TY - JOUR
T1 - Combining a statistical model with machine learning to predict groundwater flooding (or infiltration) into sewer networks
AU - Liu, Ting
AU - Ramirez-Marquez, Jose E.
AU - Jagupilla, Sarath Chandra
AU - Prigiobbe, Valentina
N1 - Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2021/12
Y1 - 2021/12
N2 - Groundwater flooding (or infiltration) in sewer systems leads to significant negative consequences such as discharge of untreated sewage, reduction of system capacity, structural deterioration, and dilution of the wastewater stream delivered to a treatment plant causing malfunction. Cities with aging networks along coastal areas, where aquifers are shallow, are particularly vulnerable. Rehabilitation is necessary to mitigate the negative impact of infiltration but costly. Therefore, a prioritization strategy of intervention is required. This paper presents a decision-support model to identify the probability of infiltration into aging sewer when observations of infiltration and sewer conditions are sparse and time-limited. The model is based on logistic regression, where the variables are: material, soil, water table, and pipe size and shape. As a proof-of-concept, the method was applied to the city of Hoboken, NJ. Machine learning was used to calibrate, validate, and test the model using infiltration measurements, provided by the water authority. Upon calibration, model predictions agree well with the measurements with an accuracy of 82%. Sensitivity analysis of the model was carried out and shows that the most important parameter is the water table of the shallow aquifer. Overall, the proposed approach can be a valuable tool for strategic intervention of sewer repair and flood mitigation in urban areas.
AB - Groundwater flooding (or infiltration) in sewer systems leads to significant negative consequences such as discharge of untreated sewage, reduction of system capacity, structural deterioration, and dilution of the wastewater stream delivered to a treatment plant causing malfunction. Cities with aging networks along coastal areas, where aquifers are shallow, are particularly vulnerable. Rehabilitation is necessary to mitigate the negative impact of infiltration but costly. Therefore, a prioritization strategy of intervention is required. This paper presents a decision-support model to identify the probability of infiltration into aging sewer when observations of infiltration and sewer conditions are sparse and time-limited. The model is based on logistic regression, where the variables are: material, soil, water table, and pipe size and shape. As a proof-of-concept, the method was applied to the city of Hoboken, NJ. Machine learning was used to calibrate, validate, and test the model using infiltration measurements, provided by the water authority. Upon calibration, model predictions agree well with the measurements with an accuracy of 82%. Sensitivity analysis of the model was carried out and shows that the most important parameter is the water table of the shallow aquifer. Overall, the proposed approach can be a valuable tool for strategic intervention of sewer repair and flood mitigation in urban areas.
KW - Coastal cities
KW - Flooding
KW - Infrastructure
KW - Machine learning
KW - Sewer infiltration
KW - Urban hydrology
UR - http://www.scopus.com/inward/record.url?scp=85115143965&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85115143965&partnerID=8YFLogxK
U2 - 10.1016/j.jhydrol.2021.126916
DO - 10.1016/j.jhydrol.2021.126916
M3 - Article
AN - SCOPUS:85115143965
SN - 0022-1694
VL - 603
JO - Journal of Hydrology
JF - Journal of Hydrology
M1 - 126916
ER -