Prediction of sediment heavy metal at the Australian Bays using newly developed hybrid artificial intelligence models

Laboratory measurement and machine learning-based analysis of driving factors for brake wear particle emissions from light-duty electric vehicles and heavy-duty vehicles

This study investigates brake wear particle (BWP) emissions from light-duty electric vehicles (EVs) and heavy-duty vehicles (HDVs) using a self-developed whole-vehicle testing system and a modified brake dynamometer. The results show that regenerative braking significantly reduces emissions: weak and strong regenerative braking modes reduce brake wear PM2.5 by 75 % and 87 %, and brake wear PM10 by 90 % and 95 %, respectively. HDVs with drum brakes produce lower emissions and higher PM2.5/PM10 ratios than those with disc brakes. A machine learning model (XGBoost) was developed to analyze the relationship between BWP emissions and factors (11 for light-duty EVs and 8 for HDVs, based on kinematic, vehicle, and braking parameters). SHapley Additive exPlanations (SHAP) were used for model interpretation. For light-duty EVs, reducing high kinetic energy losses (Ike > 6500 J) and initial speeds (V > 45 km/h) braking events significantly lowers emissions. Additionally, the emission reduction effect of regenerative braking intensity (BI) stabilizes when BI exceeds 900 J. For HDVs, controlling braking temperature (Avg.T < 200°C) and initial speed (V < 50 km/h) effectively reduces emissions. Our findings provide new insights into the emission characteristics and control strategies for BWPs. SYNOPSIS: The construction and interpretation of a machine learning based model of brake wear emissions provides new insights into the refined assessment and control of non-exhaust emissions.

Revealing the synergistic spatial effects in soil heavy metal pollution with explainable machine learning models

The identification of factors that affect changes in the heavy metal content of soil is the basis for reducing or preventing soil heavy metal pollution. In this research, 16 environmental factors were selected, and the influences of soil heavy metal spatial distribution factors and the synergy amongst space factors were evaluated using a geographic detector (GD) and the extreme gradient boosting (XGBoost)-Shapley additive explanations (SHAP) model. Three heavy metal elements, namely, Cd, Cu and Pb, in the study region were examined. The following results were obtained. (1) XGBoost demonstrated high accuracy in predicting the spatial distributions of soil heavy metals, with each heavy metal having an R2 value of over 0.6. (2) Geological type map (Geomap) and enterprise density considerably affected the concentrations of Cd, Cu and Pb in soil in the GD and XGBoost-SHAP models. In addition, cross-detection revealed strong explanatory power when natural and human factors were combined. (3) Under the same geological background, the different trends of gross domestic product effects on heavy metals indicated that pollution control measures were effective in economically developed areas, and the economy and the environment could be balanced. Meanwhile, the interaction between the normalised difference vegetation index and enterprise density showed that vegetation could alleviate heavy metal pollution in the region. This study supports strategic decision-making, serving as a reference for the global management of soil heavy metal contamination, sustainable ecological development and assurance of people's health and well-being.

Machine learning models with innovative outlier detection techniques for predicting heavy metal contamination in soils

Machine learning (ML) models for accurately predicting heavy metals with inconsistent outputs have improved owing to dataset outliers, which influence model reliability and accuracy. A comprehensive technique that combines machine learning and advanced statistical methods was applied to assess data outlier's effects on ML models. Ten ML models with three outlier detection methods predicted Cr, Ni, Cd, and Pb in Narayanganj soils. XGBoost with density-based spatial clustering of applications with noise (DBSCAN) improved model efficacy (R2). The R2 of Cr, Ni, Cd, and Pb was considerably enhanced by 11.11 %, 6.33 %, 14.47 %, and 5.68 %, respectively, indicating that outliers affected the model's HM prediction. Soil factors affected Cr (80 %), Ni (72.61 %), Cd (53.35 %), and Pb (63.47 %) concentrations based on feature importance. Contamination factor prediction showed considerable contamination for Cr, Ni, and Cd. LISA revealed Cd (55.4 %), Cr (49.3 %), and Pb (47.3 %) as the significant pollutant (p < 0.05). Moran's I index values for Cr, Ni, Cd, and Pb were 0.65, 0.58, 0.60, and 0.66, respectively, indicating strong positive spatial autocorrelation and clusters with similar contamination. Finally, this work successfully assessed the influence of data outliers on the ML model for soil HM contamination prediction, identifying crucial regions that require rapid conservation measures.

Leveraging machine learning for sustainable cultivation of Zn-enriched crops in Cd-contaminated karst regions

Karst soils often exhibit elevated zinc (Zn) levels, providing an opportunity to cultivate Zn-enriched crops. (meanwhile) However, these soils also frequently contain high background levels of toxic metals, particularly cadmium (Cd), posing potential health risks. Understanding the bioaccumulation of Cd and Zn and the related drivers in a high geochemical background area can provide important insights for the safe development of Zn-enriched crops. Traditional models often struggle to accurately predict metal levels in crop systems grown on soils with high geochemical background. This study employed machine learning models, including Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost), to explore effective strategies for sustainable cultivation of Zn-enriched crops in karst regions, focusing on bioaccumulation factors (BAF). A total of 10,986 topsoil samples and 181 paired rhizosphere soil-crop samples, including early rice, late rice, and maize, were collected from a karst region in Guangxi. The SVM and XGBoost models demonstrated superior performance, achieving R2 values of 0.84 and 0.60 for estimating the BAFs of Zn and Cd, respectively. Key determinants of the BAFs were identified, including soil iron and manganese contents, pH level, and the interaction between Zn and Cd. By integrating these soil properties with machine learning, a framework for the safe cultivation of Zn-enriched crops was developed. This research contributes to the development of strategies for mitigating Zn deficiency in crops grown on Cd-contaminated soils.

