Toukourou, Mohamed Samir (2009) Artificial intelligence application on the forecasting of flash floods. PhD thesis Informatique Temps réel Robotique et Automatique, CMGD-EMA et Électronique , ENSMP p.176.
Full text available as:
|
|
Abstract
The need for accurate predictions of flash floods has been highlighted by the recent occurrences of catastrophic floods. The scope of this thesis is therefore to apply machine learning to forecast cévenol flash floods, which have caused casualties and huge damage in France over the last 20 years. The work was performed in the framework of the Bassin Versant Numérique Expérimental Gardon project, initiated by the French Ministry in charge of Sustainable Development. In this context, this work addresses the capability of machine learning to provide flood forecasts in the absence of rainfall forecasts
The first part of this manuscript describes the family of functions chosen in the present study - neural networks-, their ability to forecast the behavior of non-linear dynamic processes, their fundamental properties (universal approximation and parsimony), as well as the conventional methods used to prevent overfitting.
The second part of this work presents the river under investigation, the Gardon d’Anduze, as well as related hydrological studies.
The third part presents the application of two traditional regularization methods: early stopping and weight decay. In order to allow the prediction of very intense floods, an original variable selection method is proposed: “partial cross validation”. After careful variable and model selection, the ability of models, obtained by either regularization method, to predict the most dramatic event of the database (September 2002) is assessed, thereby allowing an early warning of the populations.
Thus, this work demonstrates that, in contrast to statements found in many publications on neural networks applied to flash-flood forecasting, the prediction of an event that is more intense than the events present in the database is feasible, provided a rigorous methodology is used. For this reason, this work opens the way to making current models more adaptive, and to applying the method to ungauged basins.
| Item Type: | PhD Thesis (PhD) |
|---|---|
| PhD Supervisor: | Dreyfus, Gérard |
| Date: | 10 December 2009 |
| Board of examiners: | Dartus, Denis and Touzet, Claude and Dreyfus, Gérard and Johannet, Anne and Saulnier, Georges Marie and Vimont, Yannick and Janet, Bruno |
| Ecole Doctorale: | ED 431 INFORMATION, COMMUNICATION, MODELISATION ET SIMULATION |
| Discipline: | Informatique Temps réel Robotique et Automatique |
| Collection (Fonds): | ESPCI ParisTech Mines ParisTech (ENSMP) |
| Institution: | ENSMP |
| Department: | CMGD-EMA et Électronique |
| Subjects: | 2. Information and Communication Sciences and Technologies 8. Earth Sciences and Environmental Engineering |
| Uncontrolled Keywords: | Machine learning, Flash floods, Forecasting, Crues subites, Neural networks, Réseaux de neurones, Regularization, Régularisation |
| ID Code: | 5626 |
| Deposited By: | Gerard DREYFUS |
| Deposited On: | 16 December 2009 |
Repository Staff Only: edit this item