Spatial Distribution and Mobility Assessment of Carcinogenic Heavy Metals in Soil Profiles Using Geostatistics and Random Forest, Boruta Algorithm

Integrated application of multiple indicators and geographic information system-based approaches for comprehensive assessment of environmental impacts of toxic metals-contaminated agricultural soils and vegetables

Conventional monitoring and mapping approaches are laborious, expensive, and time-consuming because they need a large number of data and consequently extensive sampling and experimental operations. Therefore, due to the growing concern about the potential of contamination of soils and agricultural products with heavy metals (HMs), a field experiment was conducted on 77 farm lands in an area of 2300 ha in the southeast of Shiraz (Iran) to investigate the source of metal contamination in the soils and vegetables and to model spatial distribution of HMs (iron, Fe; manganese, Mn; copper, Cu; zinc, Zn; cadmium, Cd; nickel, Ni, and lead, Pb) over the region using geographic information system (GIS) and geostatistical (Ordinary Kriging, OK) approaches and compare the results with deterministic approaches (Inverse Distance Weighting, IDW with different weighting power). Furthermore, some ecological and health risks indices including Pollution index (PI), Nemerow integrated pollution index (NIPI), pollution load index (PLI), degree of contamination (Cdeg), modified contamination degree (mCd), PIaverage and PIvector for soil quality, multi-element contamination (MEC), the probability of toxicity (MERMQ), the potential ecological index (RI), total hazard index (THI) and total carcinogenic risk index (TCR) based on ingestion, inhalation, and dermal exposure pathways for adults and children respectively for analyzing the noncarcinogenic and carcinogenic risks were calculated. Experimental semivariogram of the mentioned HMs were calculated and theoretical models (i.e., exponential, spherical, Gaussian, and linear models) were fitted in order to model their spatial structures and to investigate the most representative models. Moreover, principal component analysis (PCA) and cluster analysis (CA) were used to identify sources of HMs in the soils. Results showed that IDW method was more efficient than the OK approach to estimate the properties and HMs contents in the soils and plants. The estimated daily intake of metals (DIM) values of Pb and Ni exceeded their safe limits. In addition, Cd was the main element responsible for ecological risk. The PIave and PIvector indices showed that soil quality in the study area is not suitable. According to mCd values, the soils classified as ultra-high contaminated for Cu and Cd, extremely high for Zn and Pb, very high, high, and very low degree of contamination for Ni, Mn, and Fe, respectively. 36, 60, and 4 % of the sampling sites had high, medium, and low risk levels with 49, 21, and 9 % probability of toxicity, respectively. The maximum health risk index (HRI) value of 20.42 with extremely high risk for children was obtained for Ni and the HI for adults and children were 0.22 and 1.55, respectively. The THI values of Pb and Cd were the highest compared to the other HMs studied, revealing a possible non-cancer risk in children associated with exposure to these metals. The routes of exposure with the greatest influence on the THI and TCR indices were in the order of ingestion > inhalation > dermal. Therefore, ingestion, as the main route of exposure, is the route of greatest contribution to health risks. PCA analysis revealed that Fe, Mn, Cu, and Ni may originate from natural sources, while Fe was appeared to be controlled by fertilizer, and Cu primarily coming from pesticide, while Cd and Pb were mainly associated with the anthropogenic contamination, atmospheric depositions, and terrific in the urban soils. While, Zn mainly originated from fertilization. Findings are vital for developing remediation approaches for controlling the contaminants distribution as well as for monitoring and mapping the quality and health of soil resources.

Multivariate analysis applied to X-ray fluorescence to assess soil contamination pathways: case studies of mass magnetic susceptibility in soils near abandoned coal and W/Sn mines