Enhancing local-scale groundwater quality predictions using advanced machine learning approaches

Assessing groundwater quality typically involves labor-intensive, time-consuming, and costly laboratory tests, making real-time monitoring impractical, especially at the local level. Groundwater quality projections at the local scale using broad spatial datasets have been inaccurate due to variations in hydrogeology, human activities, industrial operations, groundwater extraction, and waste disposal. This study aims to identify the most dependable and resilient machine learning algorithms for forecasting groundwater quality at nearby monitoring locations by utilizing simple water quality metrics that can be quickly assessed without extensive sampling and laboratory testing. The Entropy-weighted Water Quality Index (EWQI) was calculated using a large spatial and temporal dataset (2014-2021) of 977 wells with parameters including pH, total hardness (TH), calcium (Ca2⁺), magnesium (Mg2⁺), sodium (Na⁺), potassium (K⁺), sulfate (SO₄2⁻), chloride (Cl⁻), nitrate (NO₃⁻), total dissolved solids (TDS), and fluoride (F⁻). Further, similar parameters were also observed in 33 open wells at the three local monitoring sites from December 2022 to March 2023. The EWQI was predicted using a Random Forest (RF), eXtreme Gradient Boosting (XGB), and Deep Neural Network (DNN). The pH, TH, and TDS were used as input variables for EWQI predictions, as they can be easily measured using handheld probes or multi-parameters. The model performance was evaluated using R2, MAE, and RMSE. During the training stage, all three models predicted the EWQI with an R2 greater than 90%, with minimal errors when pH, TH, and TDS were input variables. To validate the models at a local scale, the EWQI was predicted at the village level (e.g., Antoli, Balapura, and Lapodiaya) using pH, TH, and TDS as input variables. The machine learning models were able to predict the EWQI very closely to the actual EWQI, with an R2 greater than 90%. It is also evident that the models could predict the EWQI using basic parameters that are easily measured, providing an overall idea of the water quality for a small area. Hence, these machine learning models could be useful for accurately representing groundwater quality, thereby avoiding the use of time-consuming and costly laboratory techniques.

Predicting bioavailability of potentially toxic elements (PTEs) in sediment using various machine learning (ML) models: A case study in Mahabad Dam and River-Iran

Considering the significant impact of potentially toxic elements (PTEs) on the ecosystem and human health, this paper, investigated the contamination level of four PTEs (Zn, Cu, Mo and Pb) and their mobility in sediments of Mahabad dam and river. Choosing the most effective machine learning algorithms is very important in accurately predicting bioavailability of PTEs. Therefore, four machine learning (ML) models including decision tree regression (DTR), random forest regression (RFR), multi-layer perceptron regression (MLPR) and support vector regression (SVR), were used and compared for estimating the selected PTEs bioavailability. For these models, 9 variables (total concentration, pH, EC, OM and five chemical forms F1 to F5 obtained by sequential extraction) in 100 sediment samples were considered. The results showed that contamination level decreases from Zn and Cu to Pb and Mo, but the order of the mobility coefficient of the elements in the sediment follows the trend of zinc > copper > molybdenum > lead, and variation coefficient indicated more variability of spatial distribution for Zn and Cu. Among the four tested models, DTR and RFR performed the best for predicting PTEs bioavailability variations (with roc_auc>0.9, R2 > 0.8 and MSE>0.5), followed by MLPR and SVR. Furthermore, the relevance of the factors controlling the metals availability, evaluated using the RFR-based feature importance method and Pearson correlation, revealed that the most important physicochemical property for Zn, Cu and Mo bioavailability was pH, whereas for Pb, EC was the determinant factor. In the case of chemical speciation, F5 had an inverse correlation with the target, while F1 and F2 had a direct correlation. These fractions contributed significantly to the prediction results. This study represents the potential successful application of ML to PTEs risk control in sediments and early warning for the surrounding water PTEs contamination.

A new attention-based CNN_GRU model for spatial-temporal PM2.5 prediction

Accurately predicting the spatial-temporal distribution of PM2.5 is challenging due to missing data and selecting an appropriate modeling method. Effective imputation of missing data must consider the relationships between variables while preserving their inherent variability and uncertainty. In this study, we employed machine learning techniques to impute missing data by analyzing the relationships between meteorological variables and other pollutants. Subsequently, we introduced an innovative spatiotemporal hybrid model, AC_GRU, which integrates a one-dimensional convolutional neural network (CNN), GRU, and an attention-based network to predict PM2.5 concentrations in urban areas. The AC_GRU model utilizes meteorological variables, PM2.5 concentrations from nearby air quality monitoring stations, and concentrations of other pollutants as inputs. This approach allows the model to learn spatiotemporal correlations within the time-series data, enhancing the accuracy of PM2.5 predictions. Additionally, the attention mechanism improves prediction accuracy by automatically weighting the past input variables based on their importance for future PM2.5 predictions. The experimental results demonstrate that our AC_GRU model outperforms state-of-the-art methods, making it a valuable tool for urban air quality management and public health protection.

