Machine Learning in Assessing the Performance of Hydrological Models
Machine learning has been employed successfully as a tool virtually in every scientific and technological field. In hydrology, machine learning models first appeared as simple feed-forward networks that were used for short-term forecasting, and have evolved into complex models that can take into acc...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Hydrology |
Subjects: | |
Online Access: | https://www.mdpi.com/2306-5338/9/1/5 |
_version_ | 1797493567642402816 |
---|---|
author | Evangelos Rozos Panayiotis Dimitriadis Vasilis Bellos |
author_facet | Evangelos Rozos Panayiotis Dimitriadis Vasilis Bellos |
author_sort | Evangelos Rozos |
collection | DOAJ |
description | Machine learning has been employed successfully as a tool virtually in every scientific and technological field. In hydrology, machine learning models first appeared as simple feed-forward networks that were used for short-term forecasting, and have evolved into complex models that can take into account even the static features of catchments, imitating the hydrological experience. Recent studies have found machine learning models to be robust and efficient, frequently outperforming the standard hydrological models (both conceptual and physically based). However, and despite some recent efforts, the results of the machine learning models require significant effort to interpret and derive inferences. Furthermore, all successful applications of machine learning in hydrology are based on networks of fairly complex topology that require significant computational power and CPU time to train. For these reasons, the value of the standard hydrological models remains indisputable. In this study, we suggest employing machine learning models not as a substitute for hydrological models, but as an independent tool to assess their performance. We argue that this approach can help to unveil the anomalies in catchment data that do not fit in the employed hydrological model structure or configuration, and to deal with them without compromising the understanding of the underlying physical processes. |
first_indexed | 2024-03-10T01:21:51Z |
format | Article |
id | doaj.art-58c9a73da0244fe6a8a72295bdc84b2c |
institution | Directory Open Access Journal |
issn | 2306-5338 |
language | English |
last_indexed | 2024-03-10T01:21:51Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Hydrology |
spelling | doaj.art-58c9a73da0244fe6a8a72295bdc84b2c2023-11-23T13:58:23ZengMDPI AGHydrology2306-53382021-12-0191510.3390/hydrology9010005Machine Learning in Assessing the Performance of Hydrological ModelsEvangelos Rozos0Panayiotis Dimitriadis1Vasilis Bellos2Institute for Environmental Research & Sustainable Development, National Observatory of Athens, 15236 Athens, GreeceDepartment of Water Resources and Environmental Engineering, School of Civil Engineering, National Technical University of Athens, 15780 Athens, GreeceDepartment of Environmental Engineering, School of Engineering, Democritus University of Thrace, 67100 Xanthi, GreeceMachine learning has been employed successfully as a tool virtually in every scientific and technological field. In hydrology, machine learning models first appeared as simple feed-forward networks that were used for short-term forecasting, and have evolved into complex models that can take into account even the static features of catchments, imitating the hydrological experience. Recent studies have found machine learning models to be robust and efficient, frequently outperforming the standard hydrological models (both conceptual and physically based). However, and despite some recent efforts, the results of the machine learning models require significant effort to interpret and derive inferences. Furthermore, all successful applications of machine learning in hydrology are based on networks of fairly complex topology that require significant computational power and CPU time to train. For these reasons, the value of the standard hydrological models remains indisputable. In this study, we suggest employing machine learning models not as a substitute for hydrological models, but as an independent tool to assess their performance. We argue that this approach can help to unveil the anomalies in catchment data that do not fit in the employed hydrological model structure or configuration, and to deal with them without compromising the understanding of the underlying physical processes.https://www.mdpi.com/2306-5338/9/1/5machine learninghydrological modellingLSTMrecurrent neural networksresidual error modelling |
spellingShingle | Evangelos Rozos Panayiotis Dimitriadis Vasilis Bellos Machine Learning in Assessing the Performance of Hydrological Models Hydrology machine learning hydrological modelling LSTM recurrent neural networks residual error modelling |
title | Machine Learning in Assessing the Performance of Hydrological Models |
title_full | Machine Learning in Assessing the Performance of Hydrological Models |
title_fullStr | Machine Learning in Assessing the Performance of Hydrological Models |
title_full_unstemmed | Machine Learning in Assessing the Performance of Hydrological Models |
title_short | Machine Learning in Assessing the Performance of Hydrological Models |
title_sort | machine learning in assessing the performance of hydrological models |
topic | machine learning hydrological modelling LSTM recurrent neural networks residual error modelling |
url | https://www.mdpi.com/2306-5338/9/1/5 |
work_keys_str_mv | AT evangelosrozos machinelearninginassessingtheperformanceofhydrologicalmodels AT panayiotisdimitriadis machinelearninginassessingtheperformanceofhydrologicalmodels AT vasilisbellos machinelearninginassessingtheperformanceofhydrologicalmodels |