictors represent changes in climate and land, market, conflict, infrastructure, demographics and livelihood zone characteristics. The most relevant predictors are found to be food security history and surface soil moisture. Overall, the model performs best for forecasting Deteriorations and Improvements in the state of food security compared to the baselines. The proposed method performs (F1 macro score) at least twice as well as the best baseline (a dummy classifier) for a Deterioration. The model performs better when forecasting long-term (7 months; F1 macro average = 0.61) compared to short-term (3 months; F1 macro average = 0.51). Combining machine learning, Integrated Phase Classification (IPC) ratings from monitoring systems, and open data can add value to existing consensus-based forecasting approaches as this combination provides longer lead times and more regular updates. Our approach can also be transferred to other countries as most of the data on the predictors are openly available from global data repositories.

SummaryRecent observations suggest that repeated fires could drive Mediterranean forests to shrublands, hosting flammable vegetation that regrows quickly after fire. This feedback supposedly favours shrubland persistence and may be strengthened in the future by predicted increased aridity. An assessment was made of how fires and aridity in combination modulated the dynamics of Mediterranean ecosystems and whether the feedback could be strong enough to maintain shrubland as an alternative stable state to forest.A model was developed for vegetation dynamics, including stochastic fires and different plant fire‐responses. Parameters were calibrated using observational data from a period up to 100 yr ago, from 77 sites with and without fires in Southeast Spain and Southern France.The forest state was resilient to the separate impact of fires and increased aridity. However, water stress could convert forests into open shrublands by hampering post‐fire recovery, with a possible tipping point at intermediate aridity.Projected increases in aridity may reduce the resilience of Mediterranean forests against fires and drive post‐fire ecosystem dynamics toward open shrubland. The main effect of increased aridity is the limitation of post‐fire recovery. Including plant fire‐responses is thus fundamental when modelling the fate of Mediterranean‐type vegetation under climate‐change scenarios.

SummaryRecent observations suggest that repeated fires could drive Mediterranean forests to shrublands, hosting flammable vegetation that regrows quickly after fire. This feedback supposedly favours shrubland persistence and may be strengthened in the future by predicted increased aridity. An assessment was made of how fires and aridity in combination modulated the dynamics of Mediterranean ecosystems and whether the feedback could be strong enough to maintain shrubland as an alternative stable state to forest.A model was developed for vegetation dynamics, including stochastic fires and different plant fire‐responses. Parameters were calibrated using observational data from a period up to 100 yr ago, from 77 sites with and without fires in Southeast Spain and Southern France.The forest state was resilient to the separate impact of fires and increased aridity. However, water stress could convert forests into open shrublands by hampering post‐fire recovery, with a possible tipping point at intermediate aridity.Projected increases in aridity may reduce the resilience of Mediterranean forests against fires and drive post‐fire ecosystem dynamics toward open shrubland. The main effect of increased aridity is the limitation of post‐fire recovery. Including plant fire‐responses is thus fundamental when modelling the fate of Mediterranean‐type vegetation under climate‐change scenarios.