Applications of hybrid dynamic Bayesian networks to water reservoir management
Bayesian networks (BNs) have been widely applied in environmental modelling to predict the behaviour of an ecosystem under conditions of change. However, this approximation doesn’t take time into consideration. To solve this issue, an extension of BNs, the dynamic Bayesian networks (DBNs), has been...
| Main Authors: | , , , |
|---|---|
| 格式: | info:eu-repo/semantics/article |
| 语言: | English |
| 出版: |
Wiley
2024
|
| 主题: | |
| 在线阅读: | http://hdl.handle.net/10835/15029 |
| _version_ | 1789406360825233408 |
|---|---|
| author | Fernández Ropero, Rosa María Flores Gallego, María Julia Rumí Rodríguez, Rafael Aguilera Aguilera, Pedro |
| author_facet | Fernández Ropero, Rosa María Flores Gallego, María Julia Rumí Rodríguez, Rafael Aguilera Aguilera, Pedro |
| author_sort | Fernández Ropero, Rosa María |
| collection | DSpace |
| description | Bayesian networks (BNs) have been widely applied in environmental modelling to predict the behaviour of an ecosystem under conditions of change. However, this approximation doesn’t take time into consideration. To solve this issue, an extension of BNs, the dynamic Bayesian networks (DBNs), has been developed in mathematics and computer science areas but has scarcely been applied in environmental modelling. This paper presents the application of DBN to water reservoir systems in Andalusia, Spain. The aim is to predict changes in the percent fullness of the reservoirs under the irregular rainfall patterns of Mediterranean watersheds. In comparison to static BNs, DBNs provide results that can be extrapolated to a particular time so that a climate change scenario can be studied in detail over time. Since results are expressed by density functions rather than unique values, several metrics are obtained from the results, including the probability of certain values. This allows the probability that water level in a reservoir reaches a certain level to be directly computed. |
| format | info:eu-repo/semantics/article |
| id | oai:repositorio.ual.es:10835-15029 |
| institution | Universidad de Cuenca |
| language | English |
| publishDate | 2024 |
| publisher | Wiley |
| record_format | dspace |
| spelling | oai:repositorio.ual.es:10835-150292024-01-10T08:37:07Z Applications of hybrid dynamic Bayesian networks to water reservoir management Fernández Ropero, Rosa María Flores Gallego, María Julia Rumí Rodríguez, Rafael Aguilera Aguilera, Pedro Continuous variables Time series TAN Naïve Bayes Water Reservoir Bayesian networks (BNs) have been widely applied in environmental modelling to predict the behaviour of an ecosystem under conditions of change. However, this approximation doesn’t take time into consideration. To solve this issue, an extension of BNs, the dynamic Bayesian networks (DBNs), has been developed in mathematics and computer science areas but has scarcely been applied in environmental modelling. This paper presents the application of DBN to water reservoir systems in Andalusia, Spain. The aim is to predict changes in the percent fullness of the reservoirs under the irregular rainfall patterns of Mediterranean watersheds. In comparison to static BNs, DBNs provide results that can be extrapolated to a particular time so that a climate change scenario can be studied in detail over time. Since results are expressed by density functions rather than unique values, several metrics are obtained from the results, including the probability of certain values. This allows the probability that water level in a reservoir reaches a certain level to be directly computed. 2024-01-10T08:37:06Z 2024-01-10T08:37:06Z 2017 info:eu-repo/semantics/article R.F. Ropero, M.J. Flores, R.Rumí, P. A. Aguilera. Applications of hybrid dynamic Bayesian networks to water reservoir management. Environmetrics, 2017 http://hdl.handle.net/10835/15029 en https://onlinelibrary.wiley.com/doi/full/10.1002/env.2432 Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess Wiley |
| spellingShingle | Continuous variables Time series TAN Naïve Bayes Water Reservoir Fernández Ropero, Rosa María Flores Gallego, María Julia Rumí Rodríguez, Rafael Aguilera Aguilera, Pedro Applications of hybrid dynamic Bayesian networks to water reservoir management |
| title | Applications of hybrid dynamic Bayesian networks to water reservoir management |
| title_full | Applications of hybrid dynamic Bayesian networks to water reservoir management |
| title_fullStr | Applications of hybrid dynamic Bayesian networks to water reservoir management |
| title_full_unstemmed | Applications of hybrid dynamic Bayesian networks to water reservoir management |
| title_short | Applications of hybrid dynamic Bayesian networks to water reservoir management |
| title_sort | applications of hybrid dynamic bayesian networks to water reservoir management |
| topic | Continuous variables Time series TAN Naïve Bayes Water Reservoir |
| url | http://hdl.handle.net/10835/15029 |
| work_keys_str_mv | AT fernandezroperorosamaria applicationsofhybriddynamicbayesiannetworkstowaterreservoirmanagement AT floresgallegomariajulia applicationsofhybriddynamicbayesiannetworkstowaterreservoirmanagement AT rumirodriguezrafael applicationsofhybriddynamicbayesiannetworkstowaterreservoirmanagement AT aguileraaguilerapedro applicationsofhybriddynamicbayesiannetworkstowaterreservoirmanagement |