Spatial distribution prediction of soil pH in arable land of Jiangxi Province based on multi-source environmental variables and the random forest model
ZHONG Xiaoyong1,2(), LI Hongyi3,4, GUO Dongyan2, XIE Modian3,4, ZHAO Wanru3,4, HU Bifeng3,4()
1. School of Finance and Public Administration, Jiangxi University of Finance and Economics, Nanchang 330013, China 2. Chinese Academy of Natural Resources Economics, Beijing 101149, China 3. School of Tourism and Urban Management, Jiangxi University of Finance and Economics, Nanchang 330013, China 4. Key Laboratory of Data Science in Finance and Economics, Jiangxi University of Finance and Economics, Nanchang 330013, China
This study aims to compare the accuracy of random forest(RF) and ordinary kriging(OK) model for predicting spatial distribution of soil pH in arable land of Jiangxi Province using different covariates combination, and assess the feasibility and potential of RF method for improving the prediction accuracy of soil pH value. The RF algorithm is used to predict the pH value of cultivated soil in Jiangxi Province based on environmental covariate such as climate, topography and vegetation, combined with soil properties and cultivated land use conditions, identify the main influencing factors. The results produced by the RF was compared with the classical OK interpolation model. Our results showed that the accuracy of RF-A model with soil properties and cultivated land use conditions as environmental variables is better than that of RF-B model which only including terrain, climate and vegetation attributes as environmental variables. Climatic condition is the dominate factor which control the spatial variation of soil pH. the topographic factors and anthropogenic factors also have essential effect on spatial variability of soil pH. Thus, this study proved RF method has theoretical and practical significance for improving the accuracy of soil pH prediction at large-scale.
钟骁勇, 李洪义, 郭冬艳, 谢模典, 赵婉如, 胡碧峰. 基于多源环境变量和随机森林模型的江西省耕地土壤pH值空间预测[J]. 自然资源遥感, 2023, 35(4): 178-185.
ZHONG Xiaoyong, LI Hongyi, GUO Dongyan, XIE Modian, ZHAO Wanru, HU Bifeng. Spatial distribution prediction of soil pH in arable land of Jiangxi Province based on multi-source environmental variables and the random forest model. Remote Sensing for Natural Resources, 2023, 35(4): 178-185.
Mao W, Li W X, Gao H, et al. pH variation and the driving factors of farmlands in Yangzhou for 30 years[J]. Journal of Plant Nutrition and Fertilizers, 2017, 23(4):883-893.
[2]
Oh N H, Richter D D. Soil acidification induced by elevated atmospheric CO2[J]. Global Change Biology, 2004, 10(11):1936-1946.
doi: 10.1111/gcb.2004.10.issue-11
[3]
Kirk G J D, Bellamy P H, Lark R M. Changes in soil pH across England and Wales in response to decreased acid deposition[J]. Global Change Biology, 2010, 16(11):3111-3119.
doi: 10.1111/gcb.2010.16.issue-11
[4]
Tian D, Niu S. A global analysis of soil acidification caused by nitrogen addition[J]. Environmental Research Letters, 2015, 10(2):024019.
doi: 10.1088/1748-9326/10/2/024019
[5]
Guo J H, Liu X J, Zhang Y, et al. Significant acidification in major Chinese croplands[J]. Science, 2010, 327(5968):1008-1010.
doi: 10.1126/science.1182570
pmid: 20150447
[6]
Hu B F, Jia X L, Hu J, et al. Assessment of heavy metal pollution and health risks in the soil-plant-human system in the Yangtze River Delta,China[J]. International Journal of Environmental Research and Public Health, 2017, 14(9):1042.
doi: 10.3390/ijerph14091042
[7]
Hu B F, Shao S, Fu Z, et al. Identifying heavy metal pollution hot spots in soil-rice systems:A case study in South of Yangtze River Delta,China[J]. Science of the Total Environment, 2019, 658:614-625.
doi: 10.1016/j.scitotenv.2018.12.150
Yang Z J, Chen X M, Jing F, et al. Spatial variability of nutrients and heavy metals in paddy field soils based on GIS and geostatistics[J]. Chinese Journal of Applied Ecology, 2018, 29(6):1893-1901.
