Prediction of Sewage Treatment Cost in Rural Regions with Multivariate Adaptive Regression Splines
<b> </b>In this paper, to interpret the cost structure of decentralized wastewater treatment plants (DWWTPs) in rural regions, a simple nonparametric regression algorithm known as multivariate adaptive regression spline (MARS) was proposed and applied to simulate the construction cost (C...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-01-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/11/2/195 |
| _version_ | 1811239025814536192 |
|---|---|
| author | Yumin Wang Lei Wu Bernard Engel |
| author_facet | Yumin Wang Lei Wu Bernard Engel |
| author_sort | Yumin Wang |
| collection | DOAJ |
| description | <b> </b>In this paper, to interpret the cost structure of decentralized wastewater treatment plants (DWWTPs) in rural regions, a simple nonparametric regression algorithm known as multivariate adaptive regression spline (MARS) was proposed and applied to simulate the construction cost (CC), operation and maintenance cost (OMC), and total cost (TC). The effects of design treatment capacity (DTC), removal efficiency of chemical oxygen demand (RCOD), and removal efficiency of ammonia nitrogen (RNH<sub>3</sub>-N) on the cost functions of CC, OMC, and TC were analyzed in detail. The results indicated that: (1) DTC is the most important parameter to determine cost structure with relative importance of 100%, followed by RCOD and RNH<sub>3</sub>-N with relative importance of 16.55%, and 9.75%, respectively; (2) when DTC is less than 5 m<sup>3</sup>/d, the slopes of CC and TC on DTC are constants of 1.923 and 1.809, respectively, with no relationship with RCOD and RNH<sub>3</sub>-N; (3) when DTC is less than 20 m<sup>3</sup>/d, the OMC is a constant of 435 RMB/year; and (4) in other cases, CC, OMC, and TC are related to RCOD and RNH<sub>3</sub>-N besides DTC. Compared with widely used support vector machine (SVM) models and multiple linear regression (MLR) models, the MARS model has better statistical significance with greater R values and smaller RMSE and MAPE values, which indicated that the MARS model is a better way to approximate the cost for DWWTPs. |
| first_indexed | 2024-04-12T12:52:33Z |
| format | Article |
| id | doaj.art-72ac12a6023648fb9159494a88aaf9fc |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-04-12T12:52:33Z |
| publishDate | 2019-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-72ac12a6023648fb9159494a88aaf9fc2022-12-22T03:32:25ZengMDPI AGWater2073-44412019-01-0111219510.3390/w11020195w11020195Prediction of Sewage Treatment Cost in Rural Regions with Multivariate Adaptive Regression SplinesYumin Wang0Lei Wu1Bernard Engel2Southeast University, School of Energy and Environment 2# Sipailou Street, Nanjing 210096, ChinaSoutheast University, School of Energy and Environment 2# Sipailou Street, Nanjing 210096, ChinaDepartment of Agricultural and Biological Engineering, Purdue University, West Lafayette 47906, IN, USA<b> </b>In this paper, to interpret the cost structure of decentralized wastewater treatment plants (DWWTPs) in rural regions, a simple nonparametric regression algorithm known as multivariate adaptive regression spline (MARS) was proposed and applied to simulate the construction cost (CC), operation and maintenance cost (OMC), and total cost (TC). The effects of design treatment capacity (DTC), removal efficiency of chemical oxygen demand (RCOD), and removal efficiency of ammonia nitrogen (RNH<sub>3</sub>-N) on the cost functions of CC, OMC, and TC were analyzed in detail. The results indicated that: (1) DTC is the most important parameter to determine cost structure with relative importance of 100%, followed by RCOD and RNH<sub>3</sub>-N with relative importance of 16.55%, and 9.75%, respectively; (2) when DTC is less than 5 m<sup>3</sup>/d, the slopes of CC and TC on DTC are constants of 1.923 and 1.809, respectively, with no relationship with RCOD and RNH<sub>3</sub>-N; (3) when DTC is less than 20 m<sup>3</sup>/d, the OMC is a constant of 435 RMB/year; and (4) in other cases, CC, OMC, and TC are related to RCOD and RNH<sub>3</sub>-N besides DTC. Compared with widely used support vector machine (SVM) models and multiple linear regression (MLR) models, the MARS model has better statistical significance with greater R values and smaller RMSE and MAPE values, which indicated that the MARS model is a better way to approximate the cost for DWWTPs.https://www.mdpi.com/2073-4441/11/2/195multivariate adaptive regression spline (MARS)decentralized wastewater treatment plants (DWWTPs)construction cost (CC)operation & maintenance cost (OMC)total cost (TC) |
| spellingShingle | Yumin Wang Lei Wu Bernard Engel Prediction of Sewage Treatment Cost in Rural Regions with Multivariate Adaptive Regression Splines Water multivariate adaptive regression spline (MARS) decentralized wastewater treatment plants (DWWTPs) construction cost (CC) operation & maintenance cost (OMC) total cost (TC) |
| title | Prediction of Sewage Treatment Cost in Rural Regions with Multivariate Adaptive Regression Splines |
| title_full | Prediction of Sewage Treatment Cost in Rural Regions with Multivariate Adaptive Regression Splines |
| title_fullStr | Prediction of Sewage Treatment Cost in Rural Regions with Multivariate Adaptive Regression Splines |
| title_full_unstemmed | Prediction of Sewage Treatment Cost in Rural Regions with Multivariate Adaptive Regression Splines |
| title_short | Prediction of Sewage Treatment Cost in Rural Regions with Multivariate Adaptive Regression Splines |
| title_sort | prediction of sewage treatment cost in rural regions with multivariate adaptive regression splines |
| topic | multivariate adaptive regression spline (MARS) decentralized wastewater treatment plants (DWWTPs) construction cost (CC) operation & maintenance cost (OMC) total cost (TC) |
| url | https://www.mdpi.com/2073-4441/11/2/195 |
| work_keys_str_mv | AT yuminwang predictionofsewagetreatmentcostinruralregionswithmultivariateadaptiveregressionsplines AT leiwu predictionofsewagetreatmentcostinruralregionswithmultivariateadaptiveregressionsplines AT bernardengel predictionofsewagetreatmentcostinruralregionswithmultivariateadaptiveregressionsplines |