Soil Cd, Cr, Cu, Ni, Pb and Zn sorption and retention models using SVM: Variable selection and competitive model

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.

Temporal and spatial evolution of different heavy metal fractions and correlation with environmental factors after prolonged acid mine drainage irrigation: A column experiment

Acid mine drainage (AMD) has global significance due to its low pH and elevated heavy metal content, which have received widespread attention. After AMD irrigation in mining areas, heavy metals are distributed among soil layers, but the influencing factors and mechanisms remain unclear. AMD contamination of surrounding soil is primarily attributed to surface runoff and irrigation and causes significant environmental degradation. A laboratory soil column experiment was conducted to investigate the temporal and spatial distribution of the heavy metals Cd and Cu, as well as the impact of key environmental factors on the migration and transformation of these heavy metals following long-term soil pollution by AMD. After AMD addition, the soil exhibited a significant increase in acidity, accompanied by notable alterations in various environmental parameters, including soil pH, Eh, Fe(II) content, and iron oxide content. Over time, Cd and Cu in the soil mainly existed in the exchangeable and carbonate-bound fractions. In spatial terms, exchangeable Cu increased with increasing depth. Pearson correlation analysis indicated significant negative correlations between pH and Cu, Cd, and Eh in pore water, as well as negative correlations between pH and the exchangeable fraction of Cd (F1), carbonate-bound fraction of Cd (F2), and exchangeable fraction of Cu (F1) in the solid phase. Additionally, a positive correlation was observed between pH and the residual fraction of Cu (F5). Furthermore, the soil total Cd content exhibited a positive correlation with pyrophosphate-Fe (Fep) and dithionite-Fe (Fed), while CdF1, CdF2, total Cu, and CuF1 displayed positive correlations with Fep. Our findings indicate that the presence of AMD in soil leads to alterations in the chemical fractions of Cd and Cu, resulting in enhanced bioavailability. These results offer valuable insights for developing effective remediation strategies for soils near mining sites.

Machine learning-based prediction of cadmium pollution in topsoil and identification of critical driving factors in a mining area

Mining activities have resulted in a substantial accumulation of cadmium (Cd) in agricultural soils, particularly in southern China. Long-term Cd exposure can cause plant growth inhibition and various diseases. Rapid identification of the extent of soil Cd pollution and its driving factors are essential for soil management and risk assessment. However, traditional geostatistical methods are difficult to simulate the complex nonlinear relationships between soil Cd and potential features. In this study, sequential extraction and hotspot analyses indicated that Cd accumulation increased significantly near mining sites and exhibited high mobility. The concentration of Cd was estimated using three machine learning models based on 3169 topsoil samples, seven quantitative variables (soil pH, Fe, Ca, Mn, TOC, Al/Si and ba value) and three quantitative variables (soil parent rock, terrain and soil type). The random forest model achieved marginally better performance than the other models, with an R2 of 0.78. Importance analysis revealed that soil pH and Ca and Mn contents were the most significant factors affecting Cd accumulation and migration. Conversely, due to the essence of controlling Cd migration being soil property, soil type, terrain, and soil parent materials had little impact on the spatial distribution of soil Cd under the influence of mining activities. Our results provide a better understanding of the geochemical behavior of soil Cd in mining areas, which could be helpful for environmental management departments in controlling the diffusion of Cd pollution and capturing key targets for soil remediation.

Contaminated soil remediation with nano-FeS loaded lignin hydrogel: A novel strategy to produce safe rice grains while reducing cadmium in paddy field

Cadmium (Cd) contamination in agricultural soil has been an elevated concern due to the high health risks associated with the transfer through the soil-food chain, particularly in the case of rice. Recently, there has numerous researches on the use of nanoparticle-loaded materials for heavy metal-polluted soil remediation, resulting in favorable outcomes. However, there has been limited research focus on the field-scale application and recovery. This study was aimed to validate the Cd reduction effect of the nano-FeS loaded lignin hydrogel composites (FHC) in mildly polluted paddies, and to propose a field-scale application method. Hence, a multi-site field experiment was conducted in southern China. After the application for 94-103 days, the FHC exhibited a high integrity and elasticity, with a recovery rate of 91.90%. The single-round remediation led to decreases of 0.42-31.72% in soil Cd content and 1.52-49.11% in grain Cd content. Additionally, this remediation technique did not adversely impact rice production. Consequently, applying FHC in the field was demonstrated to be an innovative, efficient, and promising remediation technology. Simultaneously, a strategy was proposed for reducing Cd levels while cultivating rice in mildly polluted fields using the FHC.

