Artificial intelligence for surface water quality monitoring and assessment: a systematic literature analysis
- PDF / 1,571,271 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 35 Downloads / 170 Views
REVIEW ARTICLE
Artificial intelligence for surface water quality monitoring and assessment: a systematic literature analysis Joshua O. Ighalo1,2 · Adewale George Adeniyi1 · Gonçalo Marques3 Received: 8 June 2020 / Accepted: 3 November 2020 © Springer Nature Switzerland AG 2020
Abstract The goal of this paper was to conduct a systematic literature analysis on the application of different types of artificial intelligence models in surface water quality monitoring. The analysis focused on the methods used, the location of the experiments, the input parameters, and the output metrics applied to categorise the results presented. Furthermore, the main contribution of this paper is to synthesise the existing body of knowledge in the state of the art (the last decade) and identified common threads and gaps that would open up new challenging, exciting and significant research directions. From the study, it was observed that Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Networks (ANN) are the most utilised artificial intelligence models for water quality monitoring and assessment in the last decade. Most of the studies using Neural Networks in surface water quality monitoring and assessment are originated in Iran and south-east Asia. ANFIS, Wavelet-ANN (W-ANN) and Wavelet-ANFIS (W-ANFIS) were most accurate for the prediction of surface water quality. There was no clear relationship between data size and R2 value (at the testing stage). Biochemical oxygen demand (BOD) was the most investigated parameter in surface water quality monitoring and assessment. An appraisal of recent literature was also presented and knowledge gaps and future perspective in the research area were proposed. Keywords AI · ANFIS · ANN · River · Water quality · WQA Abbreviations AI Artificial Intelligence ANFIS Adaptive Neuro-Fuzzy Inference System ANN Artificial Neural Network ARIMA Linear Auto-Regressive Integrated Moving Average BOD Biochemical Oxygen Demand BPNN Back Propagation Neural Network CFS Cascaded Fuzzy Inference System COD Chemical Oxygen Demand DO Dissolved Oxygen EC Electrical Conductivity ELM Extreme Learning Machine ENN Elman Neural Network * Gonçalo Marques [email protected] 1
Department of Chemical Engineering, University of Ilorin, P. M. B. 1515, Ilorin, Nigeria
2
Department of Chemical Engineering, Nnamdi Azikiwe University, P. M. B. 5025, Awka, Nigeria
3
Polytechnic of Coimbra, ESTGOH, Rua General Santos Costa, 3400‑124 Oliveira Do Hospital, Portugal
FIS Fuzzy Inference System MLP Multi-Layer Perceptron Neural Network NARX Nonlinear Autoregressive (with exogenous input) Network NN-CS Neural Network trained by Cuckoo Search Algorithm NN-GA Neural Network trained by Genetic Algorithm NN-PSO Neural Network trained by Particle Swarm Algorithm PI Permanganate Index R2 Coefficient of Determination RBF Radial Basis Function Neural Network RMSE Root Mean Square Error SAR Sodium Absorption Ratio SVM Support Vector Machine TA Total alkalinity TH Total Hardne
Data Loading...
