Distribution and Prediction of Soil Saturated Hydraulic Conductivity in Ningdong Based on GIS and Random Forest Algorithm

XIA Zishu; BAI Yiru; WANG Youqi; BAO Weibin; YANG Fan; ZHONG Yanxia; LI Mingji

doi:10.13870/j.cnki.stbcxb.2021.01.041

您当前的位置：

首页 >

文章列表页 >

Distribution and Prediction of Soil Saturated Hydraulic Conductivity in Ningdong Based on GIS and Random Forest Algorithm

更新时间：2025-03-12

- Distribution and Prediction of Soil Saturated Hydraulic Conductivity in Ningdong Based on GIS and Random Forest Algorithm
- Vol. 35, Issue 1, Pages: 285-293(2021)
- 作者机构：
  
  1. 宁夏大学资源环境学院,银川,750021
  2. 旱区特色资源与环境治理教育部国际合作联合实验室,银川,750021
- 作者简介：
- 基金信息：
- DOI：10.13870/j.cnki.stbcxb.2021.01.041
  CLC： S152.7
- Published：2021
- 稿件说明：
移动端阅览
XIA Zishu, BAI Yiru, WANG Youqi, et al. Distribution and Prediction of Soil Saturated Hydraulic Conductivity in Ningdong Based on GIS and Random Forest Algorithm[J]. 2021, 35(1): 285-293.
DOI：

XIA Zishu, BAI Yiru, WANG Youqi, et al. Distribution and Prediction of Soil Saturated Hydraulic Conductivity in Ningdong Based on GIS and Random Forest Algorithm[J]. 2021, 35(1): 285-293. DOI： 10.13870/j.cnki.stbcxb.2021.01.041.

摘要

为探明宁东土壤饱和导水率（Ks）的空间分布特征，在宁东采集136个原状土，采用经典统计和地统计方法分析土壤Ks的空间结构特征，并以地形因子、土壤属性等作为辅助变量，运用随机森林法（RF）、普通克里格法（OK）和逐步回归克里格法（RK）对区域土壤Ks进行预测并对3种方法的预测结果进行精度评价。结果表明：Ks介于0.05~7.13 mm/min，平均值为1.46 mm/min，变异系数为106.86%；Ks与容重、孔隙度、高程、坡度、坡向、平面曲率和剖面曲率在不同滞后距离下具有自相关关系和交互相关关系；土壤Ks块金值为38，表明随机因素引起的土壤Ks变异性较大，空间异质比为15.32%，在空间上呈现强变异性；RF法的预测精度最高，其平均相对误差（MRE）和均方根误差（RMSE）绝对值均为最小，相比OK和RK方法预测精度分别提高了5.53%和2.49%，且对局部细节的描述更准确、模拟效果最佳。RF法可以较为准确的预测宁东土壤Ks，为了解研究区土壤水文过程及林草植被建设提供数据参考。

Abstract

In order to find out the spatial distribution characteristics of soil saturated hydraulic conductivity (Ks)

136 undisturbed soils were collected in Ningdong. The spatial structure characteristics of Ks were analyzed by classical and geostatistical methods. Taking terrain factors and soil properties as auxiliary variables

the regional soil Ks were predicted by the random forest method (RF)

ordinary Kriging method (OK) and stepwise regression Kriging method (RK)

and the accuracy of the prediction results of the three methods were evaluated. The results showed that Ks ranged from 0.05 to 7.13 mm/min

with an average value of 1.46 mm/min and a coefficient of variation of 106.86%. Ks had autocorrelation and cross-correlation with bulk density

porosity

elevation

slope

aspect

plane curvature and section curvature under different lag distance. The nugget value of soil Ks was 38

indicating that the variability of soil Ks caused by random factor was large

and the spatial heterogeneity ratio was 15.32%

showing strong spatial variability. The prediction accuracy of RF was the highest

and the absolute values of mean relative error (MRE) and root mean square error (RMSE) were both the smallest. Compared with OK and RK

the prediction accuracy of RF was improved by 5.53% and 2.49%

respectively

and the description of local details was more accurate and the simulation effect was the best. RF could accurately predict soil Ks in Ningdong

and provide data reference for understanding soil hydrological process and forest and grass vegetation construction in the study area.

