Table 2 Motivation for the proposed work from the review perspective.
From: Reliable water quality prediction and parametric analysis using explainable AI models
Refs | Title | Advantages | Research gap | Quality parameters |
|---|---|---|---|---|
A biological sensor system using computer vision for water quality monitoring | \(\bullet\) Real-time analysis | \(\bullet\) Sensor Sensitivity and Selectivity | \(\bullet\) Abstract Fish Behavior | |
\(\bullet\) Cost Effectiveness | \(\bullet\) Robustness and Long term stability | \(\bullet\) Movement Velocity | ||
\(\bullet\) Versatility | \(\bullet\) Calibration | \(\bullet\) Rotation Angle Of The Fish Group | ||
\(\bullet\) Potential for Automation | \(\bullet\) Image Analysis and Algorithm Optimization | |||
Monthly water quality forecasting and uncertainty assessment via bootstrapped wavelet neural networks under missing data for Harbin, China | \(\bullet\) Accurate Water quality forecasting | \(\bullet\) Model Generalization | \(\bullet\) Ammonia Nitrogen (NH4+-N) | |
\(\bullet\) Handling Missing data | \(\bullet\) Comparison with other Models | \(\bullet\) Dissolved Oxygen | ||
\(\bullet\) Uncertainty Assessment | \(\bullet\) Data Availability and Quality | |||
\(\bullet\) Temporal Resolution | \(\bullet\) Model Optimization | |||
Groundwater quality forecasting using ML algorithms for irrigation purposes | \(\bullet\) Spatial distribution mapping | \(\bullet\) Spatial and temporal scale | \(\bullet\) Total Dissolved Solid (TDS) | |
\(\bullet\) Effective feature selection | \(\bullet\) Data availability and quality | \(\bullet\) Potential Salinity (PS) | ||
\(\bullet\) High dimensional data | \(\bullet\) Uncertainty estimation | \(\bullet\) Sodium Adsorption Ratio (SAR) | ||
\(\bullet\) Non-linearity and flexibility | \(\bullet\) Validation and comparison | \(\bullet\) Exchangeable Sodium Percentage | ||
\(\bullet\) Transparency | \(\bullet\) Magnesium Adsorption Ratio (MAR) | |||
\(\bullet\) Residual Sodium Carbonate (RSC) | ||||
Predicting nitrate concentration and its spatial distribution in groundwater resources using Support Vector Machines (SVM) model | \(\bullet\) Accurate Water quality forecasting | \(\bullet\) Model Generalization | \(\bullet\) Water Temperature | |
\(\bullet\) Handling Missing data | \(\bullet\) Comparison with other Models | \(\bullet\) Electrical Conductivity | ||
\(\bullet\) Uncertainty Assessment | \(\bullet\) Data Availability and Quality | \(\bullet\) Groundwater Depth | ||
\(\bullet\) Temporal Resolution | \(\bullet\) Model Optimization | \(\bullet\) Total Dissolved Solids | ||
\(\bullet\) Site-Specific Application | \(\bullet\) Dissolved Oxygen | |||
\(\bullet\) Ph | ||||
A novel ML-based approach for the risk assessment of nitrate groundwater contamination | \(\bullet\) Risk assessment accuracy | \(\bullet\) Dataset limitations | Groundwater Vulnerability Map :(DI<80), low (DI=80-120), moderate (DI=120-160), high (DI=160-200), and very high | |
\(\bullet\) Ability to handle complex datasets | \(\bullet\) Can exhibit temporal dynamics | |||
\(\bullet\) Spatially explicit risk mapping | \(\bullet\) Validation | |||
\(\bullet\) Transferability to different regions | \(\bullet\) Uncertainty quantification | |||
\(\bullet\) Comparative analysis | ||||
Machine Learning predictions of nitrate in groundwater used for drinking supply in the conterminous of the United States | \(\bullet\) Nationwide assessment | \(\bullet\) Data quality and availability | \(\bullet\) High Precipitation | |
\(\bullet\) Accuracy and predictive power | \(\bullet\) Incorporating temporal dynamics | \(\bullet\) Recharge | ||
\(\bullet\) Detection of the high risk areas | \(\bullet\) Transferability and regional variability | \(\bullet\) Base Flow Index | ||
\(\bullet\) Spatially explicit predictions | \(\bullet\) Uncertainty estimation | \(\bullet\) Nitrate Concentrations | ||
\(\bullet\) Comparative analysis | ||||
Ensemble modelling framework for groundwater level prediction in urban areas of India | \(\bullet\) Model training and calibration | \(\bullet\) Data quality and availability | \(\bullet\) Groundwater Levels | |
\(\bullet\) Ensemble generation | \(\bullet\) Transferability and regional variability | \(\bullet\) Rainfall, Temperature | ||
\(\bullet\) Uncertainty estimation | \(\bullet\) Validation benchmarking | \(\bullet\) NOI | ||
\(\bullet\) Enhanced pre-processing techniques | \(\bullet\) Comparative analysis | \(\bullet\) SOI | ||
\(\bullet\) NIÑ | ||||
\(\bullet\) Monthly Population Growth Rate |
