Modeling Semiarid River–Aquifer Systems with Bayesian Networks and Artificial Neural Networks
In semiarid areas, precipitations usually appear in the form of big and brief floods, which affect the aquifer through water infiltration, causing groundwater temperature changes. These changes may have an impact on the physical, chemical and biological processes of the aquifer and, thus, modeling t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/1/107 |
| _version_ | 1827668180313571328 |
|---|---|
| author | Ana D. Maldonado María Morales Francisco Navarro Francisco Sánchez-Martos Pedro A. Aguilera |
| author_facet | Ana D. Maldonado María Morales Francisco Navarro Francisco Sánchez-Martos Pedro A. Aguilera |
| author_sort | Ana D. Maldonado |
| collection | DOAJ |
| description | In semiarid areas, precipitations usually appear in the form of big and brief floods, which affect the aquifer through water infiltration, causing groundwater temperature changes. These changes may have an impact on the physical, chemical and biological processes of the aquifer and, thus, modeling the groundwater temperature variations associated with stormy precipitation episodes is essential, especially since this kind of precipitation is becoming increasingly frequent in semiarid regions. In this paper, we compare the predictive performance of two popular tools in statistics and machine learning, namely Bayesian networks (BNs) and artificial neural networks (ANNs), in modeling groundwater temperature variation associated with precipitation events. More specifically, we trained a total of 2145 ANNs with different node configurations, from one to five layers. On the other hand, we trained three different BNs using different structure learning algorithms. We conclude that, while both tools are equivalent in terms of accuracy for predicting groundwater temperature drops, the computational cost associated with the estimation of Bayesian networks is significantly lower, and the resulting BN models are more versatile and allow a more detailed analysis. |
| first_indexed | 2024-03-10T03:31:30Z |
| format | Article |
| id | doaj.art-0ebe857edaf84d83b962a0991ead4e6e |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T03:31:30Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-0ebe857edaf84d83b962a0991ead4e6e2023-11-23T11:54:13ZengMDPI AGMathematics2227-73902021-12-0110110710.3390/math10010107Modeling Semiarid River–Aquifer Systems with Bayesian Networks and Artificial Neural NetworksAna D. Maldonado0María Morales1Francisco Navarro2Francisco Sánchez-Martos3Pedro A. Aguilera4Department of Mathematics, University of Almería, 04120 Almería, SpainDepartment of Mathematics, University of Almería, 04120 Almería, SpainDepartment of Biology and Geology, University of Almería, 04120 Almería, SpainDepartment of Biology and Geology, University of Almería, 04120 Almería, SpainDepartment of Biology and Geology, University of Almería, 04120 Almería, SpainIn semiarid areas, precipitations usually appear in the form of big and brief floods, which affect the aquifer through water infiltration, causing groundwater temperature changes. These changes may have an impact on the physical, chemical and biological processes of the aquifer and, thus, modeling the groundwater temperature variations associated with stormy precipitation episodes is essential, especially since this kind of precipitation is becoming increasingly frequent in semiarid regions. In this paper, we compare the predictive performance of two popular tools in statistics and machine learning, namely Bayesian networks (BNs) and artificial neural networks (ANNs), in modeling groundwater temperature variation associated with precipitation events. More specifically, we trained a total of 2145 ANNs with different node configurations, from one to five layers. On the other hand, we trained three different BNs using different structure learning algorithms. We conclude that, while both tools are equivalent in terms of accuracy for predicting groundwater temperature drops, the computational cost associated with the estimation of Bayesian networks is significantly lower, and the resulting BN models are more versatile and allow a more detailed analysis.https://www.mdpi.com/2227-7390/10/1/107Bayesian networksartificial neural networksgroundwater temperatureclassificationsemiarid areas |
| spellingShingle | Ana D. Maldonado María Morales Francisco Navarro Francisco Sánchez-Martos Pedro A. Aguilera Modeling Semiarid River–Aquifer Systems with Bayesian Networks and Artificial Neural Networks Mathematics Bayesian networks artificial neural networks groundwater temperature classification semiarid areas |
| title | Modeling Semiarid River–Aquifer Systems with Bayesian Networks and Artificial Neural Networks |
| title_full | Modeling Semiarid River–Aquifer Systems with Bayesian Networks and Artificial Neural Networks |
| title_fullStr | Modeling Semiarid River–Aquifer Systems with Bayesian Networks and Artificial Neural Networks |
| title_full_unstemmed | Modeling Semiarid River–Aquifer Systems with Bayesian Networks and Artificial Neural Networks |
| title_short | Modeling Semiarid River–Aquifer Systems with Bayesian Networks and Artificial Neural Networks |
| title_sort | modeling semiarid river aquifer systems with bayesian networks and artificial neural networks |
| topic | Bayesian networks artificial neural networks groundwater temperature classification semiarid areas |
| url | https://www.mdpi.com/2227-7390/10/1/107 |
| work_keys_str_mv | AT anadmaldonado modelingsemiaridriveraquifersystemswithbayesiannetworksandartificialneuralnetworks AT mariamorales modelingsemiaridriveraquifersystemswithbayesiannetworksandartificialneuralnetworks AT francisconavarro modelingsemiaridriveraquifersystemswithbayesiannetworksandartificialneuralnetworks AT franciscosanchezmartos modelingsemiaridriveraquifersystemswithbayesiannetworksandartificialneuralnetworks AT pedroaaguilera modelingsemiaridriveraquifersystemswithbayesiannetworksandartificialneuralnetworks |