A Machine-Learning Approach for Prediction of Water Contamination Using Latitude, Longitude, and Elevation

Providing predictive models for quality parameters of groundwater resources in arid areas of central Iran: A case study of kashan plain

Groundwater pollution can occur due to both anthropogenic and natural causes, leading to a decline in water quality and posing a threat to human health and the environment. The pollution of ground water resources with chemical pollutants is often considered. To manage water resources sustainably, ensuring their quality and quantity is crucial. Yet, testing groundwater can be expensive and time-consuming. So, using modeling to predict the chemical parameters of groundwater resources is considered to be an efficient and economical method. In this study, we examined three models to predict groundwater quality in dry regions by using R programming language. The random forest (RF) outperformed the other models in developing predictive models for water quality. Also, the multiple linear regression (MLR) model demonstrated strong performance, particularly in predicting total hardness (TH) in Aran Va Bidgol groundwater resources. The decision tree (DT) model did well but had lower performance than the RF model in predicting quality parameters. This approach can be efficacious in the field of effective management and protection of groundwater resources and enables the assessment of risks related to water resources.

A pruned feed-forward neural network (pruned-FNN) approach to measure air pollution exposure

Environmental epidemiology studies require accurate estimations of exposure intensities to air pollution. The process from air pollutant emission to individual exposure is however complex and nonlinear, which poses significant modeling challenges. This study aims to develop an exposure assessment model that can strike a balance between accuracy, complexity, and usability. In this regard, neural networks offer one possible approach. This study employed a custom-designed pruned feed-forward neural network (pruned-FNN) approach to calculate the air pollution exposure index based on emission time and rates, terrain factors, meteorological conditions, and proximity measurements. The model's performance was evaluated by cross-validating the estimated exposure indexes with ground-based monitoring records. The pruned FNN can predict pollution exposure indexes (PEIs) that are highly and stably correlated with the monitored air pollutant concentrations (Spearman's rank correlation coefficients for tenfold cross-validation (mean ± standard deviation: 0.906 ± 0.028) and for random cross-validation (0.913 ± 0.024)). The predicted values are also close to the ground truth in most cases (95.5% of the predicted PEIs have relative errors smaller than 10%) when the training datasets are sufficiently large and well-covered. The pruned-FNN method can make accurate exposure estimations using a flexible number of variables and less extensive data in a less money/time-consuming manner. Compared to other exposure assessment models, the pruned FNN is an appropriate and effective approach for exposure assessment that covers a large geographic area over a long period of time.