The application of machine learning methods for prediction of heavy metal by activated carbons, biochars, and carbon nanotubes

Carbonaceous materials are commonly used as adsorbents for heavy metals. The determination of the adsorption capacity needs time and energy, and the key factors affecting the adsorption capacity have not been determined. Therefore, a new and efficient method is needed to predict the adsorption capacity and explore the decisive factors in the adsorption process. In this study, three tree-based machine learning models (i.e., random forest, gradient boosting decision tree, and extreme gradient boosting) were developed to predict the adsorption capacity of eight heavy metals (i.e., As, Cd, Cr, Cu, Hg, Ni, Pb, and Zn) on activated carbons, biochars, and carbon nanotubes using 3674 data points extracted from 151 journal articles. After a comprehensive comparison, the gradient boosting decision tree had the best performance for a combined model based on all data (R2 = 0.9707, RMSE = 0.1420). Moreover, independent models were developed for three datasets classified by the adsorbent and eight datasets classified by the heavy metals. In addition, a graphical user interface was built to predict the adsorption capacity of heavy metals. This study provides a novel strategy and convenient tool for the removal of heavy metals and can help to improve the removal efficiency of heavy metals to build a healthier world.

Prediction of weighted arithmetic water quality index for urban water quality using ensemble machine learning model

Urban water quality index (WQI) is an important factor for assessment quality of groundwater in the urban and rural area. In this research, the Weighted Arithmetic Water Quality Index (WA-WQI) was estimated for understanding the groundwater quality. Four machine learning (ML) models were developed including artificial neural network (ANN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XG-Boost) in addition to multiple linear regression (MLR) for WA-WQI prediction at the Ujjain city of Madhya Pradesh in India. Groundwater quality samples were collected from 54 wards under the urban area, the main eight different physiochemical parameters were selected for WA-WQI prediction. The different input parameters data were analysed and calculated for the relationships of their ability to predict the results of WA-WQI. The ML models performance were calculated using three statistical metrics such as determination coefficient (R2), mean absolute error (MAE), and root mean square error (RMSE). In this research shown the XG-Boost model is better results other than other ML models. The best modelling results over the training phase revealed R2 = 0.969, RMSE = 2.169, MAE = 2.013 and over the testing phase R2 = 0.987, RMSE = 3.273, MAE = 2.727). All the ML models results were validated using receiver operating characteristic (ROC) curve for the best models selection. The results of best model area under curve (AUC) was 0.9048. Hence, XG-Boost model was given the accurate prediction of WA-WQI in the urban area. Based on the graphical presentation evaluation, XG-Boost model showed similar results of superiority. The obtained modelling results emphasis the utility of computer aid models for better planning and essential information for decision-makers, and water experts. The implement agency can adopt the procedures of water quality to decrease pollution and safe and healthy water provide to entire Ujjain city.

Assessing industrial wastewater effluent toxicity using boosting algorithms in machine learning: A case study on ecotoxicity prediction and control strategy development

Trace heavy metals have a tendency to persist in the effluent of industrial wastewater treatment facilities, leading to toxic effects on downstream water bodies. Traditional assessment methods relied on animal testing, but ethical concerns have rendered them unacceptable. An alternative solution is to evaluate wastewater toxicity using trophic-level aquatic organisms as bioassays. However, these bioassay methods involve costly and time-consuming chemical and biological analytical experiments. In this study, an artificial intelligence-powered water quality assessment (AiWA) approach is proposed for predicting industrial effluent ecotoxicity to further enhance the quick and cost-effective ecotoxicity assessment process. Initially, 99 samples were collected from industrial wastewater treatment plants representing 21 different industries in the Republic of Korea. Fourteen parameters were measured, encompassing both physicochemical and ecotoxicological aspects. Boosting algorithms, especially extreme gradient boosting (XGBoost) and adaptive boosting (AdaBoost), were employed for model development. XGBoost outperformed AdaBoost in terms of model performance. Feature selection analysis revealed that conductivity, copper, lead, selenium, pH, and zinc concentrations were the most suitable inputs for training the boosting model. The innovated XGBoost-based AiWA model demonstrated significantly higher performance (i.e., up to 80%) compared to conventional models with an R2 value of exceeding 0.94 and root mean square error of 3.5 toxicity unit for predicting the integrated toxicity unit (ITU). Additionally, pH and conductivity emerged as crucial indicators for reflecting ecotoxicity levels. Specially, this case study indicated that non-toxic/directly dischargeable levels (TU ≤ 1) were achieved when the pH ranged from 6.8 to 8.4 and the conductivity remained below 1651 μS/cm. These findings are expected to facilitate rapid and cost-effective detection of heavy metal ecotoxicity in industrial wastewater effluents, aiding decision-making in wastewater management.