关键词

Keywords

references

Wang Y Q, Shao M A, Liu Z P, et al. Regional-scale variation and distribution patterns of soil saturated hydraulic conductivities in surface and subsurface layers in the loessial soils of China[J].Journal of Hydrology,2013,487(487):13-23.

李永宁,王忠禹,王兵,等.黄土丘陵区典型植被土壤物理性质差异及其对导水特性影响[J].水土保持学报,2019,33(6):176-189..

Machiwal D, Jha M K, Mal B C. Modelling infiltration and quantifying spatial soil variability in a wasteland of Kharagpur, India[J].Biosystems Engineering,2006,95(4):569-582.

韩永伟,高吉喜,李咏红,等.宁东能源化工基地规划生态环境影响评价研究[J].环境与可持续发展,2008,9(1):58-60.

李风军,冯晓秀,陆桂琴.宁东能源化工基地生态环境脆弱性评价研究[J].生态科学,2014,33(5):1017-1022.

李涛,李晓琳,郝新梅,等.应用土壤质地预测干旱区葡萄园土壤饱和导水率空间[J].农业工程学报,2014,30(9):84-92.

赵春雷,邵明安,贾小旭.黄土高原北部坡面尺度土壤饱和导水率分布与模拟[J].水科学进展, 2014,25(6):806-815.

李祥东,邵明安,赵春雷.西北干旱区土壤水力参数空间变异与模拟[J].干旱区研究,2019,36(6):1325-1332.

张川,陈洪松,张伟,等.喀斯特坡面表层土壤含水量、容重和饱和导水率的空间变异特征[J].应用生态学报,2014,25(6):1585-1591.

任丽,杨联安,王辉,等.基于随机森林的苹果区土壤有机质空间预测[J].干旱区资源与环境,2018,32(8):141-146.

齐雁冰,王茵茵,陈洋,等.基于遥感与随机森林算法的陕西省土壤有机质空间预测[J].自然资源学报,2017,32(6):1074-1086.

杨其坡,武伟,刘洪斌.基于地形因子和随机森林的丘陵区农田土壤有效铁空间分布预测[J].中国生态农业学报,2018,26(3):422-431.

郭澎涛, 李茂芬, 罗微, 等. 基于多源环境变量和随机森林的橡胶园土壤全氮含量预测[J]. 农业工程学报, 2015, 31(5):194-201.

卢宏亮,赵明松,刘斌寅,等.基于随机森林模型的安徽省土壤属性空间分布预测[J].土壤,2019,51(3):602-608.

李占文,骆有庆,王东菊,等.宁东能源化工基地大环境绿化有害生物危害现状及防控对策[J].宁夏工程技术,2010,9(4):376-379.

智静,乔琦,傅泽强.干旱地区工业系统资源代谢水平分析:以宁东能源煤化工基地为例[J].干旱区地理,2015,38(1):155-162.

白一茹,王幼奇,展秀丽.陕北农牧交错带土地利用方式对土壤物理性质及分布特征的影响[J].中国农业科学,2013,46(8):103-111.

中国科学院南京土壤研究所.土壤理化分析[M].上海:上海科学技术出版社,1983.

Zimmerman D L, Zimmerman M B. A Comparison of spatial semivariogram estimators and corresponding ordinary Kriging predictors[J].Technometrics,1991,33(1):77-91.

姚雪玲,傅伯杰,吕一河,等.基于GIS和统计模型的黄土丘陵沟壑区土壤水分插值方法[J].水土保持学报,2013,27(6):93-96.

包青岭,丁建丽,王敬哲,等.基于随机森林算法的土壤有机质含量高光谱检测[J].干旱区地理,2019,42(6):1404-1414.

Lindner C, Bromiley P A, Ionita M C, et al. Robust and accurate shape model matching using random forest regression-voting[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1862-1874.

于冬雪,贾小旭,黄来明.黄土区不同土层饱和导水率空间变异与影响因素[J].土壤通报,2018,49(5):1073-1079.

Dai Y J, Shan G W, Duan Q Y, et al. Development of a China dataset of soil hydraulic parameters using pedotransfer functions for land surface modeling[J].Journal of Hydrometeorology,2015,14(3):869-887.

