Managing the water–electricity demand nexus in a warming climate

Models that consider the interconnectivity between urban systems, including water and electricity, are becoming more common, both in research and in practice. However, there are still too few that consider the impact of climate change, and fewer still that look beyond the baseline climate data (i.e., precipitation and temperature). Here, a data-driven, regional model that considers a wider array of climate variables is built and tested to evaluate the impact of climate change on the coupled water and electricity demand nexus in the Midwestern USA. The model, which is based on a state-of-the-art statistical learning algorithm, is first used to compare model runs comprised of different climatic variables. The model runs included a baseline model that considers only precipitation and temperature, as well as a selected feature model that considered a wider array of climatic variables, including relative humidity and wind speed. Following this comparison, the model is used to make future projections of the coupled water and electricity demand as a function of future climate change scenarios. The results indicate that (1) the inclusion of additional climate variables beyond the baseline provides a significant improvement in predictive accuracy, and (2) the climate-sensitive portions of summer electricity and water use are expected to increase in the region by 19% and 7%, respectively. Finally, the regional-scale model is leveraged to make city-level projections, indicating a 10–20% (2–5%) increase in electricity (water) use across the analyzed cities due to a warming climate.