Identification of soil parent materials in naturally high background areas based on machine learning

Recently, farmlands with high geological background of Cd derived from carbonate rock (CA) and black shale areas (BA) have received wide attention. However, although both CA and BA belong to high geological background areas, the mobility of soil Cd differs significantly between them. In addition to the difficulty in reaching the parent material in deep soil, it is challenging to perform land use planning in high geological background areas. This study attempts to determine the key soil geochemical parameters related to the spatial patterns of lithology and the main factors influencing the geochemical behavior of soil Cd, and ultimately uses them and machine-learning methods to identify CA and BA. In total, 10,814 and 4323 surface soil samples were collected from CA and BA, respectively. Hot spot analysis revealed that soil properties and soil Cd were significantly correlated with the underlying bedrock, except for TOC and S. Further research confirmed that the concentration and mobility of Cd in high geological background areas were mainly affected by pH and Mn. The soil parent materials were then predicted using artificial neural network (ANN), random forest (RF) and support vector machine (SVM) models. The ANN and RF models showed higher Kappa coefficients and overall accuracies than those of the SVM model, suggesting that ANNs and RF have the potential to predict soil parent materials from soil data, which might help in ensuring safe land use and coordinating activities in high geological background areas.

Analysis of Cadmium Retention Mechanisms by a Smectite Clay in the Presence of Carbonates

Cadmium (Cd) is a toxic heavy metal with very low permissible exposure limits and is, thus, a very dangerous pollutant for the environment and public health and is considered by the World Health Organisation as one of the ten chemicals of major public concern. Adsorption onto solid phases and (co)precipitation processes are the most powerful mechanisms to retain pollutants and limit their migration; thus, the understanding of these processes is fundamental for assessing the risks of their presence in the environment. In this study, the immobilisation of Cd by smectite clay has been investigated by batch sorption tests, and the experimental data were interpreted with a thermodynamic model, including cation exchange and surface complexation processes. The model can describe the adsorption of Cd in smectite under a wide range of experimental conditions (pH, ionic strength, and Cd concentration). Under the conditions analysed in this study, the precipitation of otavite (CdCO₃) is shown to have a limited contribution to Cd immobilisation.

Woodland for Sludge Disposal in Beijing: Sustainable?

The sludge products of urban sewage treatment plants in Beijing are increasing year by year, and there is a large amount of stagnation, which requires scientific and reasonable disposal strategies. Currently, the woodland in the mountainous area of Beijing is considered the main means for sludge disposal; however, because the heavy metals in the sludge may cause potential pollution to the soil and groundwater, it is unclear how much sludge can be applied per unit area. To ensure the sustainable disposal of sludge, it is necessary to measure the risk of heavy metals on soil and groundwater under different sludge application rates to determine the most scientific disposal plan. In this study, the undisturbed soil columns obtained from the field were used to clarify the migration behaviors and accumulation of eight hazardous heavy metals under simulated rainfall conditions, and three sets of tests (the application rates of sludge products were 30 t·ha−1·a−1, 60 t·ha−1·a−1 and 120 t·ha−1·a−1 respectively) were set based on the supply–demand relationship between Beijing’s annual sludge output and the woodland area available for sludge disposal. The results showed that there were significant differences in the migration rules of heavy metals under different application rates, which were mainly reflected in the differences in accumulation in each layer of the soil. In terms of the leaching efficiency of heavy metals, except for Cadmium, the leaching rates of other heavy metals did not exceed 0.1%, indicating that most heavy metals accumulated in the soil. During the application process of sludge products, Arsenic and Cadmium posed a greater potential risk to groundwater than other heavy metals, to which should be paid sufficient attention. Based on the accumulation of heavy metals in soil, Arsenic was the main factor limiting the amount and frequency of sludge product application. The application rate of 60 t·ha−1·a−1 was preferred compared with the other two tests because it presented minimal risk to groundwater and soil in the short term, while the total amount of sludge disposal can be maximized.

