基于RF和EBKRP算法的新安江流域有效土壤厚度反演

王尚晓; 张晓东; 张明; 牛晓楠; 周墨; 唐志敏; 张洁; 宗乐丽; 徐帅

doi:10.13961/j.cnki.stbctb.2025.01.018

您当前的位置：

首页 >

文章列表页 >

基于RF和EBKRP算法的新安江流域有效土壤厚度反演

试验研究

- 基于RF和EBKRP算法的新安江流域有效土壤厚度反演
- Effective soil thickness inversion in Xinanjiang River basin based on random forest and empirical Bayesian Kriging regression prediction algorithms
- 水土保持通报 2025年45卷第1期页码：168-177
- 作者机构：
  
  1. 中国地质调查局南京地质调查中心,江苏,南京,210016
  2. 华南师范大学教育科学学院,广东,汕尾,516600
- 作者简介：
- 基金信息：
  
  中国地质调查局项目“华东地区自然资源动态监测与风险评估”(DD20230103)，“华东地区国土空间用途管制技术支撑与应用服务”(DD20230495);江苏省科技计划(“一带一路”创新合作项目)“黑土地土壤退化诊断评价与动态监测技术合作研发”(BZ2023003)
- DOI：10.13961/j.cnki.stbctb.2025.01.018
  中图分类号： S159
- 纸质出版：2025
- 稿件说明：
移动端阅览
王尚晓, 张晓东, 张明, 等. 基于RF和EBKRP算法的新安江流域有效土壤厚度反演[J]. 水土保持通报, 2025,45(1):168-177.

Wang Shangxiao, Zhang Xiaodong, Zhang Ming, et al. Effective soil thickness inversion in Xinanjiang River basin based on random forest and empirical Bayesian Kriging regression prediction algorithms[J]. Bulletin of Soiland Water Conservation, 2025, 45(1): 168-177.
王尚晓, 张晓东, 张明, 等. 基于RF和EBKRP算法的新安江流域有效土壤厚度反演[J]. 水土保持通报, 2025,45(1):168-177. DOI： 10.13961/j.cnki.stbctb.2025.01.018.

Wang Shangxiao, Zhang Xiaodong, Zhang Ming, et al. Effective soil thickness inversion in Xinanjiang River basin based on random forest and empirical Bayesian Kriging regression prediction algorithms[J]. Bulletin of Soiland Water Conservation, 2025, 45(1): 168-177. DOI： 10.13961/j.cnki.stbctb.2025.01.018.

摘要

[目的

]

快速、准确地获取区域有效土壤厚度，分析其空间分布特征和影响因素，为植被生长、土壤保持和粮食安全工作提供理论指导。[方法

]

以新安江流域为研究区，将野外调查数据、地形、岩性和气候等成土因素结合起来，采用经验贝叶斯克里金回归预测(EBKRP)和随机森林(RF)算法，得到有效土壤厚度反演结果，并分析其与环境变量之间的关系。[结果

]

①区域平均有效土壤厚度为0.2～0.3 m，城镇建设集中和人类活动密集的盆地和平原区土壤厚度较高，丘陵山地区则较低。②从MAE(平均绝对误差)、R

(判定系数)和RMSE(均方根误差)3项精度评价指标来看，RF算法的预测结果明显优于EBKRP算法，而且更能显示出土壤厚度空间异质性分布特征，在一定程度上提高了土壤厚度数字制图的效果。③有效土壤厚度的估算受地形和气候变量的影响较大，它们分别占变量重要性的46.77%和18.78%。[结论

]

RF算法能够有效实现对区域有效土壤厚度的反演，克服了土壤厚度空间异质性的特点，相较于有限采样的模型更精确，分辨率也更高。

Abstract

[Objective] The effective soil thickness of a region was rapidly and accurately obtained

and its spatial distribution and influencing factors was analyzed

in order to provide theoretical guidance for vegetation growth

soil conservation

and food security. [Methods] Taking the Xinanjiang River basin as the research area

combining field survey data

topography

lithology

climate

and other soil-forming factors

the empirical Bayesian Kriging regression prediction (EBKRP) and random forest (RF) algorithms were applied to obtain the effective soil thickness inversion results. The relationship between this data and environmental variables was also analyzed. [Results] ① The average effective soil thickness in the region ranged from 0.2 to 0.3 m. Soil thickness was higher in basin and plain areas with concentrated urban development and intensive human activity. Meanwhile

it was lower in hilly and mountainous regions. ② Based on three accuracy evaluation indicators of MAE (mean absolute error)

