Neural network modeling and geochemical water analyses to understand and forecast karst and non-karst part of flash floods (case study on the <i>Lez</i> river, Southern France)
Flash floods forecasting in the Mediterranean area is a major economic and societal issue. Specifically, considering karst basins, heterogeneous structure and nonlinear behaviour make the flash flood forecasting very difficult. In this context, this work proposes a methodology to estimate the co...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2015-06-01
|
| Series: | Proceedings of the International Association of Hydrological Sciences |
| Online Access: | https://www.proc-iahs.net/369/43/2015/piahs-369-43-2015.pdf |
| _version_ | 1818272073294807040 |
|---|---|
| author | T. Darras T. Darras F. Raynaud V. Borrell Estupina L. Kong-A-Siou S. Van-Exter B. Vayssade A. Johannet S. Pistre |
| author_facet | T. Darras T. Darras F. Raynaud V. Borrell Estupina L. Kong-A-Siou S. Van-Exter B. Vayssade A. Johannet S. Pistre |
| author_sort | T. Darras |
| collection | DOAJ |
| description | Flash floods forecasting in the Mediterranean area is a major economic and
societal issue. Specifically, considering karst basins, heterogeneous
structure and nonlinear behaviour make the flash flood forecasting very
difficult. In this context, this work proposes a methodology to estimate the
contribution from karst and non-karst components using toolbox including
neural networks and various hydrological methods. The chosen case study is
the flash flooding of the <i>Lez</i> river, known for his complex behaviour and huge
stakes, at the gauge station of <i>Lavallette</i>, upstream of <i>Montpellier</i> (400 000 inhabitants). After
application of the proposed methodology, discharge at the station of
<i>Lavallette</i> is spited between hydrographs of karst flood and surface runoff,
for the two events of 2014. Generalizing the method to future events will allow
designing forecasting models specifically for karst and surface flood
increasing by this way the reliability of the forecasts. |
| first_indexed | 2024-12-12T21:36:16Z |
| format | Article |
| id | doaj.art-fc74904d55d3441aa54bf2de72cc08ac |
| institution | Directory Open Access Journal |
| issn | 2199-8981 2199-899X |
| language | English |
| last_indexed | 2024-12-12T21:36:16Z |
| publishDate | 2015-06-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Proceedings of the International Association of Hydrological Sciences |
| spelling | doaj.art-fc74904d55d3441aa54bf2de72cc08ac2022-12-22T00:11:11ZengCopernicus PublicationsProceedings of the International Association of Hydrological Sciences2199-89812199-899X2015-06-01369434810.5194/piahs-369-43-2015Neural network modeling and geochemical water analyses to understand and forecast karst and non-karst part of flash floods (case study on the <i>Lez</i> river, Southern France)T. Darras0T. Darras1F. Raynaud2V. Borrell Estupina3L. Kong-A-Siou4S. Van-Exter5B. Vayssade6A. Johannet7S. Pistre8École des mines d'Alès, 6 avenue de Clavières, 30319 Alès CEDEX, FranceHydrosciences Montpellier, Université de Montpelier II, 2 Place Eugène Bataillon, 34095 Montpellier CEDEX 5, FranceHydrosciences Montpellier, Université de Montpelier II, 2 Place Eugène Bataillon, 34095 Montpellier CEDEX 5, FranceHydrosciences Montpellier, Université de Montpelier II, 2 Place Eugène Bataillon, 34095 Montpellier CEDEX 5, FranceMAYANE, 173 chemin de Fescau, 34980 Montferrier-sur-Lez, FranceHydrosciences Montpellier, CNRS, Montpellier, 2 Place Eugène Bataillon, 34095 Montpellier CEDEX 5, FranceÉcole des mines d'Alès, 6 avenue de Clavières, 30319 Alès CEDEX, FranceÉcole des mines d'Alès, 6 avenue de Clavières, 30319 Alès CEDEX, FranceHydrosciences Montpellier, Université de Montpelier II, 2 Place Eugène Bataillon, 34095 Montpellier CEDEX 5, FranceFlash floods forecasting in the Mediterranean area is a major economic and societal issue. Specifically, considering karst