Modelling bioaccumulation of heavy metals in soil-crop ecosystems and identifying its controlling factors using machine learning☆
Graphical abstract
Introduction
Soil plays a critical role in ecosystems and is the basic resource for food production, however, soil is threatened by many pollutants, among which heavy metals (HMs) are of great concern (Hu and Cheng, 2013; Zhao et al., 2014; Shao et al., 2018; Hu et al., 2019; Peng et al., 2019). In contrast to organic matter, HMs can reside in soils for long periods of time (Hu et al., 2017a; Jia et al., 2019). The wide distribution of HM-polluted soils has resulted in profound environmental and health issues (Brus et al., 2009; Hu et al., 2017b; Hu et al., 2020). HMs in soils can be slowly but consistently accumulated in the human body via different pathways such as inhalation, ingestion, and dermal contact (De Miguel et al., 2007; Wei and Yang, 2010; Hui et al., 2016). Moreover, the intake of HMs through soil-crop ecosystems has proven to be an important pathway for human exposure to HMs (Liu et al., 2007; Qian et al., 2010; Liu et al., 2013).
In recent four decades, China has experienced rapid economic growth and has undergone a significant transformation from the traditional agriculture-based economy to a manufacturing-based economy (Cheng and Hu, 2010). Industrial development and fast urban expansion have resulted in sharp increases in the amount of sewage sludge produced by industrial, transportation-related, and municipal activities nationwide (Cheng and Hu, 2012). The Yangtze River Delta (YRD), located in Eastern China, is the most developed area in the country and yields 23.6% of the national gross domestic product (Yan et al., 2018). With a population of more than 150 million, the YRD is one of the most densely populated regions in China (Shao et al., 2018; Hu et al., 2017b). It is also an important production area for many important agricultural products such as rice, tea, vegetables, and certain fruits. Many studies have revealed significant accumulation of HMs in soil and crops in the YRD region (Chen and Pu, 2007; Hu et al., 2017c; Fei et al., 2019; Xia et al., 2019). The accumulation of HMs in soil and their subsequent bioaccumulation through the food chain poses great potential health risks to citizens in the YRD. Therefore, it is of great importance to explore HM bioaccumulation in soil-crop systems and identify its controlling factors.
Bioaccumulation of HMs in soil by plants is mainly governed by the uptake mechanism, the physical and chemical properties of the soil, the chemical characteristics of the HMs, physiological characteristics of the plants, and other environmental factors (Peijnenburg et al., 2007). Previous studies analysing the factors affecting the bioaccumulation of HMs in soil-plant systems have mainly focused on these aforementioned factors and have employed traditional statistical analyses (Jin et al., 2005; Liu et al., 2017; Liu et al., 2018). These models only consider quantitative variables, focusing mostly on critical soil properties such as soil pH, soil organic matter content (SOM), and soil HM content. However, they cannot be used to quantitatively analyse the effect of qualitative variables such as soil type and soil parent materials which have also been shown to exert substantial effects on HM accumulation in soil-crop systems. Few studies have taken different factors into consideration or quantitatively analysed the detailed effects of each potential factor and the spatial characteristics of bioaccumulation of different HMs. Further, few researchers have succeeded in building a comprehensive model that is able to predict bioaccumulation factors (BAFs) of HMs in soil-crop systems. Moreover, the methods used in previous studies were unable to identify the importance of the different variables in the modelling process, which is vital for decision-makers in identifying the essential factors controlling HM pollution control and remediation in soils. Aiming to fill this research gap, in this study, we used and compared three kinds of widely used machine learning methods, namely the gradient-boosted model (GBM) (Friedman, 2002), random forest (RF) (Liaw and Wiener., 2002), and the classic linear statistic model referred to as the generalised linear model (GLM) (Nelder and Wedderburn., 1972), to predict the BAFs of different HMs and define the quantitative effects of different factors on the bioaccumulation of eight different HMs. Therefore, there were three main aims of this study. The first was to investigate the HM content and the BAFs of each HM in soil-plant ecosystems. The second objective was to build and compare the models constructed using the GBM, RF, and GLM methods to be used for predicting the BAFs of HMs in soil-plant ecosystems, and to identify the optimal method. The third aim was to identify potential controlling factors in the transfer of HMs in soil-crop ecosystems. This study could contribute to the regulation of HM contamination in soil-crop ecosystems and toward guaranteeing the safety of agricultural products.