R2 (coefficient of determination)

and RMSE (root mean square error)

the prediction results of the RF algorithm were significantly better than those of the EBKRP algorithm. It could more effectively show the spatial heterogeneity distribution of soil thickness

improving the effect of soil thickness digital mapping. ③ The effective soil thickness estimation was strongly influenced by topography and climate variables

which accounted for 46.77% and 18.78% of the variable importance

respectively. [Conclusion] The RF algorithm could effectively invert regional effective soil thickness

overcoming the spatial heterogeneity of soil thickness

and is more accurate and has a higher resolution compared to models with limited sampling.

关键词

Keywords

references

Gochis D J, Vivoni E R, Watts C J. The impact of soil depth on land surface energy and water fluxes in the North American Monsoon region [J]. Journal of Arid Environments, 2010,74(5):564-571.

Kuriakose S L, Devkota S, Rossiter D G, et al. Prediction of soil depth using environmental variables in an anthropogenic landscape: A case study in the Western Ghats of Kerala, India [J]. CATENA, 2009,79(1):27-38.

刘金涛,赵薇,刘彧.土壤厚度演化模型理论方法研究进展[J].土壤学报,2024,61(2):319-330. Liu Jintao, Zhao Wei, Liu Yu. Modelling soil thickness evolution: Advancements and challenges [J]. Acta Pedologica Sinica, 2024,61(2):319-330.

周云龙.福建南安市石井: 东田地区土壤厚度空间分布特征及主要影响因素[J].华东地质,2022,43(1):124-132. Zhou Yunlong. Spatial distribution characteristics and main influencing factors of soil thickness in Shijing-Dongtian area, Nan'an City, Fujian Province [J]. East China Geology, 2022,43(1):124-132.

Heimsath A M, Dietrich W E, Nishiizumi K, et al. Cosmogenic nuclides, topography, and the spatial variation of soil depth [J]. Geomorphology, 1999,27(1/2):151-172.

Sarkar S, Roy A K, Martha T R. Soil depth estimation through soil-landscape modelling using regression Kriging in a Himalayan terrain [J]. International Journal of Geographical Information Science, 2013,27(12):2436-2454.

Laslett G M, McBratney A B, Pahl P J, et al. Comparison of several spatial prediction methods for soil pH [J]. Journal of Soil Science, 1987,38(2):325-341.

Kravchenko A, Bullock D G. A comparative study of interpolation methods for mapping soil properties [J]. Agronomy Journal, 1999,91(3):393-400.

Zhang Shuai, Liu Gang, Chen Shuli, et al. Assessing soil thickness in a black soil watershed in Northeast China using random forest and field observations [J]. International Soil and Water Conservation Research, 2021,9(1):49-57.

Zhang Ganlin, Liu Feng, Song Xiaodong. Recent progress and future prospect of digital soil mapping: A review [J]. Journal of Integrative Agriculture, 2017,16(12):2871-2885.

Krivoruchko K, Gribov A. Evaluation of empirical Bayesian Kriging [J]. Spatial Statistics, 2019,32:100368.

Gribov A, Krivoruchko K. Empirical Bayesian Kriging implementation and usage [J]. Science of the Total Environment, 2020,722:137290.

Han Xiaole, Liu Jintao, Mitra S, et al. Selection of optimal scales for soil depth prediction on headwater hillslopes: A modeling approach [J]. Catena, 2018,163:257-275.

Mallik S, Bhowmik T, Mishra U, et al. Mapping and prediction of soil organic carbon by an advanced geostatistical technique using remote sensing and terrain data [J]. Geocarto International, 2022,37(8):2198-2214.

唐志敏,张晓东,张明,等.新安江流域土壤元素地球化学特征: 来自岩石建造类型的约束[J].华东地质,2023,44(2):172-185. Tang Zhimin, Zhang Xiaodong, Zhang Ming, et al. Geochemical characteristics of soil elements in Xin’an River basin: Constraints from rock formation types [J]. East China Geology, 2023,44(2):172-185.

王尚晓,牛晓楠,张洁,等.新安江流域2000—2021年NDVI时空变化特征及其影响因素分析[J].华东地质,2023,44(3):273-281. Wang Shangxiao, Niu Xiaonan, Zhang Jie, et al. Spatial and temporal variation features of NDVI and its influence factors in the Xin’an River basin from 2000 to 2021[J]. East China Geology, 2023,44(3):273-281.