basins, heterogeneous structure and nonlinear behaviour make the flash flood forecasting very difficult. In this context, this work proposes a methodology to estimate the contribution from karst and non-karst components using toolbox including neural networks and various hydrological methods. The chosen case study is the flash flooding of the <i>Lez</i> river, known for his complex behaviour and huge stakes, at the gauge station of <i>Lavallette</i>, upstream of <i>Montpellier</i> (400 000 inhabitants). After application of the proposed methodology, discharge at the station of <i>Lavallette</i> is spited between hydrographs of karst flood and surface runoff, for the two events of 2014. Generalizing the method to future events will allow designing forecasting models specifically for karst and surface flood increasing by this way the reliability of the forecasts.https://www.proc-iahs.net/369/43/2015/piahs-369-43-2015.pdf |
| spellingShingle | T. Darras T. Darras F. Raynaud V. Borrell Estupina L. Kong-A-Siou S. Van-Exter B. Vayssade A. Johannet S. Pistre Neural network modeling and geochemical water analyses to understand and forecast karst and non-karst part of flash floods (case study on the <i>Lez</i> river, Southern France) Proceedings of the International Association of Hydrological Sciences |
| title | Neural network modeling and geochemical water analyses to understand and forecast karst and non-karst part of flash floods (case study on the <i>Lez</i> river, Southern France) |
| title_full | Neural network modeling and geochemical water analyses to understand and forecast karst and non-karst part of flash floods (case study on the <i>Lez</i> river, Southern France) |
| title_fullStr | Neural network modeling and geochemical water analyses to understand and forecast karst and non-karst part of flash floods (case study on the <i>Lez</i> river, Southern France) |
| title_full_unstemmed | Neural network modeling and geochemical water analyses to understand and forecast karst and non-karst part of flash floods (case study on the <i>Lez</i> river, Southern France) |
| title_short | Neural network modeling and geochemical water analyses to understand and forecast karst and non-karst part of flash floods (case study on the <i>Lez</i> river, Southern France) |
| title_sort | neural network modeling and geochemical water analyses to understand and forecast karst and non karst part of flash floods case study on the i lez i river southern france |
| url | https://www.proc-iahs.net/369/43/2015/piahs-369-43-2015.pdf |
| work_keys_str_mv | AT tdarras neuralnetworkmodelingandgeochemicalwateranalysestounderstandandforecastkarstandnonkarstpartofflashfloodscasestudyontheileziriversouthernfrance AT tdarras neuralnetworkmodelingandgeochemicalwateranalysestounderstandandforecastkarstandnonkarstpartofflashfloodscasestudyontheileziriversouthernfrance AT fraynaud neuralnetworkmodelingandgeochemicalwateranalysestounderstandandforecastkarstandnonkarstpartofflashfloodscasestudyontheileziriversouthernfrance AT vborrellestupina neuralnetworkmodelingandgeochemicalwateranalysestounderstandandforecastkarstandnonkarstpartofflashfloodscasestudyontheileziriversouthernfrance AT lkongasiou neuralnetworkmodelingandgeochemicalwateranalysestounderstandandforecastkarstandnonkarstpartofflashfloodscasestudyontheileziriversouthernfrance AT svanexter neuralnetworkmodelingandgeochemicalwateranalysestounderstandandforecastkarstandnonkarstpartofflashfloodscasestudyontheileziriversouthernfrance AT bvayssade neuralnetworkmodelingandgeochemicalwateranalysestounderstandandforecastkarstandnonkarstpartofflashfloodscasestudyontheileziriversouthernfrance AT ajohannet neuralnetworkmodelingandgeochemicalwateranalysestounderstandandforecastkarstandnonkarstpartofflashfloodscasestudyontheileziriversouthernfrance AT spistre neuralnetworkmodelingandgeochemicalwateranalysestounderstandandforecastkarstandnonkarstpartofflashfloodscasestudyontheileziriversouthernfrance |