A critical review on the migration and transformation processes of heavy metal contamination in lead-zinc tailings of China

The health risks of lead-zinc (Pb-Zn) tailings from heavy metal (HMs) contamination have been gaining increasing public concern. The dispersal of HMs from tailings poses a substantial threat to ecosystems. Therefore, studying the mechanisms of migration and transformation of HMs in Pb-Zn tailings has significant ecological and environmental significance. Initially, this study encapsulated the distribution and contamination status of Pb-Zn tailings in China. Subsequently, we comprehensively scrutinized the mechanisms governing the migration and transformation of HMs in the Pb-Zn tailings from a geochemical perspective. This examination reveals the intricate interplay between various biotic and abiotic constituents, including environmental factors (EFs), characteristic minerals, organic flotation reagents (OFRs), and microorganisms within Pb-Zn tailings interact through a series of physical, chemical, and biological processes, leading to the formation of complexes, chelates, and aggregates involving HMs and OFRs. These interactions ultimately influence the migration and transformation of HMs. Finally, we provide an overview of contaminant migration prediction and ecological remediation in Pb-Zn tailings. In this systematic review, we identify several forthcoming research imperatives and methodologies. Specifically, understanding the dynamic mechanisms underlying the migration and transformation of HMs is challenging. These challenges encompass an exploration of the weathering processes of characteristic minerals and their interactions with HMs, the complex interplay between HMs and OFRs in Pb-Zn tailings, the effects of microbial community succession during the storage and remediation of Pb-Zn tailings, and the importance of utilizing process-based models in predicting the fate of HMs, and the potential for microbial remediation of tailings.

A holistic approach for understanding the status of water quality and causes of its deterioration in a drought-prone agricultural area of Southeastern India

This study investigates the groundwater quality in the Kadiri Basin, Ananthapuramu district of Andhra Pradesh, India. Groundwater samples from 77 locations were collected and tested for the concentration of various physicochemical parameters. The collected data were assimilated in the form of a groundwater quality index to estimate groundwater quality (drinking and irrigation) using an information entropy-based weight determination approach (EWQI). The water quality maps obtained from the study area suggest a definite trend in groundwater contamination of the study area. Furthermore, the influence of different physicochemical parameters on groundwater quality was determined using machine learning techniques. Learning and prediction accuracies of four different techniques, namely artificial neural network (ANN), deep learning (DL), random forest (RF), and gradient boosting machine (GBM), were investigated. The performance of the ANN model (MEA = 11.23, RSME = 21.22, MAPE = 7.48, and R2 = 0.91) was found to be highly effective for the present dataset. The ANN model was then used to understand the relative influence of physicochemical parameters on groundwater quality. It was observed that the deterioration in groundwater quality in the study area was primarily due to the excess concentration of turbidity and iron values. The relatively higher concentration of sulfate and nitrate had caused a significant impact on the groundwater quality. The study has wider implications for modeling in similar drought-prone agricultural areas elsewhere for assessing the groundwater quality.

Boundary optimization of inclined coal seam open-pit mine based on the ISSA-LSSVR coal price prediction method

As an important link in the complex system engineering project of open pit mining, the quality of the boundary determines the performance of the project to a large extent. However, changes in economic indicators may raise doubts about the optimality of mining boundaries. In this article, a coal price time series forecasting model that considers some amount of redundancy is proposed, which combines an improved sparrow search algorithm (ISSA) and a least squares support vector regression machine regression (LSSVR) algorithm. The optimal values of the penalty factor and kernel function parameter of the LSSVR model are selected by ISSA, which improves the prediction accuracy and generalization performance of the forecasting model. A multistep decision optimization method under fluctuating coal price conditions is proposed, and the model prediction results are applied to the boundary optimization design process. Using the widely applied block model as the basis, a set of optimal production nested pits is obtained, allowing the realm design results to fit the coal price fluctuation trend and further enhance enterprise efficiency. The applicability and effectiveness of this method were verified by taking an ideal two-dimensional model and an inclined coal seam open-pit coal mine in Xinjiang as an example.

Improving the efficiency of machine learning in simulating sedimentary heavy metal contamination by coupling preposing feature selection methods

Sediment cores were collected from Taihu Lake in China. The chronology was determined by radionuclide. Heavy metals and magnetic properties of each core slice were assessed, respectively. The concentrations of most heavy metals in sediments surged at 20 cm from the surface, accompanying the increase in the concentrations of single-domain magnetic particles. This may be resulted from the influence of anthropic activities on the lake's environment after the 1970s. Two feature selection methods, random forest (RF) and maximal information coefficient (MIC), were combined with support vector machine (SVM) model to simulate heavy metals, with the inclusion of selected magnetic and physicochemical parameters. Compared with the modeling results obtained with the full set of parameters, a reasonable simulation performance was obtained with RF and MIC. RF performed better than MIC by increasing the R² of simulation models for Cd, Cr, Cu, Pb, and Sb. For heavy metals with high ecological risks (As, Cd, Cr, Hg, Pb, Sb), the correlation coefficients for observed and predicted data ranged from 0.73 to 0.97 with only 14-27% of the parameters selected by RF as input variables. The RF-RBF-SVM enabled heavy metal predictions based on the magnetic properties of the lake sediments.

