Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand
The provision of potable water as a severe challenge has engaged many people worldwide. So, identifying influential factors in water demand forecasting (WDF) for the residential sector performs a vital role in water crisis management. Nowadays, long-term macro-planning for vast geographical areas he...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2022-08-01
|
| Series: | Water Supply |
| Subjects: | |
| Online Access: | http://ws.iwaponline.com/content/22/8/6833 |
| _version_ | 1811183355420475392 |
|---|---|
| author | Marziyeh Pourmousavi Hossein Nasrollahi Abdolhamid Amirkaveh Najafabadi Ahmad Kalhor |
| author_facet | Marziyeh Pourmousavi Hossein Nasrollahi Abdolhamid Amirkaveh Najafabadi Ahmad Kalhor |
| author_sort | Marziyeh Pourmousavi |
| collection | DOAJ |
| description | The provision of potable water as a severe challenge has engaged many people worldwide. So, identifying influential factors in water demand forecasting (WDF) for the residential sector performs a vital role in water crisis management. Nowadays, long-term macro-planning for vast geographical areas helps policymakers to achieve sustainable development goals. This study uses the same perspective to present a pattern for water consumption behavior and prediction. For this purpose, yearly residential water consumption data, along with climatic characteristics, and socioeconomic factors of rural areas of Isfahan, Iran, are aggregated. The feature selection task is conducted on the collected data using various machine learning (ML) methods along with a novel approach, forward selection based on smoothness index (FSSmI). Posterior to selecting features influencing residential water demand (WD), the raw data are analyzed using regression techniques, including multiple linear regression, support vector regression, and random forest regression. The employed methods show an improvement in the feature selection procedure and coefficient of determination as a result of implementing the FSSmI method. Based on the results, multiple linear regression and support vector regression gain 96% and 95% accuracy and less than 11% and 13% error respectively; it demonstrates the validity of forecasting methods.
HIGHLIGHTS
Machine learning approach is applied to predict residential long-term water demand for a new dataset.;
A novel feature selection method is developed based on the smoothness index criterion and forward selection.;
Testing and comparing machine-learning-based methods are carried out for feature selection and prediction.;
The proposed improvements resulted in better water demand prediction performance.; |
| first_indexed | 2024-04-11T09:46:32Z |
| format | Article |
| id | doaj.art-88f94aae3bf24415b57aef0fb8abd04d |
| institution | Directory Open Access Journal |
| issn | 1606-9749 1607-0798 |
| language | English |
| last_indexed | 2024-04-11T09:46:32Z |
| publishDate | 2022-08-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Water Supply |
| spelling | doaj.art-88f94aae3bf24415b57aef0fb8abd04d2022-12-22T04:30:58ZengIWA PublishingWater Supply1606-97491607-07982022-08-012286833685410.2166/ws.2022.243243Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demandMarziyeh Pourmousavi0Hossein Nasrollahi1Abdolhamid Amirkaveh Najafabadi2Ahmad Kalhor3 Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan 8415683111, Iran Department of Energy Systems, Mechanical Engineering Faculty, K. N. Toosi University of Technology, Tehran 158754416, Iran Department of Engineering Science, College of Engineering, University of Tehran, Tehran 1417935840, Iran School of Electrical and Computer Engineering, University of Tehran, Tehran 1417935840, Iran The provision of potable water as a severe challenge has engaged many people worldwide. So, identifying influential factors in water demand forecasting (WDF) for the residential sector performs a vital role in water crisis management. Nowadays, long-term macro-planning for vast geographical areas helps policymakers to achieve sustainable development goals. This study uses the same perspective to present a pattern for water consumption behavior and prediction. For this purpose, yearly residential water consumption data, along with climatic characteristics, and socioeconomic factors of rural areas of Isfahan, Iran, are aggregated. The feature selection task is conducted on the collected data using various machine learning (ML) methods along with a novel approach, forward selection based on smoothness index (FSSmI). Posterior to selecting features influencing residential water demand (WD), the raw data are analyzed using regression techniques, including multiple linear regression, support vector regression, and random forest regression. The employed methods show an improvement in the feature selection procedure and coefficient of determination as a result of implementing the FSSmI method. Based on the results, multiple linear regression and support vector regression gain 96% and 95% accuracy and less than 11% and 13% error respectively; it demonstrates the validity of forecasting methods. HIGHLIGHTS Machine learning approach is applied to predict residential long-term water demand for a new dataset.; A novel feature selection method is developed based on the smoothness index criterion and forward selection.; Testing and comparing machine-learning-based methods are carried out for feature selection and prediction.; The proposed improvements resulted in better water demand prediction performance.;http://ws.iwaponline.com/content/22/8/6833feature selectionmachine learningmutual informationregression modelwater demand forecasting |
| spellingShingle | Marziyeh Pourmousavi Hossein Nasrollahi Abdolhamid Amirkaveh Najafabadi Ahmad Kalhor Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand Water Supply feature selection machine learning mutual information regression model water demand forecasting |
| title | Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand |
| title_full | Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand |
| title_fullStr | Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand |
| title_full_unstemmed | Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand |
| title_short | Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand |
| title_sort | evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand |
| topic | feature selection machine learning mutual information regression model water demand forecasting |
| url | http://ws.iwaponline.com/content/22/8/6833 |
| work_keys_str_mv | AT marziyehpourmousavi evaluatingtheperformanceoffeatureselectiontechniquesandmachinelearningalgorithmsonfutureresidentialwaterdemand AT hosseinnasrollahi evaluatingtheperformanceoffeatureselectiontechniquesandmachinelearningalgorithmsonfutureresidentialwaterdemand AT abdolhamidamirkavehnajafabadi evaluatingtheperformanceoffeatureselectiontechniquesandmachinelearningalgorithmsonfutureresidentialwaterdemand AT ahmadkalhor evaluatingtheperformanceoffeatureselectiontechniquesandmachinelearningalgorithmsonfutureresidentialwaterdemand |