Forecasting community water system outages

Published February 8, 2024 | Version v1.1.0

Publication Open

The Division of Drinking Water at the California State Water Resources Control Board regulates 2866 Community Water Systems (CWS) throughout the State of California. Some of these CWS risk running out of water during the dry summer season. To address this problem, the Data Science Accelerator at the Office of Data and Innovation collaborated with the Division of Drinking Water to create a machine learning model that forecasts which CWS face the highest risk of running out of water.

Files

Name	Size	Download all
Forecasting community water system outages.pdf md5:0c9880f9a3716e01560b5322a18a4aff	756.2 kB	Preview Download

Albert, R., & Barabási, A. L. (2002). Statistical mechanics of complex networks. Reviews of modern physics, 74(1), 47. https://doi.org/10.1103/RevModPhys.74.47
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20, 273-297. https://doi.org/10.1007/BF00994018
Mothilal, R. K., Sharma, A., & Tan, C. (2020, January). Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 conference on fairness, accountability, and transparency (pp. 607-617). https://doi.org/10.1145/3351095.3372850
Mullin, M. (2020). The effects of drinking water service fragmentation on drought-related water security. Science, 368(6488), 274-277. https://doi.org/10.1126/science.aba7353
Fabian, P. (2011). Scikit-learn: Machine learning in Python. Journal of machine learning research 12, 2825. https://jmlr.org/papers/volume12/pedregosa11a/pedregosa11a.pdf