Prediction for odor gas generation from domestic waste based on machine learning

Domestic waste is prone to produce a variety of volatile organic compounds (VOCs), which often has unpleasant odors. A key process in treating odor gases is predicting the production of odors from domestic waste. In this study, four factors of domestic waste (weight, wet composition, temperature, and fermentation time) were adopted to be the prediction indicators in the prediction for domestic waste odor gases. Machine learning models (Random Forest, XGBoost, LightGBM) were established using the odor intensity values of 512 odor gases from domestic waste. Based on these data, the regression prediction with supervised machine learning was achieved, in which three different algorithmic models were evaluated for prediction performance. A Random Forest model with a R² value of 0.8958 demonstrated the most accurate prediction of the production of domestic waste odor gas based on our data. Furthermore, the prediction results in the Random Forest model were further discussed based on the microbial fermentation of domestic waste. In addition to enhancing our knowledge of the production of odor from domestic waste, we also explore the application of machine learning to odor pollution in our study.

Prediction of organic contaminant rejection by nanofiltration and reverse osmosis membranes using interpretable machine learning models

Efficiency improvement in contaminant removal by nanofiltration (NF) and reverse osmosis (RO) membranes is a multidimensional process involving membrane material selection and experimental condition optimization. It is unrealistic to explore the contributions of diverse influencing factors to the removal rate by trial-and-error experimentation. However, the advanced machine learning (ML) method is a powerful tool to simulate this complex decision-making process. Here, 4 traditional learning algorithms (MLR, SVM, ANN, kNN) and 4 ensemble learning algorithms (RF, GBDT, XGBoost, LightGBM) were applied to predict the removal efficiency of contaminants. Results reported here demonstrate that ensemble models showed significantly better predictive performance than traditional models. More importantly, this study achieved a compelling tradeoff between accuracy and interpretability for ensemble models with an effective model interpretation approach, which revealed the mutual interaction mechanism between the membrane material, contaminants and experimental conditions in membrane separation. Additionally, feature selection was for the first time achieved based on the aforementioned model interpretation method to determine the most important variable influencing the contaminant removal rate. Ultimately, the four ensemble models retrained by the selected variables achieved distinguished prediction performance (R²_adj = 92.4 %-99.5 %). MWCO (membrane molecular weight cut-off), McGowan volume of solute (V) and molecular weight (MW) of the compound were demonstrated to be the most important influencing factors in contaminant removal by the NF and RO processes. Overall, the proposed methods in this study can facilitate versatile complex decision-making processes in the environmental field, particularly in contaminant removal by advanced physicochemical separation processes.

A new hybrid ensemble approach for the prediction of effluent total nitrogen from a full-scale wastewater treatment plant using a combined trickling filter-activated sludge system

In this study, different K-nearest neighbors (KNN), support vector regression (SVR), decision tree (DT), and random forest (RF) algorithms integrated with the Bayesian optimization algorithm (BOP) have been applied as novel hybrid modeling/optimization tools to predict the total nitrogen in treated wastewater of Southern Tehran Wastewater Treatment Plant (STWWTP). In order to enhance the outcomes of hybrid models, the chosen sub-models (the best and least correlated hybrid models) were used to generate voting average and stacked regression ensemble models. Throughout the preprocessing step, two alternative scenarios were used to handle missing values from the samples, including elimination versus estimation via linear interpolation. The results of this research demonstrated that ensemble models were better than individual hybrid models, although not all ensemble models were superior to single models. The results also revealed that the stacking regression ensemble model using KNN-BOP and SVR-BOP as sub-models was the most superior model among the developed models, with the coefficient of determination (R²) = 0.640, root mean squared error (RMSE) = 2.378, and mean absolute error (MAE) = 1.838 on the test data. The best hybrid ensemble model that can accurately predict the concentration of total nitrogen (TN) in the effluent can give people a heads-up about water pollution caused by eutrophication before it gets bad.

Modeling, optimization and understanding of adsorption process for pollutant removal via machine learning: Recent progress and future perspectives

It is crucial to reduce the concentration of pollutants in water environment to below safe levels. Some cost-effective pollutant removal technologies have been developed, among which adsorption technology is considered as a promising solution. However, the batch experiments and adsorption isotherms widely employed at present are inefficient and time-consuming to some extent, which limits the development of adsorption technology. As a new research paradigm, machine learning (ML) is expected to innovate traditional adsorption models. This reviews summarized the general workflow of ML and commonly employed ML algorithms for pollutant adsorption. Then, the latest progress of ML for pollutant adsorption was reviewed from the perspective of all-round regulation of adsorption process, including adsorption efficiency, operating conditions and adsorption mechanism. General guidelines of ML for pollutant adsorption were presented. Finally, the existing problems and future perspectives of ML for pollutant adsorption were put forward. We highly expect that this review will promote the application of ML in pollutant adsorption and improve the interpretability of ML.

