Automated model construction for combined sewer overflow prediction based on efficient LASSO algorithm
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 12 - Engineering
- Output identifier
- 96142831
- Type
- D - Journal article
- DOI
-
10.1109/TSMC.2017.2724440
- Title of journal
- IEEE Transactions on Systems Man and Cybernetics: Systems
- Article number
- -
- First page
- 1254
- Volume
- 49
- Issue
- 6
- ISSN
- 2168-2216
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2017
- URL
-
http://dx.doi.org/10.1109/TSMC.2017.2724440
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents the first use of automated model construction algorithms applied to Waste Water Networks. This is significant because it replaces previous approaches of manually developing data driven models for each asset/variable within the network, creating significant savings and, increasing accuracy. This approach has been trialled on an operating waste water network and was found to achieve an accuracy of up to 90%, with only limited human involvement in the process of model construction. Following this work, this approach is currently being considered by Dŵr Cymru Welsh Water as a solution for their flooding prediction needs.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -