Abstract
Sewer condition is commonly assessed using closed-circuit television (CCTV) inspections. In this paper, we combine inspection results, pipe attributes, network data, and data on pipe environment to predict pipe condition and to discover which factors affect it. We apply the random forest algorithm to model pipe condition and assess the variable importance using the Boruta algorithm. We analyse the impact of predictor variables on poor condition using partial dependence plots, which are a valuable technique for this purpose. The results can be used in screening pipes for future inspections and provide insight into the dynamics between predictor variables and poor condition
| Original language | English |
|---|---|
| Article number | 1239 |
| Pages (from-to) | 1-17 |
| Number of pages | 17 |
| Journal | WATER |
| Volume | 10 |
| Issue number | 9 |
| DOIs | |
| Publication status | Published - 13 Sep 2018 |
| MoE publication type | A1 Journal article-refereed |
Keywords
- Boruta algorithm
- logistic regression
- partial dependence plot
- random forest
- sewer condition
- variable selection
Fingerprint Dive into the research topics of 'Sewer Condition Prediction and Analysis of Explanatory Factors'. Together they form a unique fingerprint.
Cite this
Laakso, T., Kokkonen, T., Mellin, I., & Vahala, R. (2018). Sewer Condition Prediction and Analysis of Explanatory Factors. WATER, 10(9), 1-17. [1239]. https://doi.org/10.3390/w10091239