A review of artificial intelligence in water purification and wastewater treatment: Recent advancements
Abstract
Artificial intelligence (AI) is an emerging powerful novel technology that can model real-time problems involving numerous intricacies. The modeling capabilities of AI techniques are quite advantageous in water purification and wastewater treatment processes because the automation of such facilities resulted in easy and low cost operations; in addition to the significant reduction in the occurrence of human errors. AI technologies involve multi-linear or non-linear relationships and process dynamics that are usually impractical to model by conventional methodologies. This review presents a compendious synopsis of recent advancements and discoveries in various AI technologies applied to source water quality determination, coagulation/flocculation, disinfection, membrane filtration, desalination, modeling wastewater treatment plants, prediction of membrane fouling, removal of heavy metals, and monitoring of biological oxygen demand (BOD) and chemical oxygen demand (COD) levels. The analysis of the performance of various AI technologies in this review proves the successful implementation of these technologies in water treatment related applications. It also highlights the limitations that hinder their implementations in real-world water treatment systems.
- Publication:
-
Journal of Water Process Engineering
- Pub Date:
- October 2022
- DOI:
- 10.1016/j.jwpe.2022.102974
- Bibcode:
- 2022JWPE...4902974S
- Keywords:
-
- ANNs;
- Artificial neural networks;
- ARMA;
- Auto-regressive moving average;
- ANFIS;
- Adaptive neuro fuzzy inference system;
- BOD;
- Biological oxygen demand;
- BPNN;
- Back propagation neural network;
- BP-ANN;
- Backpropagation ANN;
- COD;
- Chemical oxygen demand;
- CFFNN;
- Cascade feed-forward NN;
- CNN;
- Convolutional NN;
- DWTPs;
- Drinking water treatment plants;
- DL;
- Deep learning;
- DENFIS;
- Dynamic evolving neural-fuzzy inference system;
- DBPs;
- Disinfection by-products;
- DRL;
- Deep reinforcement learning;
- ELM;
- Extreme learning machines;
- ENN;
- Elman NN;
- EDSS;
- Environmental decision support systems;
- FL;
- Fuzzy logic;
- GA;
- Genetic algorithmv;
- GRNN;
- General regression neural network;
- GEP;
- Gene expression programming;
- GOR;
- Gained output ratio;
- GP;
- Grid positioning;
- HANN;
- Hybrid ANN;
- IoT;
- internet of things;
- K-FBL;
- Knowledge-based fuzzy broad learning;
- LSTM;
- Long short-term memory;
- MT;
- Model trees;
- MLR;
- Multilinear regression;
- MSE;
- Mean squared error;
- MBR;
- Membrane bioreactor;
- MARS;
- Multi-variate adaptive regression splines;
- MLP;
- Multilayer perceptron;
- MAPE;
- Mean absolute percentage error;
- NNE;
- neural network ensemble;
- PSO;
- Particle swarm optimization;
- RBF;
- Radial basis function;
- RSM;
- Response surface methodology;
- RMSE;
- Root mean squared error;
- R2;
- Coefficient of determination;
- RBFNN;
- Radial basis function NN;
- SVM;
- Support vector machine;
- SAE;
- Simple average ensemble;
- TMP;
- Trans membrane pressure;
- WWTPs;
- Wastewater treatment plants;
- WAE;
- Weighted average ensemble;
- XGBoost;
- Extreme gradient boosting;
- Water purification;
- Artificial intelligence;
- Wastewater treatment;
- Machine learning