Determining the origin and pathways of contaminants in the natural environment is key to informing any mitigation process. The mass magnetic susceptibility of soils allows a rapid method to measure the concentration of magnetic minerals, derived from anthropogenic activities such as mining or industrial processes, i.e., smelting metals (technogenic origin), or from the local bedrock (of geogenic origin). This is especially effective when combined with rapid geochemical analyses of soils. The use of multivariate analysis (MVA) elucidates complex multiple-component relationships between soil geochemistry and magnetic susceptibility. In the case of soil mining sites, X-ray fluorescence (XRF) spectroscopic data of soils contaminated by mine waste shows statistically significant relationships between magnetic susceptibility and some base metal species (e.g., Fe, Pb, Zn, etc.). Here, we show how qualitative and quantitative MVA methodologies can be used to assess soil contamination pathways using mass magnetic susceptibility and XRF spectra of soils near abandoned coal and W/Sn mines (NW Portugal). Principal component analysis (PCA) showed how the first two primary components (PC-1 + PC-2) explained 94% of the sample variability, grouped them according to their geochemistry and magnetic susceptibility in to geogenic and technogenic groups. Regression analyses showed a strong positive correlation (R2 > 0.95) between soil geochemistry and magnetic properties at the local scale. These parameters provided an insight into the multi-element variables that control magnetic susceptibility and indicated the possibility of efficient assessment of potentially contaminated sites through mass-specific soil magnetism.

Assessment of microelement ecotoxicity in fen for ecological state monitoring

Wetlands, including bogs, fens, and swamps, play a crucial role in maintaining ecological balance by absorbing pollutants. They also conserve biodiversity and serve as breeding and migration sites for living organisms whose treated by pollutants entering to the wetland ecosystems. Pollutants entering wetland ecosystems can have detrimental effects on these important functions. The article introduces the method of toxicity assessment of microelements used in the environmental condition monitoring of the Ob River's floodplain fen (Tomsk Oblast, Russia). The impact of freshwater species (PAF m3day/kgemitted) is evaluated by calculating the Life Cycle Assessment Impact score for Be, V, Cr, Mn, Fe, Cu, Zn, As, Sr, Mo, Pb, Cd, Sb, Ba, and Tl at distances of 40, 100, and 160 m from the wastewater discharge site. The study considers the elemental composition and total volume of water from various areas within the research site for assessing freshwater ecotoxicity. 12 out of 15 investigated trace elements have the greatest impact on the freshwater system in the zone of 160 m from the site of anthropogenic impact on the water body. The sampling areas can be ranked based on their ∑IS value, with IS160 = 1.3E+11, followed by IS100 = 7.5E+10, and IS40 = 1.5E+10 [PAF m3day/kgemitted].

An integrated approach for quantifying trace metal sources in surface soils of a typical farmland in the three rivers plain, China

The presence of trace metals (TMs) in agricultural soil has garnered considerable attention due to their potential migration into crops, posing a significant risk to human health. In this study, we examined the concentrations of eight trace metals (Cd, Cr, Cu, Hg, Mn, Ni, Pb, and Zn) in the soil and investigated various soil physicochemical characteristics in the Three Rivers Plain region, China. The assessment of the geoaccumulation index (Igeo) for the mean concentration of all trace metals indicated that the soils were generally free from significant TM pollution. However, a noteworthy finding emerged in relation to Hg, where the maximum Igeo value suggested moderate pollution levels. Kriging prediction results further indicated that approximately 1.55% of the study area might be impacted by Hg pollution. Moreover, it is prudent to direct attention towards Cd, Cr, Cu, Mn, and Ni, as their Igeo values revealed that the region with the highest concentrations of these metals ranged from unpolluted to moderately polluted. This study employed a comprehensive approach, utilizing the Self-Organizing Map (SOM), Kriging spatial distribution, and the Positive Matrix Factorization (PMF) model to identify the sources of TMs in agricultural soil. The results unveiled that the primary contributors to TM presence were the natural parental materials, alongside industrial activities such as coal mining and coal plant operations, as well as agricultural practices. These findings provide foundational insights for future management strategies in the Three Rivers Plain, aiming to enhance agricultural productivity and promote sustainability.