Predictive modeling of pharmaceutical product removal by a managed aquifer recharge system: Comparison and optimization of models using ensemble learners

Pharmaceutical products (PPs) are emerging water pollutants with adverse environmental and health-related impacts, owing to their toxic, persistent, and undetectable microscopic nature. Globally, increasing scientific knowledge and advanced technologies have allowed researchers to study PP-associated problems and their removal for water reuse. Experimental modeling methods require laborious, lengthy, expensive, and environmentally hazardous lab-work to optimize the process. On the other hand, predictive machine learning (ML) models can trace the complex input-output relationship of a process using available datasets. In this study, ensemble ML techniques, including decision tree (DT), random forest (RF), and Xtreme gradient boost (XGB), were used to explore PP (diclofenac, iopromide, propranolol, and trimethoprim) removal by a managed aquifer recharge (MAR) system. The model input parameters included characteristics of reclaimed water and soil used in the columns, pH, dissolved organic carbon, operating time, nitrogen dioxide, sulfate, nitrate, electrical conductivity, manganese, and iron. The selected PP removal was the model output. Datasets were collected through a one-year experimental study of continuous MAR system operation to predict the removal of PPs. DT, RF, and XGB models were then developed for one of the selected compounds and tested for the others to check the reliability of the ML model results. The developed models were assessed using statistical performance matrices. The experimental results showed >80% removal of propranolol and trimethoprim; however, removal of diclofenac and iopromide was only ≈50% by the MAR system. The proposed DT and RF models presented higher coefficients of determination (R² ≥ 0.92) for diclofenac, propranolol, and trimethoprim than for iopromide (R² ≤ 0.63). In contrast, the XGB model showed better results for diclofenac, iopromide, propranolol, and trimethoprim, with R² values of 0.92, 0.72, 0.96, and 0.97, respectively. Therefore, XGB could be the best predictive model to provide insight into the adaptation of ML models to predict PP removal by the MAR system, thereby minimizing experimental work.

The spatial distribution of phytoliths and phytolith-occluded carbon in wheat (Triticum aestivum L.) ecosystem in China

Phytolith is a form of SiO₂ in plants. Carbon can be sequestrated as phytolith-occluded carbon (PhytOC) during the formation of phytoliths. PhytOC is characterized by its high resistance to temperature, oxidation and decomposition under protection of phytoliths and can be stored in the soil for thousands of years. Soil also is a huge PhytOC sink; however, most studies focus on PhytOC storage in straw and other residues. Wheat is a major staple food crop accumulating high content of Si and distributed widely, while its potential for PhytOC is not clear. At present, PhytOC storage only considers on the average value, but not on the relationship between ecological factors and the spatial distribution of PhytOC sequestration. Climatic factors and soil physiochemical properties together affect the formation process and stability of phytoliths. In our study, we collected wheat straw and soil samples from 95 sites among five provinces to extract phytolith and PhytOC. We constructed XGBoost model to predict the spatial distribution of phytolith and PhytOC across the country using the national soil testing and formula fertilization nutrient dataset and climate data. As a result, soil physiochemical factors such as available silicon (Si_avail), total carbon (C_tot) and total nitrogen (N_tot) and climate factors related to temperature and precipitation have a great positive impact on the production of phytoliths and PhytOC. Meanwhile, PhytOC storage in wheat ecosystems was estimated to be 7.59 × 10⁶ t, which is equivalent to 27.83 Tg of CO₂. In China, the distribution characteristics of phytoliths and PhytOC in wheat straw and soil display a trend of decrease from south to north. He'nan Province is the largest wheat production area, producing approximately 1.59 × 10⁶ t PhytOC per year. Therefore, PhytOC is a stable CO₂ sink pathway in the agricultural ecosystems, which is of great importance for mitigating climate warming.

Hybrid machine learning approach for landslide prediction, Uttarakhand, India

Natural disasters always have a damaging effect on our way of life. Landslides  cause serious damage to both human and natural resources around the world. In this paper, the prediction accuracy of five hybrid models for landslide occurrence in the Uttarkashi, Uttarakhand (India) was evaluated and compared. In this approach, the Rough Set theory coupled with five different models namely Bayesian Network (HBNRS), Backpropagation Neural Network (HBPNNRS), Bagging (HBRS), XGBoost (HXGBRS), and Random Forest (HRFRS) were taken into account. The database for the models development was prepared using fifteen conditioning factors that had 373 landslide and 181 non-landslide locations that were then randomly divided into training and testing locations with a ratio of 75%:25%. The appropriateness and predictability of these conditioning factors were assessed using the multi-collinearity test and the least absolute shrinkage and selection operator approach. The accuracy, sensitivity, specificity, precision, and F-Measures, and the area under the curve (AUC)-receiver operating characteristics curve, were used to evaluate and compare the performance of the individual and hybrid created models. The findings indicate that the constructed hybrid model HXGBRS (AUC = 0.937, Precision = 0.946, F1-score = 0.926 and Accuracy = 89.92%) is the most accurate model for predicting landslides when compared to other models (HBPNNRS, HBNRS, HBRS, and HRFRS). Importantly, when the fusion is performed with the rough set method, the prediction capability of each model is improved. Simultaneously, the HXGBRS model proposed shows superior stability and can effectively avoid overfitting. After the core modules were developed, the user-friendly platform was designed as an integrated GIS environment using dynamic maps for effective landslide prediction in large prone areas. Users can predict the probability of landslide occurrence for selected region by changing the values of a conditioning factors. The created approach could be beneficial for predicting the impact of landslides on slopes and tracking landslides along national routes.

