Abstract
Estimating heavy metal concentrations in soil-rice systems is of great significance to identify the factors controlling heavy metal transfer in soil-crop ecosystems. Recent research utilizes the advantage of convolutional calculations to extract and learn complicated information from 17 environmental covariates in rice and achieve promising results. However, as the complexity and interconnectivity in soil-crop ecosystem, just relying on convolutional calculations and a deep network structure is far from enough. The data processed by traditional deep learning technologies even with convolutional calculations are limited to Euclidean space; these architectures do not have the ability to extract information from the relationships in graph structures, which may contain rich information. Thus, in this paper, we try to integrate graph information into convolutional calculations for heavy metal prediction and propose a model named ConvGNN-HM. ConvGNN-HM combines the advantages of graph learning and convolutional calculations to predict heavy metal concentrations in a soil-rice system with analysis of 17 environmental factors. For comparison, we conduct an experiment to compare ConvGNN-HM with techniques with convolutional neural networks, multilayer perceptron, back-propagation neural networks, support vector machine, random forest, Bayesian ridge regression, and multiple linear regression. The experimental results illustrate that ConvGNN-HM got the best prediction values; the R2 values of ConvGNN-HM for cadmium (Cd), plumbum (Pb), chromium (Cr), arsenic (As), and hydrargyrum (Hg) in rice were 0.84, 0.75, 0.79, 0.49, and 0.83, respectively, and the MAE values were also acceptable. We further conduct sensitivity analysis to demonstrate the stability and robustness of ConvGNN-HM. This study demonstrates the usefulness of combining graph learning and convolutional calculations in the prediction of heavy metal concentrations and provides a new perspective to build multidimensional and multi-scale complex ecosystem models.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The data that support the findings of this study are available from “Risk assessment Laboratory for Environmental Factors of Agro-product Quality Safety, Ministry of Agriculture and villages (Changsha),” but restrictions apply to the availability of these data. The data were used under license for the current study, so they are not publicly available. However, data are available from the authors upon reasonable request and with permission of “Risk assessment Laboratory for Environmental Factors of Agro-product Quality Safety, Ministry of Agriculture and villages (Changsha).”
References
Alizamir M, Sobhanardakani S (2017) Predicting arsenic and heavy metals contamination in groundwater resources of Ghahavand plain based on an artificial neural network optimized by imperialist competitive algorithm. Environ Health Eng Manag 4:225–231
Bhagat SK, Tran TM, Yaseen ZM (2020) Heavy metal contamination prediction using ensemble model: case study of bay sedimentation. Australia J Hazard Mater 403:123492
Bhagat SK, Paramasivan M, Al-Mukhtar M, Tiyasha T, Pyrgaki K, Tung TM, Yaseen ZM (2021) Prediction of lead (Pb) adsorption on attapulgite clay using the feasibility of data intelligence models. Environ Sci Pollut Res 28:31670–31688
Blanco CMG, Gomez VMB, Crespo P, Ließ M (2018) Spatial prediction of soil water retention in a Paramo landscape: methodological insight into machine learning using random forest. Geoderma 316:100–114
Cao WQ, Zhang C (2020) A collaborative compound neural network model for soil heavy metal content prediction. IEEE Access 8:129497–129509
Carey AM, Scheckel KG, Lombi E, Newville M, Choi Y, Norton GJ, Charnock JM, Feldmann J, Price AH, Meharg AA (2010) Grain unloading of arsenic species in rice. Plant Physiol 152:309–319
Chen HY, Yuan XY, Li TY, Hu S, Ji JF, Wang C (2016) Characteristics of heavy metal transfer and their influencing factors in different soil-crop systems of the industrialization region, China. Ecotox Environ Safe 126:193–201
