Machine Learning Models for Spring Discharge Forecasting
Nowadays, drought phenomena increasingly affect large areas of the globe; therefore, the need for a careful and rational management of water resources is becoming more pressing. Considering that most of the world’s unfrozen freshwater reserves are stored in aquifers, the capability of prediction of...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Geofluids |
| Online Access: | http://dx.doi.org/10.1155/2018/8328167 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832559086137245696 |
|---|---|
| author | Francesco Granata Michele Saroli Giovanni de Marinis Rudy Gargano |
| author_facet | Francesco Granata Michele Saroli Giovanni de Marinis Rudy Gargano |
| author_sort | Francesco Granata |
| collection | DOAJ |
| description | Nowadays, drought phenomena increasingly affect large areas of the globe; therefore, the need for a careful and rational management of water resources is becoming more pressing. Considering that most of the world’s unfrozen freshwater reserves are stored in aquifers, the capability of prediction of spring discharges is a crucial issue. An approach based on water balance is often extremely complicated or ineffective. A promising alternative is represented by data-driven approaches. Recently, many hydraulic engineering problems have been addressed by means of advanced models derived from artificial intelligence studies. Three different machine learning algorithms were used for spring discharge forecasting in this comparative study: M5P regression tree, random forest, and support vector regression. The spring of Rasiglia Alzabove, Umbria, Central Italy, was selected as a case study. The machine learning models have proven to be able to provide very encouraging results. M5P provides good short-term predictions of monthly average flow rates (e.g., in predicting average discharge of the spring after 1 month, R2=0.991, RAE=14.97%, if a 4-month input is considered), while RF is able to provide accurate medium-term forecasts (e.g., in forecasting average discharge of the spring after 3 months, R2=0.964, RAE=43.12%, if a 4-month input is considered). As the time of forecasting advances, the models generally provide less accurate predictions. Moreover, the effectiveness of the models significantly depends on the duration of the period considered for input data. This duration should be close to the aquifer response time, approximately estimated by cross-correlation analysis. |
| format | Article |
| id | doaj-art-8c43e87095d74749bcab1362c7138d8e |
| institution | Kabale University |
| issn | 1468-8115 1468-8123 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Geofluids |
| spelling | doaj-art-8c43e87095d74749bcab1362c7138d8e2025-02-03T01:30:55ZengWileyGeofluids1468-81151468-81232018-01-01201810.1155/2018/83281678328167Machine Learning Models for Spring Discharge ForecastingFrancesco Granata0Michele Saroli1Giovanni de Marinis2Rudy Gargano3Department of Civil and Mechanical Engineering, University of Cassino and Southern Lazio, via G. Di Biasio 43, 03043 Cassino (FR), ItalyDepartment of Civil and Mechanical Engineering, University of Cassino and Southern Lazio, via G. Di Biasio 43, 03043 Cassino (FR), ItalyDepartment of Civil and Mechanical Engineering, University of Cassino and Southern Lazio, via G. Di Biasio 43, 03043 Cassino (FR), ItalyDepartment of Civil and Mechanical Engineering, University of Cassino and Southern Lazio, via G. Di Biasio 43, 03043 Cassino (FR), ItalyNowadays, drought phenomena increasingly affect large areas of the globe; therefore, the need for a careful and rational management of water resources is becoming more pressing. Considering that most of the world’s unfrozen freshwater reserves are stored in aquifers, the capability of prediction of spring discharges is a crucial issue. An approach based on water balance is often extremely complicated or ineffective. A promising alternative is represented by data-driven approaches. Recently, many hydraulic engineering problems have been addressed by means of advanced models derived from artificial intelligence studies. Three different machine learning algorithms were used for spring discharge forecasting in this comparative study: M5P regression tree, random forest, and support vector regression. The spring of Rasiglia Alzabove, Umbria, Central Italy, was selected as a case study. The machine learning models have proven to be able to provide very encouraging results. M5P provides good short-term predictions of monthly average flow rates (e.g., in predicting average discharge of the spring after 1 month, R2=0.991, RAE=14.97%, if a 4-month input is considered), while RF is able to provide accurate medium-term forecasts (e.g., in forecasting average discharge of the spring after 3 months, R2=0.964, RAE=43.12%, if a 4-month input is considered). As the time of forecasting advances, the models generally provide less accurate predictions. Moreover, the effectiveness of the models significantly depends on the duration of the period considered for input data. This duration should be close to the aquifer response time, approximately estimated by cross-correlation analysis.http://dx.doi.org/10.1155/2018/8328167 |
| spellingShingle | Francesco Granata Michele Saroli Giovanni de Marinis Rudy Gargano Machine Learning Models for Spring Discharge Forecasting Geofluids |
| title | Machine Learning Models for Spring Discharge Forecasting |
| title_full | Machine Learning Models for Spring Discharge Forecasting |
| title_fullStr | Machine Learning Models for Spring Discharge Forecasting |
| title_full_unstemmed | Machine Learning Models for Spring Discharge Forecasting |
| title_short | Machine Learning Models for Spring Discharge Forecasting |
| title_sort | machine learning models for spring discharge forecasting |
| url | http://dx.doi.org/10.1155/2018/8328167 |
| work_keys_str_mv | AT francescogranata machinelearningmodelsforspringdischargeforecasting AT michelesaroli machinelearningmodelsforspringdischargeforecasting AT giovannidemarinis machinelearningmodelsforspringdischargeforecasting AT rudygargano machinelearningmodelsforspringdischargeforecasting |