Exploring biochar and fishpond sediments potential to change soil phosphorus fractions and availability

Phosphorus (P) availability in soil is paradoxical, with a significant portion of applied P accumulating in the soil, potentially affecting plant production. The impact of biochar (BR) and fishpond sediments (FPS) as fertilizers on P fixation remains unclear. This study aimed to determine the optimal ratio of BR, modified biochar (MBR), and FPS as fertilizer replacements. A pot experiment with maize evaluated the transformation of P into inorganic (Pi) and organic (Po) fractions and their contribution to P uptake. Different percentages of FPS, BR, and MBR were applied as treatments (T1-T7), T1 [(0.0)], T2 [FPS (25.0%)], T3 [FPS (25.0%) + BR (1%)], T [FPS (25%) +MBR (3%)], T5 [FPS (35%)], T6 [FPS (35%) +BR (1%)], and T7 [FPS (35%) + MBR (1%)]. Using the modified Hedley method and the Tiessen and Moir fractionation scheme, P fractions were determined. Results showed that various rates of MBR, BR, and FPS significantly increased labile and moderately labile P fractions (NaHCO3-Pi, NaHCO3-Po, HClD-Pi, and HClC-Pi) and residual P fractions compared with the control (T1). Positive correlations were observed between P uptake, phosphatase enzyme activity, and NaHCO3-Pi. Maximum P uptake and phosphatase activity were observed in T6 and T7 treatments. The addition of BR, MBR, and FPS increased Po fractions. Unlike the decline in NaOH-Po fraction, NaHCO3-Po and HClc-Po fractions increased. All Pi fractions, particularly apatite (HClD-Pi), increased across the T1-T7 treatments. HClD-Pi was the largest contributor to total P (40.7%) and can convert into accessible P over time. The T5 treatment showed a 0.88% rise in residual P. HClD-Pi and residual P fractions positively correlated with P uptake, phosphatase activity, NaOH-Pi, and NaOH-Po moderately available fractions. Regression analysis revealed that higher concentrations of metals such as Ca, Zn, and Cr significantly decreased labile organic and inorganic P fractions (NaHCO3-Pi, R 2 = 0.13, 0.36, 0.09) and their availability (NaHCO3-Po, R 2 = 0.01, 0.03, 0.25). Excessive solo BR amendments did not consistently increase P availability, but optimal simple and MBR increased residual P contents in moderately labile and labile forms (including NaOH-Pi, NaHCO3-Pi, and HClD-Pi). Overall, our findings suggest that the co-addition of BR and FPS can enhance soil P availability via increasing the activity of phosphatase enzyme, thereby enhancing plant P uptake and use efficiency, which eventually maintains the provision of ecosystem functions and services.

A Two-Step Simulated Annealing Algorithm for Spectral Data Feature Extraction

To address the shortcomings in many traditional spectral feature extraction algorithms in practical application of low modeling accuracy and poor stability, this paper introduces the "Boruta algorithm-based local optimization process" based on the traditional simulated annealing algorithm and proposes the "two-step simulated annealing algorithm (TSSA)". This algorithm combines global optimization and local optimization. The Boruta algorithm ensures that the feature extraction results are all strongly correlated with the dependent variable, reducing data redundancy. The accuracy and stability of the algorithm model are significantly improved. The experimental results show that compared with the traditional feature extraction method, the accuracy indexes of the inversion model established by using the TSSA algorithm for feature extraction were significantly improved, with the determination coefficient R² of 0.9654, the root mean square error (RMSE) of 3.6723 μg/L, and the mean absolute error (MAE) of 3.1461 μg/L.

Predicting the dust events frequency around a degraded ecosystem and determining the contribution of their controlling factors using gradient boosting-based approaches and game theory

This study was aimed to evaluate the performance of gradient boosting machine (GBM) and extreme gradient boosting (XGB) models with linear, tree, and DART boosters to predict monthly dust events frequency (MDEF) around a degraded wetland in southwestern Iran. The monthly required data for a long-term period from 1988 to 2018 were obtained through ground stations and satellite imageries. The best predictors were selected among the eighteen climatic, terrestrial, and hydrological variables based on the multicollinearity (MC) test and the Boruta algorithm. The models' performance was evaluated using the Taylor diagram. Game theory (i.e., SHAP values: SHV) was used to determine the contribution of factors controlling MDEF in different seasons. Mean wind speed, maximum wind speed, rainfall, standardized precipitation evapotranspiration index (SPEI), soil moisture, erosive winds frequency, vapor pressure, vegetation area, water body area, and dried bed area of the wetland were confirmed as the best variables for predicting the MDEF around the studied wetland. The XGB-linear and XGB-tree showed a higher capability in predicting the MDEF variations in the summer and spring seasons. However, the XGB-Dart yielded better than XGB-linear and XGB-tree models in predicting the MDEF during the autumn and winter seasons. Rainfall (SHV = 1.6), surface water discharge (SHV = 2.4), mean wind speed (SHV = 10.1), and erosive winds frequency (SHV = 1.6) had the highest contribution in predicting the target variable in winter, spring, summer, and autumn, respectively. These findings demonstrate the effectiveness of the gradient boosting-based approaches and game theory in determining the factors affecting MDEF around a destroyed international wetland in southwestern Iran and the findings may be used to diminish their impacts on residents of this region of Iran.