Machine learning based prediction for China's municipal solid waste under the shared socioeconomic pathways

Reliable forecast of municipal solid waste (MSW) generation is crucial for sustainable and efficient waste management. Big data analysis is a novel method to forecast MSW more accurately. Thus, this study employs five kinds of supervised machine learning approaches including linear regression, polynomial regression, support vector machine, random forest, and extreme gradient boosting (XGBoost) to examine their forecast performances. China's MSW generation from 2020 to 2060 under five shared socioeconomic pathways (SSPs) is further predicted and the mechanisms between MSW generation and socioeconomic features are explored. Results show that population and GDP are two dominant indicators in MSW prediction, and XGBoost model is proved to be effective in MSW forecast. MSW generation of China in 2060 is estimated to be 464-688 megatons under different SSPs scenarios, about four to six times of that in 2000. SSP3 that has the most population, least GDP and the highest climate change challenges is the only scenario showing a potential of MSW peak during the study period. The key for MSW increase is mainly the increase of per capita MSW caused by GDP. Finally, several policy recommendations are raised to reduce the overall MSW generation.

A review of the application of machine learning in water quality evaluation

With the rapid increase in the volume of data on the aquatic environment, machine learning has become an important tool for data analysis, classification, and prediction. Unlike traditional models used in water-related research, data-driven models based on machine learning can efficiently solve more complex nonlinear problems. In water environment research, models and conclusions derived from machine learning have been applied to the construction, monitoring, simulation, evaluation, and optimization of various water treatment and management systems. Additionally, machine learning can provide solutions for water pollution control, water quality improvement, and watershed ecosystem security management. In this review, we describe the cases in which machine learning algorithms have been applied to evaluate the water quality in different water environments, such as surface water, groundwater, drinking water, sewage, and seawater. Furthermore, we propose possible future applications of machine learning approaches to water environments.

Integrative artificial intelligence models for Australian coastal sediment lead prediction: An investigation of in-situ measurements and meteorological parameters effects

Heavy metals (HMs) such as Lead (Pb) have played a vital role in increasing the sediments of the Australian bay's ecosystem. Several meteorological parameters (i.e., minimum, maximum and average temperature (T_min, T_max and T_avg^oC), rainfall (R_n mm) and their interactions with the other batch HMs, are hypothesized to have high impact for the decision-making strategies to minimize the impacts of Pb. Three feature selection (FS) algorithms namely the Boruta method, genetic algorithm (GA) and extreme gradient boosting (XGBoost) were investigated to select the highly important predictors for Pb concentration in the coastal bay sediments of Australia. These FS algorithms were statistically evaluated using principal component analysis (PCA) Biplot along with the correlation metrics describing the statistical characteristics that exist in the input and output parameter space of the models. To ensure a high accuracy attained by the applied predictive artificial intelligence (AI) models i.e., XGBoost, support vector machine (SVM) and random forest (RF), an auto-hyper-parameter tuning process using a Grid-search approach was also implemented. Cu, Ni, Ce, and Fe were selected by all the three applied FS algorithms whereas the T_avg and R_n inputs remained the essential parameters identified by GA and Boruta. The order of the FS outcome was XGBoost > GA > Boruta based on the applied statistical examination and the PCA Biplot results and the order of applied AI predictive models was XGBoost-SVM > GA-SVM > Boruta-SVM, where the SVM model remained at the top performance among the other statistical metrics. Based on the Taylor diagram for model evaluation, the RF model was reflected only marginally different so overall, the proposed integrative AI model provided an evidence a robust and reliable predictive technique used for coastal sediment Pb prediction.

Transforming approach for assessing the performance and applicability of rice arsenic contamination forecasting models based on regression and probability methods

Probability models are preferred over regression models recently in contamination evaluation but lacking proper performance comparison between two model types. Linear regression, logistic regression, XGBoost-based regression, and probability models were built considering soil arsenic and certain soil physicochemical properties of 287 samples to predict arsenic in rice grains. The outputs of all models were binarily classified uniformly for comparison. The complex algorithm-based models--XGBoost-based regression (R² =0.046 ± 0.036) and probability models (cross-entropy = 0.697 ± 0.020)-did not surpass the simple linear regression (R² =0.046 ± 0.031) and logistic regression models (cross-entropy = 0.694 ± 0.021). Accuracy, sensitivity, specificity, precision, and F1 score showed that the probability models exhibit no advantage on regression models, although the indicators above did not serve as proper scoring rules for the probability model. When discretizing the contaminant concentration in grains for probabilistic modeling, the limit concentration was considered as the splitting point but not the structure of the datasets, which would reduce the inherent advantage of the probability model. When predicting the contamination of crops, the probability model cannot eliminate the regression model, and simple but robust algorithm-based models are preferred when the quality and quantity of the dataset are undesirable.