Using Artificial Intelligent to Model Predict the Biological Resilience With an Emphasis on Population of cyanobacteria in Jajrood River in The Eastern Tehran, Iran

Prediction of bio-resilience in water resources such as rivers is important for better management of land-use systems and water resources. This study has proposed the use of artificial intelligent (AI) models for assessing the relationship among the biological conditions in Jajrood River. For this purpose, the qualitative monthly data of the river related to 2008-2018 were applied. Different resilience indicators for preparation of scenarios were determined using the canonical correlation analysis (CCA) method. Appropriate time-series scenarios (5scenarios) were modelled via Gene Expression Programming (GEP) plus Support Vector Machine (SVM), the bio-indicators were predicted. In order to reduce the error, the wavelet hybrids (W-GEP and W-SVM) were also used for modelling. Validation of the models was performed using Nash-Sutcliffe efficiency (E), root mean square error (RMSE), and mean‏ absolute error (MAE). In all the models investigated, Scenario 3 and Scenario 4 had the highest and lowest accuracies as 0.98 and 0.33 in validation, respectively. The third scenario combined with NO3 ^-, BOD_t-1, BOD, PO3^-, and Q provided the best results. Then, the values of 0.98, 0.94, 0.82, and 0.78 were obtained for its validation by WSVM, WGEP, SVM, and GEP models, respectively. These findings suggested the superiority of hybrid models and SVM over classical models and GEP in water quality assessment respectively. Examination of the scenarios revealed that NO₃ ^- and DO had the highest and the lowest impact on Shannon index of Cyanophyceae algae over time, as a bio-indicator of water quality in the river, respectively.

Adsorption of benzene on soils under different influential factors: an experimental investigation, importance order and prediction using artificial neural network

The adsorption of benzene on soils is specifically associated with its migration and transformation. Although previous studies have proved that the adsorption of benzene is affected by various factors, studies simultaneously considering the effects of multiple factors are rare. This study aimed to identify the qualitative and quantitative relationships between multiple influential factors and the adsorption capacity of benzene (BC). Batch adsorption experiments considering different influential factors, including initial concentration (IC), pH, temperature (T), ion strength (IS) and organic matter content (OMC), were conducted in three kinds of soils collected in a chemical industry park. The correlation analysis between different influential factors and BC was carried out based on the experimental data. The artificial neural network (ANN) was applied to predict BC. The results showed that BC increased with the increase of T. As the pH increased, BCs on silty loam and loam increased, while that on sandy loam decreased. Besides, BCs on silty loam and loam raised with increasing OMC, while that on sandy loam remained unchanged. BCs on all three kinds of soils attained their peaks when IS was small and then become stable with an increase in IS. The sequence of correlation between BC and influential factors is listed as IC > OMC > T > IS > pH for silty loam, OMC > IC > T > IS > pH for loam and IC > T > IS > pH > OMC for sandy loam. ANN analysis showed satisfactory accuracy in predicting BC under different influential factors. These results help us understand the important factors affecting benzene adsorption and provide a tool to get the adsorption information easily in complex site conditions.

Prediction of copper ions adsorption by attapulgite adsorbent using tuned-artificial intelligence model

Copper (Cu) ion in wastewater is considered as one of the crucial hazardous elements to be quantified. This research is established to predict copper ions adsorption (Ad) by Attapulgite clay from aqueous solutions using computer-aided models. Three artificial intelligent (AI) models are developed for this purpose including Grid optimization-based random forest (Grid-RF), artificial neural network (ANN) and support vector machine (SVM). Principal component analysis (PCA) is used to select model inputs from different variables including the initial concentration of Cu (IC), the dosage of Attapulgite clay (Dose), contact time (CT), pH, and addition of NaNO₃ (SN). The ANN model is found to predict Ad with minimum root mean square error (RMSE = 0.9283) and maximum coefficient of determination (R² = 0.9974) when all the variables (i.e., IC, Dose, CT, pH, SN) were considered as input. The prediction accuracy of Grid-RF model is found similar to ANN model when a few numbers of predictors are used. According to prediction accuracy, the models can be arranged as ANN-M5> Grid-RF-M5> Grid-RF-M4> ANN-M4> SVM-M4> SVM-M5. Overall, the applied statistical analysis of the results indicates that ANN and Grid-RF models can be employed as a computer-aided model for monitoring and simulating the adsorption from aqueous solutions by Attapulgite clay.