Soil parameters affecting the levels of potentially harmful metals in Thessaly area, Greece: a robust quadratic regression approach of soil pollution prediction

The behavior and possible contamination risk due to the presence of potentially harmful metals (PHM) were studied based on 2250 soil samples that were collected in a 5-year period (2013-2017) from the plain of Thessaly (prefectures of Karditsa, Trikala, and Larissa). The vertical distribution of metals was also investigated from sample profiles at three depths 0-30, 30-60, and 60-90cm. The soils of the sampling belong to four taxonomy soil orders that are dominant in the studied area (Alfisols, Inceptisols, Endisols, and Vertisols). In a novel approach, robust quadratic regression analysis on multiple variables was used to define prediction models of the concentrations of two metals: Fe which is an essential metal and the toxic Cd. Linear and quadratic regression formulae were estimated based on the iteratively reweighted least squares robust regression approach in an effort to eliminate the impact of the outliers. These formulae define how several soil properties affect the distribution of the considered metals in each soil order. The evaluation of the estimated regression equations based on the R² metric indicates that they constitute a useful, reliable, and valuable tool for managing, describing, and predicting the pollution in the studied area.

Metal Accumulation and Biomass Production in Young Afforestations Established on Soil Contaminated by Heavy Metals

The restoration of forest ecosystems on metal-contaminated sites can be achieved whilst producing valuable plant biomass. Here, we investigated the metal accumulation and biomass production of young afforestations on contaminated plots by simulating brownfield site conditions. On 16 3-m² plots, the 15 cm topsoil was experimentally contaminated with Zn/Cu/Pb/Cd = 2854/588/103/9.2 mg kg⁻¹ using smelter filter dust, while 16 uncontaminated plots (Zn/Cu/Pb/Cd = 97/28/37/< 1) were used as controls. Both the calcareous (pH 7.4) and acidic (pH 4.2) subsoils remained uncontaminated. The afforestations consisted of groups of conifers, deciduous trees, and understorey plants. During the four years of cultivation, 2254/86/0.35/10 mg m⁻² Zn/Cu/Pb/Cd were extracted from the contaminated soils and transferred to the aboveground parts of the plants (1279/72/0.06/5.5 mg m⁻² in the controls). These extractions represented 3/2/3% of the soluble soil Zn/Cu/Cd fractions. The conifers showed 4–8 times lower root-to-shoot translocation of Cu and Zn than the deciduous trees. The contamination did not affect the biomass of the understorey plants and reduced that of the trees by 23% at most. Hence, we conclude that the afforestation of brown field sites with local tree species is an interesting option for their reclamation from an ecological as well as economic perspective.

A deep learning approach for real-time crash prediction using vehicle-by-vehicle data

In road safety, real-time crash prediction may play a crucial role in preventing such traffic events. However, much of the research in this line generally uses data aggregated every five or ten minutes. This article proposes a new image-inspired data architecture capable of capturing the microscopic scene of vehicular behavior. In order to achieve this, an accident-prediction model is built for a section of the Autopista Central urban highway in Santiago, Chile, based on the concatenation of multiple-input Convolutional Neural Networks, using both the aggregated standard traffic data and the proposed architecture. Different oversampling methodologies are analyzed to balance the training data, finding that the Deep Convolutional Generative Adversarial Networks technique with random undersampling presents better results when generating synthetic instances that permit maximizing the predictive performance. Computational experiments suggest that this model outperforms other traditional prediction methodologies in terms of AUC and sensitivity values over a range of false positives with greater applicability in real life.

