|
|
基于随机森林的土壤重金属浓度预测
|
Abstract:
土壤中重金属的潜在危害越来越受到人们的重视。预测连续的重金属浓度面有助于确定环境管理和修复的热点问题区域。近年来，基于森林的算法在解决包括地球科学在内的各个领域的各种问题中得到了广泛的应用。随机森林回归是一种有效的预测方法。本文利用土壤样本数据和其他协变量数据，将随机森林回归算法应用于预测土壤重金属浓度栅格图。本研究中的“污水排放点”、“干洗店”、“交通数据”(命名为AADT)和EPA TRI (有毒物质释放清单)与土壤重金属如何传播的主要途径有关。它还包括佛罗里达州“主要/次要排放”和“副排放”的数据。本文采用随机森林回归方法预测了铅、锌的连续重金属浓度。将点数据分成不同的种类进行密度面计算。将这些密度数据与土壤性质数据和采样数据结合起来，创建两个数据集：预测点和训练点。两者都在研究范围内，具有相同的解释变量集。然后利用随机森林回归模型得到预测结果。最后，使用RMSE评估预测精度。结果表明，随机森林回归模型中决策树数量的增加，RMSE值降低。
The potential hazard of heavy metals in soil has been attracted more and more attention. Prediction of a continuous heavy metal concentration surface helps identify hotspot problem areas for environmental management and remediation. In recent years, forest-based algorithm has become popular in solving many kinds of problems in different fields, including geoscience. Random Forest Regression is one of them works well in prediction. The paper represents an application of Random Forest Regression algorithm in predict concentration surface using soil sample data collected the research project by Liebens et al. (2012) and other covariates data. Such as “sewer waste points”, “dry cleaner”, “Traffic data (Named AADT) and EPA TRI (toxic release inventory) in this study relate with the main way about how soil heavy metal spread. It also includes Florida DEP “major/minor emitters” and “DEP emitters” data. In this paper, we use random forest regression to predict continuous heavy metal concentration focus on Pb and Zn. The point’s data were divided into different kinds to calculate the density surfaces. Joined these density data with soil properties data and sampling data to create two datasets: prediction points and training points. Both are in the study area and have the same set of explanatory variables. Then run a Random Forest Regression model to get the prediction results. Finally, assess prediction accuracy with RMSE. The results show that RMSE value decreases when the number of decision trees increases in the random forest regression model.
| [1] | Cai, L., Xu, Z., Ren, M., Guo, Q., Hu, X., Hu, G., Wan, H. and Peng, P. (2012) Source Identification of Eight Hazard-ous Heavy Metals in Agricultural Soils of Huizhou, Guangdong Province, China. Ecotoxicology and Environmental Safety, 78, 2-8. https://doi.org/10.1016/j.ecoenv.2011.07.004 |
| [2] | Dong, B., Zhang, R., Gan, Y., et al. (2019) Multiple Methods for the Identification of Heavy Metal Sources in Cropland Soils from a Resource-Based Region. Science of the Total Environment, 651, 3127-3138. https://doi.org/10.1016/j.scitotenv.2018.10.130 |
| [3] | 王春红, 阮进生, 蒋超群, 等. 基于GIS和地统计学的土壤重金属污染评价研究进展[J]. 安徽农业科学, 2012, 40(20): 10414-10418. |
| [4] | 纪冬丽, 曾琬晴, 张新波, 张竞, 王庆国, 张万军, 邓令, 杨光辉, 吴思睿. 天津近郊农田土壤重金属风险评价及空间主成分分析[J/OL]. 环境化学, 1-11. |
| [5] | 徐蕾, 肖昕, 马玉, 韩筱璇. 徐州农田土壤重金属空间分布及来源分析[J]. 生态与农村环境学报, 2019, 35(11): 1453-1459. |
| [6] | Chen, Y.X., Jiang, X.S., Wang, Y., et al. (2018) Assessment of Ecological Environment and Human Health of Heavy Metals in Mining Area Based on GIS. Acta Scientiae Circumstantiae, 38, 1642-1652. |
| [7] | 刘硕, 吴泉源, 曹学江, 王集宁, 张龙龙, 蔡东全, 周历媛, 刘娜. 龙口煤矿区土壤重金属污染评价与空间分布特征[J]. 环境科学, 2016, 37(1): 270-279. |
| [8] | Zhao, H., He, B., Wang, T.Y., et al. (2019) Pollution Characteristics of Heavy Metals and Source-Sink Relationship in Typical City of the South China. Acta Scientiae Circumstantiae, 39, 2231-2239. |
| [9] | Soffianian, A.R., Bapeer Bakir, H. and Khodakarami, L. (2015) Evaluation of Heavy Metals Concentration in Soil Using GIS, RS and Geostatistics. IOSR Journal of Environmental Science, 9, 61. |
| [10] | Li, F., Cai, Y. and Zhang, J. (2018) Spatial Characteristics, Health Risk Assessment and Sustainable Management of Heavy Metals and Metalloids in Soils from Central China. Sustainability, 10, 91. https://doi.org/10.3390/su10010091 |
| [11] | Fei, X., Christakos, G., Xiao, R., Ren, Z., Liu, Y. and Lv, X. (2019) Improved Heavy Metal Mapping and Pollution Source Apportionment in Shanghai City Soils Using Auxiliary Information. Science of the Total Environment, 661, 168-177. https://doi.org/10.1016/j.scitotenv.2019.01.149 |