Heavy metal contamination prediction using ensemble model: Case study of Bay sedimentation, Australia

Lead (Pb) is a primary toxic heavy metal (HM) which present throughout the entire ecosystem. Some commonly observed challenges in HM (Pb) prediction using artificial intelligence (AI) models include overfitting, normalization, validation against classical AI models, and lack in learning/technology transfer. This study explores the extreme gradient boosting (XGBoost) model as a superior SuperLearning (SL) algorithms for Pb prediction. The proposed model was examined using historical data at the Bramble and Deception Bay (BB and DB) stations, Australia. The model was trained at one of the stations and transferred to a cross-station and vice versa. XGBoost showed higher reliability with less declination in (R²: coefficient of determination), i.e., 0.97 % over the testing phase, among others models at BB. At the cross-station (DB), the performance of the XGBoost model was decreased by 2.74 % (R²) against random forests (RF). The mean absolute error (MAE) observed 40 % (XGBoost) and 47 % (RF) less than artificial neural network (ANN). The XGBoost model performance declined by 3.44 % (R²) over testing (DB), which is minor among validated models. At the cross-station (BB), the XGBoost model showed the least decrement in terms of R², i.e., 7.99 % against the ANN (8.31 %), RF (10.26 %), and support vector machine (SVM, 36.19 %).

Machine learning for predicting greenhouse gas emissions from agricultural soils

Machine learning (ML) models are increasingly used to study complex environmental phenomena with high variability in time and space. In this study, the potential of exploiting three categories of ML regression models, including classical regression, shallow learning and deep learning for predicting soil greenhouse gas (GHG) emissions from an agricultural field was explored. Carbon dioxide (CO₂) and nitrous oxide (N₂O) fluxes, as well as various environmental, agronomic and soil data were measured at the site over a five-year period in Quebec, Canada. The rigorous analysis, which included statistical comparison and cross-validation for the prediction of CO₂ and N₂O fluxes, confirmed that the LSTM model performed the best among the considered ML models with the highest R coefficient and the lowest root mean squared error (RMSE) values (R = 0.87 and RMSE = 30.3 mg·m^-2·hr^-1 for CO₂ flux prediction and R = 0.86 and RMSE = 0.19 mg·m^-2·hr^-1 for N₂O flux prediction). The predictive performances of LSTM were more accurate than those simulated in a previous study conducted by a biophysical-based Root Zone Water Quality Model (RZWQM2). The classical regression models (namely RF, SVM and LASSO) satisfactorily simulated cyclical and seasonal variations of CO₂ fluxes (R = 0.75, 0.71 and 0.68, respectively); however, they failed to reasonably predict the peak values of N₂O fluxes (R < 0.25). Shallow ML was found to be less effective in predicting GHG fluxes than other considered ML models (R < 0.7 for CO₂ flux and R < 0.3 for estimating N₂O fluxes) and was the most sensitive to hyperparameter tuning. Based on this comprehensive comparison study, it was elicited that the LSTM model can be employed successfully in simulating GHG emissions from agricultural soils, providing a new perspective on the application of machine learning modeling for predicting GHG emissions to the environment.