Statistical analysis of active fire remote sensing data: examples from South Asia

Active fires emit aerosols and greenhouse gases in the atmosphere. In this paper, the behavior of active fires over a period of 1 year in Nepal, Bhutan, and Sri Lanka is studied using spatial statistics. In these countries, these fires are mainly forest and vegetation fires; they wreak havoc to the environment by damaging flora and fauna and emitting toxic gases. This study is based on data acquired through remote sensing of data acquisition platform, NASA's MODIS. Spatial statistics is used here to study the incidence of such fires with respect to geographical location. The behaviors of parameters of various autoregressive models like Spatial Durban Model, Spatial Lag Model, Spatial Error Model, Manski Model, and Kelegian Prucha Model are minutely analyzed. The best model with the highest pseudo R² is selected. The spatial behavior of the fire radiative power (FRP) for the three countries is also predicted using spatial interpolation and kriging. The burning potential of vegetations in unsampled areas is envisaged by thus predicting FRP. This study gives a country-wise perspective to the behavior of fire; this is with reference to South Asia. It holds a great significance for countries of the developing world which lack a strong backbone of good-quality official records. Through the statistical analyses of data collected by such platforms, important information on impact of forest fires can be indirectly assessed.

An integrated approach for spatial distribution of potentially toxic elements (Cu, Pb and Zn) in topsoil

In this study, statistical analysis and spatial distribution were performed to compare raw data and centred log-ratio (clr) transformed data of three copper (Cu), lead (Pb), and zinc (Zn) potentially toxic elements (PTEs) concentration for 550 surface soil samples in Khuzestan plain. The results of both approaches showed that classical univariate analysis and compositional data analysis are essential to find the real structure of data and clarify its different aspects. Results also indicated that spatial distributions of raw data and clr-transformed data were completely different in three studied metals. Raw data necessarily shows the effects of anthropogenic activities and needs an additional evaluation of human health risk assessment for these three studied elements. Data obtained from clr-coefficient maps also demonstrated the role of geological processes in the distribution pattern of potentially toxic elements (PTEs). To improve the understanding of the implications for PTE pollution and consequences for human health, a RGB colour composite map was produce to identify the potential origin of PTEs from areas with higher than typical baseline concentrations.

Detecting lane change maneuvers using SHRP2 naturalistic driving data: A comparative study machine learning techniques

Lane change has been recognized as a challenging driving maneuver and a significant component of traffic safety research. Developing a real-time continuous lane change detection system can assist drivers to perform and deal with complex driving tasks or provide assistance when it is needed the most. This study proposed trajectory-level lane change detection models based on features from vehicle kinematics, machine vision, roadway characteristics, and driver demographics under different weather conditions. To develop the models, the SHRP2 Naturalistic Driving Study (NDS) and Roadway Information Database (RID) datasets were utilized. Initially, descriptive statistics were utilized to investigate the lane change behavior, which revealed significant differences among different weather conditions for most of the parameters. Six data fusion categories were introduced for the first time, considering different data availability. In order to select relevant features in each category, Boruta, a wrapper-based algorithm was employed. The lane change detection models were trained, validated, and comparatively evaluated using four Machine Learning algorithms including Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), and eXtrem Gradient Boosting (XGBoost). The results revealed that the highest overall detection accuracy was found to be 95.9 % using the XGBoost model when all the features were included in the model. Moreover, the highest overall detection accuracy of 81.9 % using the RF model was achieved considering only vehicle kinematics-based features, indicating that the proposed model could be utilized when other data are not available. Furthermore, the analysis of the impact of weather conditions on lane change detection suggested that incorporating weather could improve the accuracy of lane change detection. In addition, the analysis of early lane change detection indicated that the proposed algorithm could predict the lane changes within 5 s before the vehicles cross the lane line. The developed detection models could be used to monitor and control driver behavior in a Cooperative Automated Vehicle environment.

