Optimizing Household Water Decisions for Managing Intermittent Water Supply in Mexico City

One billion people worldwide experience intermittent water supply (IWS), in which piped is delivered for limited durations. Households with IWS must invest storage infrastructure and often rely on multiple sources of water; therefore, these household-level purchasing decisions a critical component access. Informed by interviews households, we use radial basis function networks, type artificial neural network, to determine optimal household management that maximize reliability while minimizing costs representative Mexico City uses municipal water, trucked rainwater. We find securing reliable households greatly assisted installation tanks at least 2500 L. In the case options, overall cost reduced scheduling deliveries nonconsecutive days. Rainwater harvesting systems were shown be economically viable supply. This study demonstrates importance considering when evaluating investments cities IWS.