Monitoring hydropower reliability in Malawi with satellite data and machine learning

Hydro-climatic extremes can affect the reliability of electricity supply, in par-ticular in countries that depend greatly on hydropower or cooling water andhave a limited adaptive capacity. Assessments of the vulnerability of the powersector and of the impact of extreme events are thus crucial for decision-makers,and yet often they are severely constrained by data scarcity. Here, we intro-duce and validate an energy-climate-water framework linking remotely-senseddata from multiple satellite missions and instruments (TOPEX/POSEIDON.OSTM/Jason, VIIRS, MODIS, TMPA, AMSR-E) and field observations. Theplatform exploits random forests regression algorithms to mitigate data scarcityand predict river discharge variability when ungauged. The validated predic-tions are used to assess the impact of hydroclimatic extremes on hydropowerreliability and on the final use of electricity in urban areas proxied by night-time light radiance variation. We apply the framework to the case of Malawifor the periods 2000-2018 and 2012-2018 for hydrology and power, respectively.Our results highlight the significant impact of hydro-climatic variability anddry extremes on both the supply of electricity and its final use. We thus showthat a modelling framework based on open-access data from satellites, machinelearning algorithms, and regression analysis can mitigate data scarcity and im-prove the understanding of vulnerabilities. The proposed approach can supportlong-term infrastructure development monitoring and identify vulnerable pop-ulations, in particular under a changing climate.