[9]
Xia F, Hu B, Zhu Y, et al. Improved mapping of potentially toxic elements in soil via integration of multiple data sources and various geostatistical methods[J]. Remote Sensing, 2020, 12(22):3775.
doi: 10.3390/rs12223775
[10]
Hu B, Zhou Y, Jiang Y, et al. Spatio-temporal variation and source changes of potentially toxic elements in soil on a typical plain of the Yangtze River Delta,China (2002—2012)[J]. Journal of Environmental Management, 2020, 271:110943.
doi: 10.1016/j.jenvman.2020.110943
Ding Y P, Zhang J H, Liu Y H, et al. Spatial distribution characteristics and influencing factors of soil organic carbon in Yihe River basin based on GWR model[J]. Acta Ecologica Sinica, 2021, 41(12):4876-4885.
Zhang Y, Tu N M, Xie H Y, et al. Spatial and temporal variation of soil nutrients in tobacco-rice multiple-cropping area of Chaling[J]. Chinese Journal of Soil Science, 2021, 52(2):297-305.
doi: 10.1046/j.1365-2389.2001.00380.x
[13]
McBratney A B, Santos M L M, Minasny B. On digital soil mapping[J]. Geoderma, 2003, 117(1-2):3-52.
doi: 10.1016/S0016-7061(03)00223-4
[14]
Teng H, Rossel R A V, Shi Z, et al. Updating a national soil classification with spectroscopic predictions and digital soil mapping[J]. Catena, 2018, 164:125-134.
doi: 10.1016/j.catena.2018.01.015
[15]
Peng J, Biswas A, Jiang Q, et al. Estimating soil salinity from remote sensing and terrain data in southern Xinjiang Province,China[J]. Geoderma, 2019, 337:1309-1319.
doi: 10.1016/j.geoderma.2018.08.006
Pang L H, Liu F, Zhao X, et al. Digital mapping of topsoil attributes in Qinghai Province[J]. Chinese Journal of Soil Science, 2019, 50(3):505-513.
doi: 10.1046/j.1365-2389.1999.00245.x
[17]
Arrouays D, Poggio L, Guerrero O A S, et al. Digital soil mapping and GlobalSoilMap.Main advances and ways forward[J]. Geoderma Regional, 2020, 21:e00265.
doi: 10.1016/j.geodrs.2020.e00265
[18]
Li H, Liu X, Hu B, et al. Field-scale characterization of spatio-temporal variability of soil salinity in three dimensions[J]. Remote Sensing, 2020, 12(24):4043.
doi: 10.3390/rs12244043
[19]
Yan F, Shang G W, Zhang J, et al. Depth-to-bedrock map of China at a spatial resolution of 100 meters[J]. Scientific Data, 2020, 7(1):1-13.
doi: 10.1038/s41597-019-0340-y
[20]
Fu T, Zhao R, Hu B, et al. Novel framework for modelling the cadmium balance and accumulation in farmland soil in Zhejiang Province,east China:Sensitivity analysis,parameter optimisation,and forecast for 2050[J]. Journal of Cleaner Production, 2021, 279:123674.
doi: 10.1016/j.jclepro.2020.123674
He L Q, Liu Q, Wang D C, et al. Estimation of soil organic carbon storage based on digital soil mapping technique[J]. Chinese Journal of Applied Ecology, 2021, 32(2):591-600.
Zhang G L, Zhu A X, Shi Z, et al. Progress and future prospect of soil geography[J]. Progress in Geography, 2018, 37(1):57-65.
doi: 10.18306/dlkxjz.2018.01.007
[23]
Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32.
doi: 10.1023/A:1010933404324
Ren L, Yang L A, Wang H, et al. Spatial prediction of soil organic matter in apple region based on random forest[J]. Journal of Arid Land Resources and Environment, 2018, 32(8):141-146.
