Optimized Design of Neural Networks for a River Water Level Prediction System
| Autor: | Antonio Madueño Luna, Pedro M. Ferreira, António E. Ruano, Miriam López Lineros |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Mean squared error
Computer science Topology (electrical circuits) TP1-1185 computer.software_genre Biochemistry River water Article river stage data Analytical Chemistry Rivers Water Quality Genetic algorithm Electrical and Electronic Engineering Instrumentation Multi-Objective Genetic Algorithm River stage data Artificial neural networks Artificial neural network Chemical technology Water Partition (database) Atomic and Molecular Physics and Optics Water level Multi-objective genetic algorithm Data mining Neural Networks Computer computer artificial neural networks Predictive modelling |
| Zdroj: | Sensors (Basel, Switzerland) Sensors, Vol 21, Iss 6504, p 6504 (2021) Sensors Volume 21 Issue 19 Repositório Científico de Acesso Aberto de Portugal Repositório Científico de Acesso Aberto de Portugal (RCAAP) instacron:RCAAP |
| ISSN: | 1424-8220 |
| Popis: | In this paper, a Multi-Objective Genetic Algorithm (MOGA) framework for the design of Artificial Neural Network (ANN) models is used to design 1-step-ahead prediction models of river water levels. The design procedure is a near-automatic method that, given the data at hand, can partition it into datasets and is able to determine a near-optimal model with the right topology and inputs, offering a good performance on unseen data, i.e., data not used for model design. An example using more than 11 years of water level data (593,178 samples) of the Carrión river collected at Villoldo gauge station shows that the MOGA framework can obtain low-complex models with excellent performance on unseen data, achieving an RMSE of 2.5 × 10−3 , which compares favorably with results obtained by alternative design. info:eu-repo/semantics/publishedVersion |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|