Estimating Urban Vegetation Biomass from Sentinel-2A Image Data

Urban vegetation biomass is a key indicator of the carbon storage and sequestration capacity and ecological effect of an urban ecosystem. Rapid and effective monitoring and measurement of urban vegetation biomass provide not only an understanding of urban carbon circulation and energy flow but also a basis for assessing the ecological function of urban forest and ecology. In this study, field observations and Sentinel-2A image data were used to construct models for estimating urban vegetation biomass in the case study of the east Chinese city of Xuzhou. Results show that (1) Sentinel-2A data can be used for urban vegetation biomass estimation; (2) compared with the Boruta based multiple linear regression models, the stepwise regression models—also multiple linear regression models—achieve better estimations (RMSE = 7.99 t/hm2 for low vegetation, 45.66 t/hm2 for broadleaved forest, and 6.89 t/hm2 for coniferous forest); (3) the models for specific vegetation types are superior to the models for all-type vegetation; and (4) vegetation biomass is generally lowest in September and highest in January and December. Our study demonstrates the potential of the free Sentinel-2A images for urban ecosystem studies and provides useful insights on urban vegetation biomass estimation with such satellite remote sensing data.

Comparison of methods for addressing the point-to-area data transformation to make data suitable for environmental, health and socio-economic studies

Soil lead (Pb) provides an important exposure pathway to the human body through soil ingestion and dust inhalation and is closely associated with human health as well as social behaviour. The challenge of transforming different spatial supports arises when linking point data (Pb concentration) to areal data (health status or social behaviour). A detailed review of methodologies for integrating point and areal data has been carried out. Among a number of methodologies, eight methods: (1) average, (2) median, (3) centroids inverse distance weighted (IDW), (4) average block IDW, (5) median block IDW, (6) centroids ordinary kriging (OK), (7) average block OK and (8) median block OK, have been compared using Pb data set in the Greater London Authority (GLA) area. The results indicated that the method of median block IDW was recommended for further investigation of the relationship between Pb concentration and socio-economic factors in the ward-level of the GLA area. The reasons were (i) spatial interpolations were useful for predicting unobserved values when simple average and median could not work in the locations where there were no samples collected in some areal units; (ii) the median value was more suitable than the average value for a skewed data set; (iii) the block method reduced estimation error and provided more representative values of areal units than the centroid method; (iv) IDW reserved more spatial variation than OK, containing more local maxima (hotspot) and local minima. Despite that it is still hard to decide the optimal method, this study has highlighted the point-to-area transformation issue and provided valuable examples to compare the different methods.

Distribution Characteristics and Pollution Assessment of Soil Heavy Metals under Different Land-Use Types in Xuzhou City, China

Xuzhou, as a mining city in China, has been experiencing 130 years of coal mining and processing. To explore the spatial distribution characteristics and pollution status of soil heavy metals (Cr, Cd, As, Hg, Zn, and Pb) under different land-use types, a total of 2697 topsoil samples were collected in all of the areas (except for water) of Xuzhou in 2016. Overall, the mean concentrations of Cr (70.266 mg/kg), Cd (0.141 mg/kg), As (10.375 mg/kg), Hg (0.036 mg/kg), Zn (64.788 mg/kg), and Pb (24.84 mg/kg) in Xuzhou soils were lower than the environmental quality standard for soils (GB15618-1995). However, the mean concentrations of Cr, Hg, and Pb exceeded their corresponding background values, with the mean concentration of Hg being almost three times its background value. For different land-use types, the highest mean concentration of Cr was concentrated in grassland soils. The mean concentrations of Cd, As, Zn, and Pb in mining area soils were higher than those in the other soils. The mean concentration of Hg was the highest in the built-up area soils. Based on the potential ecological risk assessment, the forestland, garden land, grassland, and others were at low and moderate risk levels, the farmland and mining area were at low, moderate, and high risk levels, and the built-up area was at various risk levels in Xuzhou. There was a significant positive correlation between Cr, Pb, and Hg concentrations and the corresponding organic carbon contents in the farmland, built-up area, garden land, forestland, and other soils ( p < 0.01 ). A high degree of correlation was found between Cr and Hg concentrations, as well as organic carbon contents in grassland soils, with values of p < 0.05 and p < 0.01 , respectively. An obvious correlation could be seen between Hg concentrations and organic carbon contents in mining area soils ( p < 0.01 ).