| [12] | Sergeev, A.P., Buevich, A.G., Baglaeva, E.M. and Shichkin, A.V. (2019) Combining Spatial Autocorrelation with Machine Learning Increases Prediction Accuracy of Soil Heavy Metals. Catena, 174, 425-435. https://doi.org/10.1016/j.catena.2018.11.037 |
| [13] | Cai, L.M., Wang, Q.S., Wen, H.H., et al. (2019) Heavy Metals in Agricultural Soils from a Typical Township in Guangdong Province, China: Occurrences and Spatial Distribution. Ecotoxicology and Environmental Safety, 168, 184-191. https://doi.org/10.1016/j.ecoenv.2018.10.092 |
| [14] | Huang, S., Shao, G., Wang, L., et al. (2019) Spatial Distribution and Potential Sources of Five Heavy Metals and One Metalloid in the Soils of Xiamen City, China. Bulletin of Environmental Contamination and Toxicology, 103, 308-315. https://doi.org/10.1007/s00128-019-02639-5 |
| [15] | Hou, D., O’Connor, D., Nathanail, P., Tian, L. and Ma, Y. (2017) Integrated GIS and Multivariate Statistical Analysis for Regional Scale Assessment of Heavy Metal Soil Con-tamination: A Critical Review. Environmental Pollution, 231, 1188-1200. https://doi.org/10.1016/j.envpol.2017.07.021 |
| [16] | Santos-Francés, F., Martínez-Gra？a, A., Zarza, C.á., Sánchez, A.G. and Rojo, P.A. (2017) Spatial Distribution of Heavy Metals and the Environmental Quality of Soil in the Northern Plateau of Spain by Geostatistical Methods. International Journal of Environmental Research and Public Health, 14, 568. https://doi.org/10.3390/ijerph14060568 |
| [17] | Zhou, J. and Liu, H. (2013) A Spatial-Homogeneity-Based Interpolation Algorithm for Soil Properties. International Conference on Geoinformatics, Kaifeng, 20-22 June 2013, 1-4. https://doi.org/10.1109/Geoinformatics.2013.6626171 |
| [18] | Yang, J., Cao, L., Wang, J., Liu, C., Huang, C., Cai, W., Fang, H. and Peng, X. (2014) Speciation of Metals and Assessment of Contamination in Surface Sediments from Daya Bay, South China Sea. Sustainability, 6, 9096-9113. https://doi.org/10.3390/su6129096 |
| [19] | Agca, N. (2015) Spatial Distribution of Heavy Metal Content in Soils around an Industrial Area in Southern Turkey. Arabian Journal of Geosciences, 8, 1111-1123. https://doi.org/10.1007/s12517-013-1240-7 |
| [20] | 周卫红, 张静静, 邹萌萌, 等. 土壤重金属有效态含量检测与监测现状、问题及展望[J]. 中国生态农业学报, 2017, 25(4): 605-615. |
| [21] | Yang, J., Lv, F., Zhou, J., Song, Y. and Li, F. (2017) Health Risk Assessment of Vegetables Grown on the Contaminated Soils in Daye City of Hubei Province, China. Sustainability, 9, 2141. https://doi.org/10.3390/su9112141 |
| [22] | Technica, G. and City, S.T. (2019) Char-acterization of Heat Waves: A Case Study for Peninsular Malaysia. Geographia Technica, 14, 146-156. https://doi.org/10.21163/GT_2019.141.11 |
| [23] | Liebens, J., Mohrherr, C.J. and Rao, K.R. (2012) Trace Metal Assessment in Soils in a Small City and Its Rural Surroundings, Pensacola, FL, USA. Environmental Earth Sciences, 65, 1781-1793. https://doi.org/10.1007/s12665-011-1158-x |
| [24] | Shaheen, A. and Iqbal, J. (2018) Spatial Distribution and Mobility Assessment of Carcinogenic Heavy Metals in Soil Profiles Using Geostatistics and Random Forest, Boruta Algorithm. Sustainability (Switzerland), 10, 799. https://doi.org/10.3390/su10030799 |
| [25] | Bhunia, G.S., Shit, P.K. and Maiti, R. (2018) Comparison of GIS-Based Interpolation Methods for Spatial Distribution of Soil Organic Carbon (SOC). Journal of the Saudi Society of Agricul-tural Sciences, 17, 114-126. https://doi.org/10.1016/j.jssas.2016.02.001 |
| [26] | G？l, C., Bulut, S. and Bolat, F. (2017) Comparison of Different Interpolation Methods for Spatial Distribution of Soil Organic Carbon and Some Soil Properties in the Black Sea Backward Region of Turkey. Journal of African Earth Sciences, 134, 85-91. https://doi.org/10.1016/j.jafrearsci.2017.06.014 |
| [27] | Fifi, U., Winiarski, T. and Emmanuel, E. (2013) Assessing the Mobility of Lead, Coppermore Are Cadmium in a Calcareous Soil of Port-au-Prince, Haiti. International Journal of Environmental Research and Public Health, 10, 5830-5843. https://doi.org/10.3390/ijerph10115830 |
