Case Studies of Using Statistics and Machine Learning to Inventory and Locate Lead Service Lines

New regulations require utilities to create and maintain service line inventories. Incomplete, inaccurate, and unreliable historical records make it challenging to use service line inventories to inform planning, support decisions, and communicate risk to the public. Best practices in statistics and data science can be used to develop more accurate inventories, create realistic budgets, inform capital planning, and manage lead service line (LSL) replacement programs. We partnered with the Association of State Drinking Water Administrators (ASDWA) to outline important considerations for state regulators and utility leadership when using statistical and predictive methods for LSL inventory and replacement. Water systems can use these principles to plan strategically, make data-driven decisions, set budgets and requests for funds, build capacity in some skill areas, communicate with the public and build trust, and, most importantly, continue to protect the health of all individuals in the system.