Performance evaluation of artificial intelligence paradigms—artificial neural networks, fuzzy logic, and adaptive neuro-fuzzy inference system for flood prediction

• Published in: Environmental science and pollution research international Vol. 28; no. 20; pp. 25265 - 25282
• Main Authors: Tabbussum, Ruhhee, Dar, Abdul Qayoom
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.05.2021; Springer Nature B.V
• Subjects: Accuracy; Adaptive systems; Algorithms; Aquatic Pollution; Artificial intelligence; Artificial neural networks; Atmospheric Protection/Air Quality Control/Air Pollution; Back propagation; Back propagation networks; Bayesian analysis; Bayesian theory; Computer simulation; Conjugates; Earth and Environmental Science; Economic impact; Ecotoxicology; Environment; Environmental Chemistry; Environmental Health; Environmental science; Flood control; Flood forecasting; Flood predictions; Floods; Fuzzy logic; Fuzzy systems; Inference; Mathematical models; Mean square errors; Neural networks; Performance evaluation; Performance measurement; prediction; Prediction models; prognosis; Regularization; Research Article; Root-mean-square errors; socioeconomics; Statistical analysis; Stream discharge; Stream flow; Waste Water Technology; Water Management; Water Pollution Control; Gaussian membership function; Takagi-Sugeno fuzzy inference system; Levenberg Marquardt neural network; Flood forecasting; Subtractive clustering; Adaptive neuro-fuzzy inference system
• ISSN: 0944-1344; 1614-7499; 1614-7499
• DOI: 10.1007/s11356-021-12410-1

Flood prediction has gained prominence world over due to the calamitous socio-economic impacts this hazard has and the anticipated increase of its incidence in the near future. Artificial intelligence (AI) models have contributed significantly over the last few decades by providing improved accuracy and economical solutions to simulate physical flood processes. This study explores the potential of the AI computing paradigm to model the stream flow. Artificial neural network (ANN), fuzzy logic, and adaptive neuro-fuzzy inference system (ANFIS) algorithms are used to develop nine different flood prediction models using all the available training algorithms. The performance of the developed models is evaluated using multiple statistical performance evaluators. The predictability and robustness of the models are tested through the simulation of a major flood event in the study area. A total of 12 inputs were used in the development of the models. Five training algorithms were used to develop the ANN models (Bayesian regularization, Levenberg Marquardt, conjugate gradient, scaled conjugate gradient, and resilient backpropagation), two fuzzy inference systems to develop fuzzy models (Mamdani and Sugeno), and two training algorithms to develop the ANFIS models (hybrid and backpropagation). The ANFIS model developed using hybrid training algorithm gave the best performance metrics with Nash-Sutcliffe Model Efficiency (NSE) of 0.968, coefficient of correlation ( R 2 ) of 97.066%, mean square error (MSE) of 0.00034, root mean square error (RMSE) of 0.018, mean absolute error (MAE) of 0.0073, and combined accuracy (CA) of 0.018, implying the potential of using the developed models for flood forecasting. The significance of this research lies in the fact that a combination of multiple inputs and AI algorithms has been used to develop the flood models. In summary, this research revealed the potential of AI algorithm-based models in predicting floods and also developed some useful techniques that can be used by the Flood Control Departments of various states/regions/countries for flood prognosis.