Cheng FY, Liu SL, Yin YJ, Zhang YQ, Zhao QH, Dong SK (2017) Identifying trace metal distribution and occurrence in sediments, inundated soils, and non-flooded soils of a reservoir catchment using self-organizing maps, an artificial neural network method. Environ Sci Pollut Res 24:19992–20004
China National Environmental Monitoring Centre (CNEMC) (2017) Technical regulations on sample collection, circulation, preparation and preservation of agricultural products (in Chinese)
Fakhri Y, Khaneghah AM, Conti GO, Ferrante M, Khezri A, Darvishi A, Ahmadi M, Hasanzadeh V, Rahimizadeh A, Keramati H, Moradi B, Amanidaz N (2018) Probabilistic risk assessment (Monte Carlo simulation method) of Pb and Cd in the onion bulb (Allium cepa) and soil of Iran. Environ Sci Pollut Res 25:30894–30906
Han J, Morag C (1995) The influence of the sigmoid function parameters on the speed of backpropagation learning. Lect Notes Comput Sci 930:195–201
Handan UO, Tuba GB, Ercan G, Baris OH, Mehmet C, Hakan S (2020) Application of artificial neural networks to predict the heavy metal contamination in the Bartin River. Environ Sci Pollut Res. https://doi.org/10.1007/s11356-020-10156-w
Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
Hu BF, Xue J, Zhou Y, Shao S, Fu ZY, Li Y, Chen SC, Qi L, Shi Z (2020) Modelling bioaccumulation of heavy metals in soil-crop ecosystems and identifying its controlling factors using machine learning. Environ Pollut 262:114308
Ke B, Nguyen H, Bui XN, Bui HB, Nguyen TT (2021) Prediction of the sorption efficiency of heavy metal onto biochar using a robust combination of fuzzy C-means clustering and back-propagation neural network. J Environ Manag 293:112808
Khan A, Khan S, Khan MA, Qamar Z, Waqas M (2015) The uptake and bioaccumulation of heavy metals by food plants, their effects on plants nutrients, and associated health risk: a review. Environ Sci Pollut Res 22:13772–13799
Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. International Conference on Learning Representations 2015 (ICLR 2015) abs/1412.6980
Lecun Y, Bengio Y, Hinton GE (2015) Deep learning. Nature 521(7553):436
Li SM, Pan XQ (2021) A computational drug repositioning model based on hybrid similarity side information powered graph neural network. Future Gener Comput Syst 125:24–31
Li PF, Hua P, Gui DW, Niu J, Pei P, Zhang J, Krebs P (2020) A comparative analysis of artificial neural networks and wavelet hybrid approaches to long-term toxic heavy metal prediction. Sci Rep-UK 10:13439
Li PP, Hao HH, Mao XG, Jianjun Xu, Lv YT, Chen WM, Ge DB, Zhang Z (2022a) Convolutional neural network-based applied research on the enrichment of heavy metals in the soil–rice system in China. Environ Sci Pollut Res 2022:1–14
Li PP, Hao HH, Zhang Z, Mao XG, Xu JJ, Lv YT, Chen WM, Ge DB (2022b) A field study to estimate heavy metal concentrations in a soil-rice system: application of graph neural networks. Sci Total Environ 832:155099
Liu P, Liu Z, Hu Y, Shi Z, Pan Y, Wang L, Wang GX (2019) Integrating a hybrid back propagation neural network and particle swarm optimization for estimating soil heavy metal contents using hyperspectral data. Sustainability 11:419
Lomax C, Liu WJ, Wu L, Xue K, Xiong J, Zhou J, McGrath SP, Meharg AA, Miller AJ, Zhao FJ (2012) Methylated arsenic species in plants originate from soil microorganisms. New Phytol 193:665–672
Lu A, Wang J, Qin X, Wang K, Han P, Zhang S (2012) Multivariate and geostatistical analyses of the spatial distribution and origin of heavy metals in the agricultural soils in Shunyi, Beijing, China. Sci Total Environ 425:66–74
Lu H, Li HM, Liu T, Fan YF, Yuan Y, Xie MX, Qian X (2019) Simulating heavy metal concentrations in an aquatic environment using artificial intelligence models and physicochemical indexes. Sci Total Environ 694:133591
Ministry of Ecology and Environment of PRC (MEEPRC) (2016) Soil and sediment-determination of aqua regia extracts of 12 metal elements-inductively coupled plasma mass spectrometry (HJ 803–2016). (in Chinese)
Mundher YA (2021) An insight into machine learning models era in simulating soil, water bodies and adsorption heavy metals: review, challenges and solutions. Chemosphere 277:130126
National Health Commission of PRC (NHCPRC) (2016) National standard for food safety-determination of multiple elements in food (GB 5009.268–2016). (in Chinese).