Chemometrics for environmental monitoring: a review

Environmental monitoring is necessary to ensure the overall health and conservation of an ecosystem. However, ecosystems (e.g. air, water, soil), are complex, involving numerous processes (both native and external), inputs, contaminants, and living organisms. As such, monitoring an environmental system is not a trivial task. The data obtained from natural systems is often multifaceted and convoluted, as a multitude of inputs can be intertwined within the matrix of the information obtained as part of a study. This means that trends and important results can be easily overlooked by conventional and single dimensional data analysis protocols. Recently, chemometric methods have emerged as a powerful method for maximizing the details contained within a chemical data set. Specifically, chemometrics refers to the use of mathematical and statistical analysis methods to evaluate chemical data, beyond univariant analysis. This type of analysis can provide a quantitative description of environmental measurements, while also having the capacity to reveal previously overlooked trends in data sets. Applying chemometrics to environmental data allows us to identify and describe the inter-relationship of environmental drivers, sources of contamination, and their potential impact upon the environment. This review aims to provide a detailed understanding of chemometric techniques, how they are currently used in environmental monitoring, and how these techniques can be used to improve current practices. An enhanced ability to monitor environmental conditions and to predict trends would be greatly beneficial to government and research agencies in their ability to develop environmental policies and analytical procedures.

The performance of emerging materials derived from waste organism blood and saponified modified orange peel for immobilization of available Cd in soil

Waste organism blood (WOB) and orange peel are emerging stabilization materials obtained as by-products from agricultural processes, which are quite suitable for heavy metal immobilization in soil. In this work, waste organism blood and chemically modified orange peel (SOP) were investigated as potential sorbents for immobilization of available Cd in soil. Application of 5% WOB and SOP effectively immobilized cadmium (Cd) with an associated regulation of soil pH, among which the pH of acidic soil increased most significantly. While the application of 3% SOP alone stabilized almost the same amount of available Cd compared to WOB, it caused the highest stabilization rate of 58.85% when applied at 5%. By contrast, SOP combined with WOB (the mass ratio of the material is 1 : 1) at a 5% addition rate stabilized the available Cd in soils remarkably, with a stabilization rate of 57.74%. This study revealed that the soil particles after stabilization have a more compact and flaky structure, and the SOP and WOB had a particular pore structure, which was helpful for the adsorption of available Cd in soil. This study put forward new insights into the potential effects of Cd immobilization in contaminated soil by newly emerging stabilization biomass materials (WOB and SOP).

Efficacy of Enzymatically Induced Calcium Carbonate Precipitation in the Retention of Heavy Metal Ions

This study evaluated the efficacy of enzyme induced calcite precipitation (EICP) in restricting the mobility of heavy metals in soils. EICP is an environmentally friendly method that has wide ranging applications in the sustainable development of civil infrastructure. The study examined the desorption of three heavy metals from treated and untreated soils using ethylene diamine tetra-acetic acid (EDTA) and citric acid (C6H8O7) extractants under harsh conditions. Two natural soils spiked with cadmium (Cd), nickel (Ni), and lead (Pb) were studied in this research. The soils were treated with three types of enzyme solutions (ESs) to achieve EICP. A combination of urea of one molarity (M), 0.67 M calcium chloride, and urease enzyme (3 g/L) was mixed in deionized (DI) water to prepare enzyme solution 1 (ES1); non-fat milk powder (4 g/L) was added to ES1 to prepare enzyme solution 2 (ES2); and 0.37 M urea, 0.25 M calcium chloride, 0.85 g/L urease enzyme, and 4 g/L non-fat milk powder were mixed in DI water to prepare enzyme solution 3 (ES3). Ni, Cd, and Pb were added with load ratios of 50 and 100 mg/kg to both untreated and treated soils to study the effect of EICP on desorption rates of the heavy metals from soil. Desorption studies were performed after a curing period of 40 days. The curing period started after the soil samples were spiked with heavy metals. Soils treated with ESs were spiked with heavy metals after a curing period of 21 days and then further cured for 40 days. The amount of CaCO3 precipitated in the soil by the ESs was quantified using a gravimetric acid digestion test, which related the desorption of heavy metals to the amount of precipitated CaCO3. The order of desorption was as follows: Cd > Ni > Pb. It was observed that the average maximum removal efficiency of the untreated soil samples (irrespective of the load ratio and contaminants) was approximately 48% when extracted by EDTA and 46% when extracted by citric acid. The soil samples treated with ES2 exhibited average maximum removal efficiencies of 19% and 10% when extracted by EDTA and citric acid, respectively. It was observed that ES2 precipitated a maximum amount of calcium carbonate (CaCO3) when compared to ES1 and ES3 and retained the maximum amount of heavy metals in the soil by forming a CaCO3 shield on the heavy metals, thus decreasing their mobility. An approximate improvement of 30% in the retention of heavy metal ions was observed in soils treated with ESs when compared to untreated soil samples. Therefore, the study suggests that ESs can be an effective alternative in the remediation of soils contaminated with heavy metal ions.

Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran

Estimation of the soil organic carbon (SOC) content is of utmost importance in understanding the chemical, physical, and biological functions of the soil. This study proposes machine learning algorithms of support vector machines (SVM), artificial neural networks (ANN), regression tree, random forest (RF), extreme gradient boosting (XGBoost), and conventional deep neural network (DNN) for advancing prediction models of SOC. Models are trained with 1879 composite surface soil samples, and 105 auxiliary data as predictors. The genetic algorithm is used as a feature selection approach to identify effective variables. The results indicate that precipitation is the most important predictor driving 14.9% of SOC spatial variability followed by the normalized difference vegetation index (12.5%), day temperature index of moderate resolution imaging spectroradiometer (10.6%), multiresolution valley bottom flatness (8.7%) and land use (8.2%), respectively. Based on 10-fold cross-validation, the DNN model reported as a superior algorithm with the lowest prediction error and uncertainty. In terms of accuracy, DNN yielded a mean absolute error of 0.59%, a root mean squared error of 0.75%, a coefficient of determination of 0.65, and Lin’s concordance correlation coefficient of 0.83. The SOC content was the highest in udic soil moisture regime class with mean values of 3.71%, followed by the aquic (2.45%) and xeric (2.10%) classes, respectively. Soils in dense forestlands had the highest SOC contents, whereas soils of younger geological age and alluvial fans had lower SOC. The proposed DNN (hidden layers = 7, and size = 50) is a promising algorithm for handling large numbers of auxiliary data at a province-scale, and due to its flexible structure and the ability to extract more information from the auxiliary data surrounding the sampled observations, it had high accuracy for the prediction of the SOC base-line map and minimal uncertainty.

Effect of dissolved organic matters on adsorption and desorption behavior of heavy metals in a water-level-fluctuation zone of the Three Gorges Reservoir, China

Operation of recession and inundation in Three Gorges Reservoir (TGR) revealed a potential contribution to the migration of heavy metals in soil and fluvial systems, thus led to negative ecological impacts. The work herein investigated the concentration and speciation of three typical heavy metals (Cd, Cr and Cu) in a water-level-fluctuation zone of TGR, as well as simulated the adsorption and desorption behavior of heavy metals on soils, which aimed at elucidating the fate of heavy metals in this special area. Field investigation revealed that water level fluctuation greatly enabled the migration of heavy metals to inner or upper soil layers. Laboratory experiments showed that adsorption of Cd(II) was a chemical process and dissolved organic matters (DOM) in soils strengthened the combination of Cd(II) to soil surface which inhibited the desorption process. Cr(VI) was physically adsorbed and readily to be desorbed. DOM enabled deposition of Cr(VI) in soils. Cation exchange was dominate mechanism in Cu(II) adsorption process, whereas DOM presented positive effects on desorption of Cu(II). The results presented in this study would provide basic theory for scientific research in TGR.

Tropical climate effect on the toxic heavy metal pollutant course of road-deposited sediments

In modern society, the intense vehicle traffic and the lack of effective mitigating strategies may adversely impact freshwater systems. Road-deposited sediments (RDS) accumulate a variety of toxic substances which are transported into nature during hydrologic events, mainly affecting water bodies through stormwater runoff. The aim of this study was to evaluate the RDS metal enrichment ratio between the end of wet season and the middle of the dry season for Cd, Cr, Cu, Fe, Mn, Ni, Pb and Zn in samples from Natal, Brazil. Twenty RDS, drainage system and river sediment samples were collected in the wet and dry seasons using a stainless-steel pan, brush and spatula. In the laboratory, the samples were submitted to acid digestion and heavy metal concentrations were measured by atomic absorption spectrometry (AAS). A consistent RDS enrichment by heavy metals in dry season samples was followed by an increase in the finest particle size fraction (D < 63 μm). Maximum concentrations were 5, ND, 108, 23810, 83, ND, 77 and 150 mg kg^-1 for Cd, Cr, Cu, Fe, Mn, Ni, Pb and Zn, respectively. The RDS enrichment ratio was Cr(1.3 × ), Cu(2.6 × ), Fe(3.3 × ), Mn(1.5 × ), Pb(1.5 × ) and Zn(2.1 × ). The Geo-accumulation Index values showed that RDS were moderately polluted for Cu and slighted polluted for Zn and Pb. Principal Component Analysis (PCA) showed that the accumulation of toxic heavy metals decreased according to water flow.

