National UCMR 5 records processed through the reproducible analytical pipeline.
PROJECT 01 / National Water Intelligence · EPA UCMR 5
PFAS Drinking Water Decision Intelligence
A national-scale decision intelligence project that turns EPA UCMR 5 drinking-water monitoring data into transparent engineering priorities, utility treatment strategy, lifecycle economics, and capital-allocation scenarios for PFAS infrastructure planning.
NATIONAL DRINKING-WATER DECISION INTELLIGENCEPFAS
Screening national occurrence data, identifying systems that warrant deeper engineering review, and testing how treatment economics and constrained public funding can shape infrastructure decisions.
1.99MAnalytical results
10,313Water systems
1,127Screened forward
388Tier 1 priorities
DATASETU.S. EPA Fifth Unregulated Contaminant Monitoring Rule (UCMR 5)
SIZE1,992,002 analytical results · 10,313 public water systems · 26,732 sampling points
MEASURED EVIDENCE
What can be verified.
Metrics and outputs drawn from the project artifacts, not estimates added for presentation.
Systems represented in the national drinking-water analysis.
PWSs with at least one PFOA or PFOS screening trigger under the documented method.
Systems placed in the highest engineering-review priority tier.
VALIDATION
The repository documents structural QA, explicit PFOA/PFOS screening assumptions, a decomposable 100-point priority model, three verified utility case studies, 20-year lifecycle cost sensitivity analysis, and $100M–$1B capital-assistance scenarios. UCMR 5 occurrence results are used for technical screening and prioritization; they do not by themselves establish regulatory compliance or noncompliance.
Why this project matters
PFAS in drinking water is a national infrastructure concern, but occurrence data alone do not tell engineers, utilities, funders, or policy teams where deeper review should begin. The challenge is to move from millions of monitoring records to a transparent view of potential treatment need, utility context, lifecycle economics, and funding priorities.
What was developed
The project builds a reproducible EPA data pipeline, applies documented PFOA/PFOS screening logic, ranks 1,127 systems with a transparent engineering-review framework, verifies three real-world utility case studies, models 20-year lifecycle cost sensitivity, and tests constrained capital-assistance portfolios with mixed-integer optimization.
What it means
The analysis creates an auditable planning framework rather than a black-box ranking. It separates measured EPA evidence from engineering assumptions, verified utility facts, cost assumptions, and policy choices, helping reviewers see what is known, what is assumed, and what should be investigated next.
04 / WHERE THIS WORK APPLIES
From project to practical use.
This work can support drinking-water utilities, environmental and civil engineering teams, state revolving-fund programs, emerging-contaminant assistance programs, public-sector capital planning, treatment-alternative screening, affordability analysis, and infrastructure portfolio prioritization. The verified Fayetteville, Emmaus, and Waite Park case studies also show how the same national screening signal can lead to very different next decisions depending on utility size, treatment stage, cost exposure, and project readiness.
05 / LIMITATION
What the project does not solve, yet.
The national model does not contain nationally consistent current design flow, exact current population, project readiness, site-specific treatment cost, or complete current process-train information for every screened system. UCMR size class is therefore used only as an explicit exposure proxy, and UCMR treatment and potential-source fields are treated as contextual rather than verified current engineering conditions.
06 / NEXT ITERATION
Future advancement
Add exact current population served, disadvantaged-community and affordability indicators, project readiness and permitting, secured funding and remaining funding gap, site-specific design flow and treatment cost, state priority-list rules, resilience co-benefits, and utility match capacity so the allocation model can move closer to real program decision support.
TECHNICAL TOOLKIT
PythonSQLSQLiteEPA UCMR 5Data QAEngineering PrioritizationLifecycle Cost ModelingMixed-Integer OptimizationScenario Analysis