Search

In this study, we present a machine‐learning model capable of predicting food insecurity in the Horn of Africa, which is one of the most vulnerable regions worldwide. The region has frequently been affected by severe droughts and food crises over the last several decades, which will likely increase in future. Therefore, exploring novel methods of increasing early warning capabilities is of vital importance to reducing food‐insecurity risk. We present a XGBoost machine‐learning model to predict food‐security crises up to 12 months in advance. We used >20 data sets and the FEWS IPC current‐situation estimates to train the machine‐learning model. Food‐security dynamics were captured effectively by the model up to 3 months in advance (R2 > 0.6). Specifically, we predicted 20% of crisis onsets in pastoral regions (n = 96) and 20%–50% of crisis onsets in agro‐pastoral regions (n = 22) 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 (2019–2022), 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. Plain Language Summary: In the face of increasing droughts and food crises, this study explored the use of machine learning to provide predictions of food crises in the Horn of Africa, up to 12 months in advance. We used an algorithm called "XGBoost," which we fed with over 20 data sets of potential food security drivers. After training the model, we found that food security dynamics were accurately predicted up to 3 months in advance, especially in pastoral and agro‐pastoral regions. The model accurately predicted 20% of crisis onsets in pastoral areas and 20%–50% in agro‐pastoral regions with a 3‐month lead time. In agro‐pastoral and pastoral regions, our machine learning algorithm showed a similar performance to the established early warning system from FEWS NET. The machine‐learning model did not show good performance in crop‐farming areas. Nonetheless, this study underscores the potential of integrating machine‐learning methods into existing operational systems like FEWS NET. By doing so, it paves the way for improved early warning capabilities, crucial in mitigating the looming threat of food insecurity in the Horn of Africa. Key Points: A machine‐learning model is presented to predict food‐security crises in the Horn of AfricaThe model demonstrates high overall performance, and performs similarly to FEWS NET outlooks in the (agro‐) pastoral regionsThis study can be utilized to integrate machine learning into existing early warning systems, thereby creating hybrid solutions for the future [ABSTRACT FROM AUTHOR]

The Horn of Africa Drylands are increasingly experiencing severe droughts, which impose a threat on traditional livelihood strategies. Understanding adaptation behavior in rural communities is key to helping reduce the impact of these droughts. We investigate adaptation behavior by assessing four established economic and social psychological theories on decision making under risk: expected utility theory (EUT), rank dependent utility theory (RDU), protection motivation theory (PMT), and theory of planned behavior (PMT). To measure adaptation behavior and the theory constructs, we conducted a household survey in Kenya (N = 502). Regression analysis shows that the economic theories (EUT and RDU) have the best fit for our data. Risk and time preferences are found to play an important role in adaptation decisions. An analysis of differences in decision making for distinct types of adaptation measures shows that risk averse (agro‐)pastoralists are more likely to implement adaptation measures that are adjustments to their current livelihood practices, and less willing to invest in adaptation measures that require a shift to other livelihood activities. Moreover, we find significant effects for elements of the social psychological theories (PMT and TPB). A person's belief in their own ability to implement an adaptation measure (perceived self‐efficacy) and adaptation by family and friends are important factors in explaining adaptation decisions. Finally, we find that the type of adaptation measures that people implement is influenced by, among others, gender, education level, access to financial resources, and access to government support or aid. Our analysis gives insights into the drivers of individual adaptation decisions, which can enhance policies promoting adaptation of dryland communities. [ABSTRACT FROM AUTHOR]

Advances in the field of extreme event attribution allow to estimate how anthropogenic global warming affects the odds of individual climate disasters, such as river floods. Extreme event attribution typically uses precipitation as proxy for flooding. However, hydrological processes and antecedent conditions make the relation between precipitation and floods highly nonlinear. In addition, hydrology acknowledges that changes in floods can be strongly driven by changes in land‐cover and by other human interventions in the hydrological system, such as irrigation and construction of dams. These drivers can either amplify, dampen or outweigh the effect of climate change on local flood occurrence. Neglecting these processes and drivers can lead to incorrect flood attribution. Including flooding explicitly, that is, using data and models of hydrology and hydrodynamics that can represent the relevant hydrological processes, will lead to more robust event attribution, and will account for the role of other drivers beyond climate change. Existing attempts are incomplete. We argue that the existing probabilistic framework for extreme event attribution can be extended to explicitly include floods for near‐natural cases, where flood occurrence was unlikely to be influenced by land‐cover change and human hydrological interventions. However, for the many cases where this assumption is not valid, a multi‐driver framework for conditional event attribution needs to be established. Explicit flood attribution will have to grapple with uncertainties from lack of observations and compounding from the many processes involved. Further, it requires collaboration between climatologists and hydrologists, and promises to better address the needs of flood risk management. This article is categorized under:Paleoclimates and Current Trends > Modern Climate ChangePaleoclimates and Current Trends > Detection and AttributionAssessing Impacts of Climate Change > Observed Impacts of Climate Change [ABSTRACT FROM AUTHOR]

Critical infrastructure (CI) is exposed to natural hazards that may lead to the devastation of these infrastructures and burden society with the indirect consequences that stem from this. The vulnerability is a key determinant for understanding, assessing and reducing natural hazard-induced risks to these infrastructures. To date, however, essential vulnerability information for CI is distributed across literature instead of being accessible through a centralized dataset. This study, through a systematic literature review, synthesises the state-of-the-art of fragility and vulnerability curves for CI assets of energy, transport, water, waste, telecoms, health and education in context of natural hazards and offers a unique physical vulnerability database. The publicly available centralized database that contains over 1,250 curves can directly be used as input for risk assessment studies that evaluate the expected or potential damages to assets due to flooding, earthquakes, windstorms and landslides. The literature review highlights that vulnerability development has mainly focused on earthquake curves for a wide range of infrastructure types. Windstorms have the second largest share in the database, but are especially limited to energy curves. While all CI systems require more vulnerability research, additional efforts are needed for telecommunication which is largely underrepresented in our database. [ABSTRACT FROM AUTHOR]

Coastal flooding and sea level rise (SLR) will affect farmers in coastal areas, as increasing salinity levels will reduce crop yields, leading to a loss of net annual income for farming communities. In response, farmers can take various actions. In order to assess such a response under SLR, we applied an agent-based model (ABM) to simulate the adaptation and migration decisions of farmers in coastal Mozambique. The ABM is coupled with a salinization module to simulate the relationship between soil salinity and SLR. The decision rules in the model (DYNAMO-M) are based on the economic theory of subjective expected utility. This theory posits that households can maximize their welfare by deciding whether to (a) stay and face losses from salinization and flooding, (b) stay and adapt (switching to salt-tolerant crops and enhancing physical resilience such as elevating houses), or (c) migrate to safer inland areas. The results show that coastal farmers in Mozambique face total losses of up to US$12.5 million per year from salt intrusion and up to US$800 million per year from flooding of buildings (RCP8.5 in the year 2080). Sorghum farmers may experience little damage from salt intrusion, while rice farmers may experience losses of up to US$15,000 per year. We show that medium-sized farmers (1–20 ha) are most at risk. This is because their farm size means that adaptation costs are substantial, while their incomes are too low to cover these costs. The number of households adapting varies between different districts (6 %–50 %), with salt adaptation being the most common, as costs are lowest. Despite adaptation measures, about 13 %–20 % of the total 300,000 farmers in coastal flood zones will migrate to safer areas under different settings of adaptive behaviour and different climatic and socioeconomic scenarios. [ABSTRACT FROM AUTHOR]