Section snippets
Study area
The region under study (28°51′–30°33′N and 120°55′–122°16′E) lies at the southern part of the YRD, the most developed region in China (Fig. 1). The study region has a population of roughly 6 million people and an approximate area of 9800 km2. It is well known for industrial and commercial activities as well as foreign trade. It of interest to note that the area is home to the largest international port in the world. In recent decades, the studied region has been experiencing rapid and intensive
Summary statistics of HMs in soil-crop ecosystems
The basic descriptive statistics of HM contents in the soil samples are listed in Table S5. The average contents of HMs in soil followed the order Zn (111.16 mg kg−1) > Cr (69.64 mg kg−1) > Pb (42.89 mg kg−1) > Cu (35.50 mg kg−1) > Ni (29.99 mg kg−1) > As (6.67 mg kg−1) > Hg (0.31 mg kg−1) > Cd (0.20 mg kg−1). The contents of all HMs in soil were higher than their background levels in soils (Table S5) but significantly lower than the national limit values (Table S6) (CNEMC., 1990). The
HM content in soil-crop systems
The contents of the eight HMs targeted in this study in soil were significantly higher than the corresponding background values in soil in the research area (Table S5), which clearly demonstrates accumulation caused by anthropogenic contributions. For HMs in plants, there is still no complete national standard on the regulation of HM concentrations in different kinds of crops. This makes it difficult to assess the levels of HMs in crops.
In the research area studied, crops more easily absorbed
Conclusions
In this study, we analysed HM contents in 1822 paired soil-crop samples. The GBM, RF, and GLM models were adopted to predict the BAFs of different HMs in soil-crop ecosystems based on 13 auxiliary variables, and the importance of the different variables in the models were quantified. The method used in this study could contribute to the prediction of HM contents in crops based on the HM contents in soil and other available information about the soil. This could result in significant savings in
CRediT authorship contribution statement
Bifeng Hu: Conceptualization, Data curation, Formal analysis, Methodology, Writing - original draft, Writing - review & editing. Jie Xue: Data curation. Yin Zhou: Formal analysis, Writing - original draft. Shuai Shao: Data curation, Formal analysis. Zhiyi Fu: Formal analysis, Methodology. Yan Li: Supervision. Songchao Chen: Methodology, Writing - review & editing. Lin Qi: Data curation. Zhou Shi: Conceptualization, Funding acquisition, Supervision, Writing - original draft, Writing - review &
Declaration of competing interest
The authors have declared that no competing interests exist.
Acknowledgment
This work was supported by the National Key Research and Development Program of China (2018YFC1800105) and the Key Research and Development Project of Zhejiang Province, China (2015C02011). We also acknowledge the support received by Bifeng Hu from the China Scholarship Council (under grant agreement No. 201706320317) for 3 years’ Ph.D. study in INRA and Orléans University.
References (81)
- et al.
Effects of short-term pH fluctuations on cadmium, nickel, lead, and zinc availability to ryegrass in a sewage sludge-amended field
Chemosphere
(2008) - et al.
Biochar soil amendment as a solution to prevent Cd-tainted rice from China: results from a cross-site field experiment
Ecol. Eng.
(2013) - et al.
Effects of biochar on availability and plant uptake of heavy metals–A meta-analysis
J. Environ. Manag.
(2018) - et al.
Risk-based evaluation of the exposure of children to trace elements in playgrounds in Madrid (Spain)
Chemosphere
(2007) - et al.
Improved heavy metal mapping and pollution source apportionment in Shanghai City soils using auxiliary information
Sci. Total Environ.
(2019) Stochastic gradient boosting
Comput. Stat. Data Anal.
(2002)- et al.
Multiple factors impact the contents of heavy metals in vegetables in high natural background area of China
Chemosphere
(2017) - et al.
Selection and breeding of plant cultivars to minimize cadmium accumulation
Sci. Total Environ.
(2008) - et al.
Integrated GIS and multivariate statistical analysis for regional scale assessment of heavy metal soil contamination: a critical review
Environ. Pollut.
(2017) - et al.
The challenges and solutions for cadmium-contaminated rice in China: a critical review
Environ. Int.
(2016)
Identifying heavy metal pollution hot spots in soil-rice systems: a case study in South of Yangtze River Delta, China
Sci. Total Environ.