Remote Sensing Monitoring of Winter Wheat Stripe Rust Based on mRMR-XGBoost Algorithm

For the problem of multi-dimensional feature redundancy in remote sensing detection of wheat stripe rust using reflectance spectrum and solar-induced chlorophyll fluorescence (SIF), a feature selection and disease index (DI) monitoring model combining mRMR and XGBoost algorithm was proposed in this study. Firstly, characteristic wavelengths selected by successive projections algorithm (SPA) were combined with the vegetation indices, trilateral parameters, and canopy SIF parameters to constitute the initial feature set. Then, the max-relevance and min-redundancy (mRMR) algorithm and correlation coefficient (CC) analysis were used to reduce the dimensionality of the initial feature set, respectively. Features selected by mRMR and CC were input as independent variables into the extreme gradient boosting regression (XGBoost) and gradient boosting regression tree (GBRT) to monitor the severity of stripe rust. The experimental results show that, compared with CC analysis, the monitoring accuracy of the features selected by mRMR in the XGBoost and GBRT models increased by 12% and 17% on average, respectively. Meanwhile, the mRMR-XGBoost model achieved the best monitoring accuracy (R2 = 0.8894, RMSE = 0.1135). The R2 between the measured DI and predicted DI of mRMR-XGBoost was improved by an average of 5%, 12%, and 22% compared with mRMR-GBRT, CC-XGBoost, and CC-GBRT models. These results suggested that XGBoost is more suitable for the remote sensing monitoring of wheat stripe rust, and mRMR has more advantages than the commonly used CC analysis in feature selection. Field survey data validation results also confirm that the mRMR-XGBoost algorithm has excellent monitoring applicability and scalability. The proposed model could provide a reference for data dimensionality reduction and crop disease index monitoring based on hyperspectral data.

Predicting Heavy Metal Adsorption on Soil with Machine Learning and Mapping Global Distribution of Soil Adsorption Capacities

Studying heavy metal adsorption on soil is important for understanding the fate of heavy metals and properly assessing the related environmental risks. Existing experimental methods and traditional models for quantifying adsorption, however, are time-consuming and ineffective. In this study, we developed machine learning models for the soil adsorption of six heavy metals (Cd(II), Cr(VI), Cu(II), Pb(II), Ni(II), and Zn(II)) using 4420 data points (1105 soils) extracted from 150 journal articles. After a comprehensive comparison, our results showed that the gradient boosting decision tree had the best performance for a combined model based on all the data. The Shapley additive explanation method was used to identify the feature importance and the effects of these features on the adsorption, based on which six independent models were developed for the six metals to achieve better model performance than the combined model. Using these independent models, the global distribution of heavy metal adsorption capacities on soils was predicted with known soil properties. Reversed models, including one combined model for all the six metals and six independent models, were also built using the same data sets to predict the heavy metal concentration in water when the adsorbed amount is known for a soil/sediment.

Statistical comparison between SARIMA and ANN's performance for surface water quality time series prediction

The performance comparison studies of the autoregressive integrated moving average model (ARIMA) and the artificial neural network (ANN) were mostly carried out between the selected model structures through trial-and-error, strongly influenced by model structure uncertainty. This research aims to make up for this inadequacy. First, a surface water quality prediction case study including eight monitoring sites in China was introduced. Second, the ARIMA and ANN's performance was compared statistically between 6912 Seasonal ARIMA (SARIMA) and 110,592 feedforward ANN with different model structures, based on the mean square error (MSE) distributions depicted by boxplots. In a statistical view, the ANN models obtained a significantly lower median value and a more concentrated distribution of validation MSEs, which indicated lighter overfitting and better generalization ability. Furthermore, the optimal SARIMA models' performance is inferior to even the median of the ANN models in the case study. In contrast with the previous comparisons among selected models, the statistical comparison in this study shows lower uncertainty.

Impact of Input Filtering and Architecture Selection Strategies on GRU Runoff Forecasting: A Case Study in the Wei River Basin, Shaanxi, China

A gated recurrent unit (GRU) network, which is a kind of artificial neural network (ANN), has been increasingly applied to runoff forecasting. However, knowledge about the impact of different input data filtering strategies and the implications of different architectures on the GRU runoff forecasting model’s performance is still insufficient. This study has selected the daily rainfall and runoff data from 2007 to 2014 in the Wei River basin in Shaanxi, China, and assessed six different scenarios to explore the patterns of that impact. In the scenarios, four manually-selected rainfall or runoff data combinations and principal component analysis (PCA) denoised input have been considered along with single directional and bi-directional GRU network architectures. The performance has been evaluated from the aspect of robustness to 48 various hypermeter combinations, also, optimized accuracy in one-day-ahead (T + 1) and two-day-ahead (T + 2) forecasting for the overall forecasting process and the flood peak forecasts. The results suggest that the rainfall data can enhance the robustness of the model, especially in T + 2 forecasting. Additionally, it slightly introduces noise and affects the optimized prediction accuracy in T + 1 forecasting, but significantly improves the accuracy in T + 2 forecasting. Though with relevance (R = 0.409~0.763, Grey correlation grade >0.99), the runoff data at the adjacent tributary has an adverse effect on the robustness, but can enhance the accuracy of the flood peak forecasts with a short lead time. The models with PCA denoised input has an equivalent, even better performance on the robustness and accuracy compared with the models with the well manually filtered data; though slightly reduces the time-step robustness, the bi-directional architecture can enhance the prediction accuracy. All the scenarios provide acceptable forecasting results (NSE of 0.927~0.951 for T + 1 forecasting and 0.745~0.836 for T + 2 forecasting) when the hyperparameters have already been optimized. Based on the results, recommendations have been provided for the construction of the GRU runoff forecasting model.