Immobilization of cadmium in polluted soils by phytogenic iron oxide nanoparticles

While phytogenic nanomaterials have been successfully used to remove heavy metals in wastewater, the potential to successfully use such materials to immobilize heavy metals in soils is still unclear. In this study, phytogenic iron oxide nanoparticles (PION) were used to immobilize cadmium (Cd) in six soils. Amendment with PION effectively immobilized Cd, with a concomitant increase in the concentrations of iron oxides, soil pH and dissolved organic carbon (DOC) under both oxic and anoxic conditions. However, observed changes in soil properties and Cd fractions were different under oxic and anoxic conditions. After PION application, the exchangeable Cd fraction decreased by up to 91 and 69%, while the carbonate bound Cd fraction decreased by up to 61 and 75%, under oxic and anoxic conditions, respectively. Pearson correlation analysis revealed that under both oxic and anoxic conditions, Cd fractions were significantly and positively correlated with free iron oxide content and pH, where free iron oxide content was positively correlated with amorphous iron oxide, DOC and pH. The Cd immobilization mechanisms potentially involved either (1) formation of insoluble hydroxides at elevated pH; (2) participation of biomolecules released from PION in ligand complexation with Cd and (3) co-precipitated of Cd during the formation of iron oxides. This study provided new insights into the potential effects of PION applications for practical Cd immobilization in contaminated soils.

Machine-learning-based quantitative estimation of soil organic carbon content by VIS/NIR spectroscopy

Soil organic carbon (SOC) is an important soil property that has profound impact on soil quality and plant growth. With 140 soil samples collected from Ebinur Lake Wetland National Nature Reserve, Xinjiang Uyghur Autonomous Region of China, this research evaluated the feasibility of visible/near infrared (VIS/NIR) spectroscopy data (350-2,500 nm) and simulated EO-1 Hyperion data to estimate SOC in arid wetland regions. Three machine learning algorithms including Ant Colony Optimization-interval Partial Least Squares (ACO-iPLS), Recursive Feature Elimination-Support Vector Machine (RF-SVM), and Random Forest (RF) were employed to select spectral features and further estimate SOC. Results indicated that the feature wavelengths pertaining to SOC were mainly within the ranges of 745-910 nm and 1,911-2,254 nm. The combination of RF-SVM and first derivative pre-processing produced the highest estimation accuracy with the optimal values of Rt (correlation coefficient of testing set), RMSE t and RPD of 0.91, 0.27% and 2.41, respectively. The simulated EO-1 Hyperion data combined with Support Vector Machine (SVM) based recursive feature elimination algorithm produced the most accurate estimate of SOC content. For the testing set, Rt was 0.79, RMSE t was 0.19%, and RPD was 1.61. This practice provides an efficient, low-cost approach with potentially high accuracy to estimate SOC contents and hence supports better management and protection strategies for desert wetland ecosystems.

Analysis of the adsorption and retention models for Cd, Cr, Cu, Ni, Pb, and Zn through neural networks: selection of variables and competitive model

In this study, the neural networks are used to predict and explain the behavior of different edaphological variables in the adsorption and retention of heavy metals, both isolated and competing. A comparison with the results obtained using multiple regression, stepwise analysis, and regression trees is performed. In the neural network technique, CEC amorphous and crystallized oxides and kaolinite in the clay fraction are the most selected variables for making the optimal models, while mica and, to a lesser extent, plagioclase, are the next variables selected. Additionally, a competitive model has been considered, using simultaneously different metals. In the competitive model, the model predicts a more intense competence between Pb and Ni for the adsorption process and between Cr and Ni for the retention process.