Composite assessment of human health risk from potentially toxic elements through multiple exposure routes: a case study in farmland in an important industrial city in East China
J. Geochem. Explor.
A methodological framework for identifying potential sources of soil heavy metal pollution based on machine learning: a case study in the Yangtze Delta, China
Envrion. Pollut.
Lead contamination in tea garden soils and factors affecting its bioavailability
Chemosphere
Mobilization of heavy metals and arsenic in polluted wetland soils and its dependence on dissolved organic matter
Sci. Total Environ.
Bioavailability and plant accumulation of heavy metals and phosphorus in agricultural soils amended by long-term application of sewage sludge
Chemosphere
Concentration and transportation of heavy metals in vegetables and risk assessment of human exposure to bioaccessible heavy metals in soil near a waste-incinerator site, South China
Sci. Total Environ.
Human health risk assessment of heavy metals in soil-vegetable system: a multi-medium analysis
Sci. Total Environ.
Assessment of the bioavailability, bioaccessibility and transfer of heavy metals in the soil-grain-human systems near a mining and smelting area in NW China
Sci. Total Environ.
Cadmium accumulation in edible flowering cabbages in the Pearl River Delta, China: critical soil factors and enrichment models
Environ. Pollut.
Accumulation of heavy metals from contaminated soil to plants and evaluation of soil remediation by vermiculite
Chemosphere
Heavy metals in urban soils: a case study from the city of Palermo (Sicily), Italy
Sci. Total Environ.
Accumulation of total mercury and methylmercury in rice plants collected from different mining areas in China
Environ. Pollut.
Monitoring metals in terrestrial environments within a bioavailability framework and a focus on soil extraction
Ecotoxicol. Environ. Saf.
Estimating soil salinity from remote sensing and terrain data in southern Xinjiang Province, China
Geoderma
Mapping soil organic matter contents at field level with Cubist, Random Forest and kriging
Geoderma
Concentrations of cadmium, lead, mercury and arsenic in Chinese market milled rice and associated population health risk
Food Contr.
Heavy metal hyperaccumulating plants: how and why do they do it? And what makes them so interesting?
Plant Sci.
Multivariate and geostatistical analyses of the spatial distribution and sources of heavy metals in agricultural soil in Dehui, Northeast China
Chemosphere
Effects of Pb on the oxidative stress and antioxidant response in a Pb bioaccumulator plant Vallisneria natans
Ecotoxicol. Environ. Saf.
A review of heavy metal contaminations in urban soils, urban road dusts and agricultural soils from China
Microchem. J.
Zn, Ni, Mn, Cr, Pb and Cu in soil-tea ecosystem: the concentrations, spatial relationship and potential control
Chemosphere
The influence of bioavailable heavy metals and microbial parameters of soil on the metal accumulation in rice grain
Chemosphere
Comparative proteomic analysis provides new insights into cadmium accumulation in rice grain under cadmium stress
J. Hazard Mater.
Cadmium in soil–rice system and health risk associated with the use of untreated mining wastewater for irrigation in Lechang, China
Agric. Water Manag.
Assessing cadmium exposure risks of vegetables with plant uptake factor and soil property
Environ. Pollut.
Accumulation, spatio-temporal distribution, and risk assessment of heavy metals in the soil-corn system around a polymetallic mining area from the Loess Plateau, northwest China
Geoderma
The influence of pH and organic matter content in paddy soil on heavy metal availability and their uptake by rice plants
Environ. Pollut.
Bioavailability and soil-to-crop transfer of heavy metals in farmland soils: a case study in the Pearl River Delta, South China
Environ. Pollut.
Heavy metal contaminations in a soil–rice system: identification of spatial dependence in relation to soil properties of paddy fields
J. Hazard Mater.
Cited by (139)
Predicting the efficiency of arsenic immobilization in soils by biochar using machine learning
2025, Journal of Environmental Sciences (China)Comparative analysis of different machine learning algorithms for predicting trace metal concentrations in soils under intensive paddy cultivation
2024, Computers and Electronics in AgricultureSpatial distribution prediction of soil heavy metals based on sparse sampling and multi-source environmental data
2024, Journal of Hazardous Materials
- ☆
This paper has been recommended for acceptance by Wen-Xiong Wang.