This article deals with evolutionary artificial neural network (ANN) and aims to propose a systematic and automated way to find out a proper network architecture. To this, we adapt four metaheuristics to resolve the problem posed by the pursuit of optimum feedforward ANN architecture and introduced a new criteria to measure the ANN performance based on combination of training and generalization error. Also, it is proposed a new method for estimating the computational complexity of the ANN architecture based on the number of neurons and epochs needed to train the network. We implemented this approach in software and tested it for the problem of identification and estimation of pollution sources and for three separate benchmark data sets from UCI repository. The results show the proposed computational approach gives better performance than a human specialist, while offering many advantages over similar approaches found in the literature.
In the last decades, artificial neural network has been increasingly applied in hydrological modeling given its potential to process the complex nonlinear relationships of the associated physical-environmental variables and produce a suitable solution (for instance, a forecasting model) in a relatively short time. In this scope, this work reports the design methodology and the operational results obtained with an artificial neural network-based model developed to forecast, with 2 h in advance, the level of a river in the mountainous region of Rio de Janeiro state in Brazil. This is an area susceptible to natural disasters with recent records of floods and landslides that caused environmental and socio-economic damage of large proportions. The proposed neural network uses an innovative learning algorithm (the quasi-Newton optimization method is applied to the slopes of each hidden activation function) and, as input features, values of rainfall and river level data collected from 8 monitoring stations located on studied watershed between 2013 and 2014. The results of the neural model, with NASH index greater than 0.86, are promising making possible its operational use on an issuing flood alerts system.
Resumo. O monitoramento de desastres naturais no Brasilé responsabilidade do Centro Nacional de Monitoramento e Alertas de Desastres Naturais (Cemaden), que trabalha em colaboração com diversosórgãos e conta com uma divisão dedicada a pesquisa científica. Modelos empíricos baseados em dados utilizam técnicas estatísticas e/ou de aprendizado de máquina para, dado um banco de dados para treinamento, promover estimações frente a novos padrões de entrada. O produto neuroprevisão consiste em uma Rede Neural Artificial aplicada para prever o nível de um dado rio. Por outro lado, modelos físicos utilizam equações referentes ao fenômeno modelado, e os parâmetros de tais equações podem ser estimados com base em dados observacionais. O produto Modelagem hidrológica rápidá e baseado na equação do tempo de translado. Este trabalho promove comparações entre diferentes abordagens em fase de testes operacionais no Cemaden.Palavras-chave. Rede Neural Artificial, Neuroprevisão, Modelo Hidrológico, Modelo empírico, Modelo físico.
IntroduçãoO Brasilé um país com grande risco da ocorrência de desastres socioambientais [1]. Um dos grandes desafios das entidadesé monitoramento e alerta precoce desses eventos extremos de modo que seja possível mitigar as perdas causadas por esses fenômenos. Em virtude disso, tem se buscado a implementação de modelos e programas de computador que sejam capazes de realizar uma previsão para um dado evento natural, com boa qualidade e confiabilidade com um horizonte de previsão que permita a realização de ações que minimizem as perdas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.