Leveraging an Aggressive Inspection Program and Predictive Modeling to Develop an LSL Inventory for Jackson
Bibliographic record
Abstract
When it comes to building a lead service line inventory, a one-size-fits-all approach is not a good fit for most communities. The reality is that most water agencies tend to have incomplete data—often found in a mix of paper records, spreadsheets, databases, PDF documents, and geographic information system (GIS) data. This was the case in Jackson, Mississippi. With little to no available records, a multi-pronged methodology was required. Under the direction of JXN Water, Inc., third-party manager for Jackson’s water distribution system, a service line (SL) inventory was developed using an aggressive potholing inspection program. Consisting of approximately 400 residential locations plus all 55 Jackson Public Schools, the team carried out approximately 1,600 inspections by hydro excavating and testing the lines. An ongoing meter replacement program also provided targeted information to aid inventory development. A key component to the success of this aggressive field program was the public outreach coordination across numerous consultants, contractors, and JXN Water. All the field potholing information obtained was input into a machine learning tool and using predictive modeling was able to guide teams in the next set of inspections. With the use of predictive modeling, the inspections were specifically targeted, resulting in cost savings. This paper will discuss Jackson, Mississippi’s story of successes and lessons learned in building, and maturing, their Lead Service Line Inventory and Replacement Plan. This program is just one important piece to rebuild the community’s trust in their water agency, all the while complying with the EPA’s Lead and Copper Rule Revisions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".