易晨,李德成,张甘霖,等.土壤厚度的划分标准与案例研究[J].土壤学报,2015,52(1):220-227. Yi Chen, Li Decheng, Zhang Ganlin, et al. Criteria for partition of soil thickness and case studies [J]. Acta Pedologica Sinica, 2015,52(1):220-227.

McBratney A, Santos M L M, Minasny B. On digital soil mapping [J]. Geoderma, 2003,117:3-52.

邱思慧,林少颖,王维奇.中国东部地区不同海拔梯度土壤有机碳库特征及其影响因素综述[J].中国水土保持科学(中英文),2022,20(3):142-150. Qiu Sihui, Lin Shaoying, Wang Weiqi. Characteristics of soil organic carbon pool at different altitude gradients in Eastern China and its influencing factors: A review [J]. Science of Soil and Water Conservation, 2022,20(3):142-150.

赵玉国,张甘霖,龚子同,等.海南岛不同地质背景下的土壤类型、质量特征和作物适宜性[J].第四纪研究,2005,25(3):389-395. Zhao Yuguo, Zhang Ganlin, Gong Zitong, et al. Soil type,soil quality and crop suitability of soils developed from different geology environments in Hainan Island [J]. Quaternary Sciences, 2005,25(3):389-395.

刘鹏举,夏智武,唐小明.基于DEM和坡面特征的坡位生成方法[J].北京林业大学学报,2016,38(2):68-73. Liu Pengju, Xia Zhiwu, Tang Xiaoming. Slope position extraction method based on DEM and slope features [J]. Journal of Beijing Forestry University, 2016,38(2):68-73.

O’Loughlin E M. Prediction of surface saturation zones in natural catchments by topographic analysis [J]. Water Resources Research, 1986,22(5):794-804.

Zhang Xiao, Liu Liangyun, Chen Xidong, et al. GLC-FC30: Global land-cover product with fine classification system at 30 m using time-series Landsat imagery [J]. Earth System Science Data, 2021,13(6):2753-2776.

王晶,赵文武,刘月,等.植物功能性状对土壤保持的影响研究述评[J].生态学报,2019,39(9):3355-3364. Wang Jing, Zhao Wenwu, Liu Yue, et al. Effects of plant functional traits on soil conservation: A review [J]. Acta Ecologica Sinica, 2019,39(9):3355-3364.

常海钦,付亚龙,林鑫,等.流域盆地化学风化强度空间分布及控制因素研究: 以长江和珠江为例[J].地球科学进展,2019,34(1):93-102. Chang Haiqin, Fu Yalong, Lin Xin, et al. Spatial distribution and controlling factors of chemical weathering intensity in drainage basins: A case study in the Yangtze River basin and Pearl River basin [J]. Advances in Earth Science, 2019,34(1):93-102.

Breiman L. Statistical modeling: The two cultures (with comments and a rejoinder by the author) [J]. Statistical Science, 2001,16(3):216-218.

Molla A, Zhang Weiwei, Zuo Shudi, et al. A machine learning and geostatistical hybrid method to improve spatial prediction accuracy of soil potentially toxic elements [J]. Stochastic Environmental Research and Risk Assessment, 2023,37(2):681-696.

Yang Qiyong, Zhang Fawang, Jiang Zhongcheng, et al. Relationship between soil depth and terrain attributes in karst region in Southwest China [J]. Journal of Soils and Sediments, 2014,14(9):1568-1576.

Moore I D, Grayson R B, Ladson A R. Digital terrain modelling: A review of hydrological, geomorphological, and biological applications [J]. Hydrological Processes, 1991,5(1):3-30.

刘宝元,阎百兴,沈波,等.东北黑土区农地水土流失现状与综合治理对策[J].中国水土保持科学,2008,6(1):1-8. Liu Baoyuan, Yan Baixing, Shen Bo, et al. Current status and comprehensive control strategies of soil erosion for cultivated land in the Northeastern black soil area of China [J]. Science of Soil and Water Conservation, 2008,6(1):1-8.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

2000—2024年黄河源园区生态环境质量变化及其驱动因素

资源枯竭型城市转型对净生态系统生产力的影响——以江苏省徐州市为例

黄河流域三大城市群城市土地绿色利用效率的空间关联网络与影响因素

典型干旱区山地-绿洲-荒漠生态系统服务价值的时空演变——以玛纳斯河流域为例

融雪期微地形对土壤水分时空分布的影响及短期预测