National Soil and Fertilizer Station, Ministry of Agriculture of PRC (NSFSPRC) (1994) Technical specification for soil analysis. China Agriculture Press (in Chinese)
Saqib M (2020) Forecasting COVID-19 outbreak progression using hybrid polynomial-Bayesian ridge regression model. Appl Intell 51:2703–2713
Sevik H, Cetin M, Ozel HU, Ozel HB, Mossi MMM, Cetin IZ (2019) Determination of Pb and Mg accumulation in some of the landscape plants in shrub forms. Environ Sci Pollut Res. https://doi.org/10.1007/s11356-019-06895-0
Tan T, Qian Y, Yu K (2015) Cluster adaptive training for deep neural network based acoustic model. IEEE/ACM Trans Audio SpeechLang 24:459–468
Tsagkatakis G, Moghaddam M, Tsakalides P (2020) Multi-temporal convolutional neural networks for satellite-derived soil moisture observation enhancement. International Geoscience and Remote Sensing Symposium. https://doi.org/10.1109/igarss39084.2020.9323790
Wang X, An S, Xu YQ, Hou HP, Chen FY, Yang YJ, Zhang SL, Liu R (2019) A back propagation neural network model optimized by mind evolutionary algorithm for estimating Cd, Cr, and Pb concentrations in soils using VIS-NIR diffuse reflectance pectroscopy. Appl Sci Basel 10:51
Wang YY, Su Y, Lu SG (2020) Predicting accumulation of Cd in rice (Oryza sativa L.) and soil threshold concentration of Cd for rice safe production. Sci Total Environ 738:139805
Xie Y (2021) Overview of Xiangtan. Xiangtan Natural Resources and Planning Bureau. Retrieved November 5, 2021, from http://www.xiangtan.gov.cn/68/index.htm#page3
Xiong TT, Leveque T, Austruy A, Goix S, Schreck E, Dappe V, Sobanska S, Foucault Y, Dumat C (2014) Foliar uptake and metal(loid) bioaccessibility in vegetables exposed to particulate matter. Environ Geochem Hlth 36:897–909
Xu XT, Chen SB, Ren LG, Han C, Lv DL, Zhang YF, Ai FK (2021) Estimation of heavy metals in agricultural soils using VIS-NIR spectroscopy with fractional-order derivative and generalized regression neural network. Remote Sens Basel 13:2718–2718
Yaseen ZM (2021) An insight into machine learning models era in simulating soil, water bodies and adsorption heavy metals: review, challenges and solutions. Chemosphere 277:130126
Yu D. Seide F, Li G (2012) Conversational speech transcription using context-dependent deep neural networks. Proceedings of the International Conference on International Conference on Machine Learning (ICML 2012), pp. 1–2
Zang F, Wang S, Nan Z, Ma J, Zhang Q, Chen Y, Li Y (2017) 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 305:188–196
Acknowledgements
The authors are extremely thankful to the anonymous reviewers that work in this paper.
Funding
Not applicable.
Author information
Authors and Affiliations
Contributions
Zhuo Zhang, conceptualization, methodology, software, data analysis, visualization, and paper writing. Yuanyuan Li, organization, supervision, data analysis and processing, and paper writing. Yang Bai, software, data processing, and paper reviewing. Ya Li, software, data processing, and visualization. Meng Liu, paper editing and English polishing. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethics approval and consent to participate
Not applicable.
Consent for publication
All authors have read this manuscript and consent for publication in Environmental Science and Pollution Research.
Conflict of interest
The authors declare no competing interests.
Additional information
Responsible Editor: Elena Maestri
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, Z., Li, Y., Bai, Y. et al. Convolutional graph neural networks-based research on estimating heavy metal concentrations in a soil-rice system. Environ Sci Pollut Res 30, 44100–44111 (2023). https://doi.org/10.1007/s11356-023-25358-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-023-25358-1