[25]
O’Brien R, Ishwaran H. A random forests quantile classifier for class imbalanced data[J]. Pattern Recognition, 2019, 90:232-249.
doi: 10.1016/j.patcog.2019.01.036
pmid: 30765897
[26]
Pouladi N, Møller A B, Tabatabai S, et al. Mapping soil organic matter contents at field level with Cubist,random forest and Kriging[J]. Geoderma, 2019, 342:85-92.
doi: 10.1016/j.geoderma.2019.02.019
[27]
Vaysse K, Lagacherie P. Using quantile regression forest to estimate uncertainty of digital soil mapping products[J]. Geoderma, 2017, 291:55-64.
doi: 10.1016/j.geoderma.2016.12.017
[28]
Guo P T, Li M F, Luo W, et al. Digital mapping of soil organic matter for rubber plantation at regional scale:An application of random forest plus residuals Kriging approach[J]. Geoderma, 2015, 237:49-59.
[29]
da Silva Chagas C, de Carvalhe W Jr, Bhering S B, et al. Spatial prediction of soil surface texture in a semiarid region using random forest and multiple linear regressions[J]. Catena, 2016, 139:232-240.
doi: 10.1016/j.catena.2016.01.001
[30]
Camera C, Zomeni Z, Noller J S, et al. A high resolution map of soil types and physical properties for Cyprus:A digital soil mapping optimization[J]. Geoderma, 2017, 285:35-49.
doi: 10.1016/j.geoderma.2016.09.019
[31]
Amirian-Chakan A, Minasny B, Taghizadeh-Mehrjardi R, et al. Some practical aspects of predicting texture data in digital soil mapping[J]. Soil and Tillage Research, 2019, 194:104289.
doi: 10.1016/j.still.2019.06.006
[32]
Chen S C, Liang Z Z, Webster R, et al. A high-resolution map of soil pH in China made by hybrid modelling of sparse soil data and environmental covariates and its implications for pollution[J]. Science of the Total Environment, 2019, 655:273-283.
doi: 10.1016/j.scitotenv.2018.11.230
Wang S H, Lu H L, Zhao M S, et al. Assessing soil pH in Anhui Province based on different features mining methods combined with generalized boosted regression models[J]. Chinese Journal of Applied Ecology, 2020, 31(10):3509-3517.
[35]
周宏冀. 江西省耕地土壤pH空间变异与管理分区研究[D]. 南昌: 江西财经大学, 2019.
Zhou H J. Study on spatial variation and management zoning of soil pH value of cultivated land in Jiangxi Province[D]. Nanchang: Jiangxi University of Finance and Economics, 2019.
Qi Y B, Wang Y Y, Chen Y, et al. Soil organic matter prediction based on remote sensing data and random forest model in Shaanxi Province[J]. Journal of Natural Resources, 2017, 32(6):1074-1086.
Yuan Y Q, Chen H Y, Zhang L M, et al. Prediction of spatial distribution of soil organic carbon in farmland based on multi-variables and random forest algorithm: A case study of a subtropical complex geomorphic region in Fujian as an example[J]. Acta Pedologica Sinica, 2021, 58(4):887-899.
Wang H, Cao J, Wu J H, et al. Spatial and temporal variability in soil pH of Shaanxi Province over the last 40 years[J]. Chinese Journal of Eco-Agriculture, 2021, 29(6):1117-1126.
Dai W H, Huang Y, Wu L, et al. Relationships between soil organic matter content(SOM) and pH in topsoil of zonal soils in China[J]. Acta Pedologica Sinica, 2009, 46(5):851-860.
Kang T, Zhou C H, Wei Z Q, et al. Regional distribution characteristics and influencing factors of soil cation exchange capacity in Jiangxi[J]. Chinese Agricultural Science Bulletin, 2021, 37(14):66-71.
doi: 10.11924/j.issn.1000-6850.casb2020-0486
Wang H, Xing X J, Xu Z C. Relationship between pH value and available nutrients of purple soil in panxi tobacco-growing areas[J]. Soil and Fertilizer Sciences in China, 2007(6):19-22.
Zhu D M, Liu Y, Zhang L, et al. Effects of pH,Eh,Fe,and flooded time on available-Cd content after flooding of different kinds of soil[J]. Journal of Agro-Environment Science, 2017, 36(8):1508-1517.
[44]
Ding C, Du S, Ma Y, et al. Changes in the pH of paddy soils after flooding and drainage:Modeling and validation[J]. Geoderma, 2019, 337:511-513.
doi: 10.1016/j.geoderma.2018.10.012