Warrick A W, Nielsen D R. Spatial variability of soil physical properties[J].Applications of Soil Physics,1980,42(3):319-344.

连纲,郭旭东,傅伯杰,等.黄土高原小流域土壤容重及水分空间变异特征[J].生态学报,2006,26(3):647-654.

赵越,罗志军,廖牧鑫,等.泰和县耕地土壤养分空间分布及影响因素[J].水土保持学报,2018,32(5):299-306.

张珍明,周运超,黄先飞,等.喀斯特小流域土壤有机碳密度及碳储量空间分布异质性[J].水土保持学报,2017,31(2):184-190.

王军,傅伯杰,邱扬,等.黄土丘陵小流域土壤水分的时空变异特征-半变异函数[J].地理学报,2000,55(4):428-438.

邵明安,王全九,黄明斌.土壤物理学[M].北京:高等教育出版社,2006:228-261.

Cambardella C A, Moorman T B, Parkin T B, et al. Field-scale variability of soil properties in central iowa soils[J].Soil Science Society of America Journal,1994,58(5):1501-1511.

刘志鹏,邵明安,王云强.区域尺度下黄土高原土壤全钾含量的空间模拟[J].农业工程学报,2012,28(22):132-140.

Chapuis, Robert P. Predicting the saturated hydraulic conductivity of soils:A review[J].Bulletin of Engineering Geology & the Environment,2012,71(3):401-434.

Hu W, Shao M A, Si B C. Seasonal changes in surface bulk density and saturated hydraulic conductivity of natural landscapes[J].European Journal of Soil Science,2012,63(6):820-830.

Sonobe R, Tani H, Wang X, et al. Parameter tuning in the support vector machine and random forest and their performances in cross-and same-year crop classification using TerraSAR-X[J].International Journal of Remote Sensing,2014,35(23):7898-7909.

Wagner B, Tarnawski V R, Hennings V, et al. Evaluation of pedo-transfer functions for unsaturated soil hydraulic conductivity using an independent data set[J].Soil Science Society of America Journal,2001,108(1/2):145-147.

傅子洹,王云强,安芷生.黄土区小流域土壤容重和饱和导水率的时空动态特征[J].农业工程学报,2015,31(13):128-134.

白一茹,王幼奇,王菲,等.压砂地土壤导水特性空间格局及影响因子[J].干旱地区农业研究,2016,34(4):55-61.

张晗,欧阳真程,赵小敏,等.江西省耕地土壤氮素空间变异特征及其主控因素[J].水土保持学报,2018,32(5):307-315.

刘春利,胡伟,贾宏福,等.黄土高原水蚀风蚀交错区坡地土壤剖面饱和导水率空间异质性[J].生态学报,2012,32(4):1211-1219.

王幼奇,赵云鹏,白一茹,等.中宁枸杞土壤碳组分分布特征及其空间异质性[J].环境科学,2018,39(3):1396-1403.

谢恩泽,赵永存,陆访仪,等.不同方法预测苏南农田土壤有机质空间分布对比研究[J].土壤学报,2018,55(5):14-24.

Zhu Q, Lin H S. Comparing ordinary kriging and regression kriging for soil properties in contrasting landscapes[J].Pedosphere,2010,20(5):594-606.

王茵茵,齐雁冰,陈洋,等.基于多分辨率遥感数据与随机森林算法的土壤有机质预测研究[J].土壤学报,2016,53(2):342-354.

Views

1092

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-Temporal-Scale Variation Characteristics of Canopy Conductance in Artificial Shrubland Ecosystems and Its Biophysical Driving Mechanisms

Nationwide Landslide Hazard Based on Landslides Induced by 9 Earthquakes in China and Surrounding Regions from 2005 to 2017

Spatio-termporal Characteristics and Pedotransfer of Soil Penetration Resistance in Eroded Sloping Farmland of Black Soil Region, China

Analysis on Influencing Factors of Slope Stability in Loess Hilly and Gully Region

Relationship Between Soil Moisture and Topography-vegetation Factors on Fixed Dunes in the Southern Margin of the Gurbantunggut Desert

Related Author

YANG Fenglin

SHI Guangyao

FU Shaomin

CAI Lulu

WANG Yuxia

DU Lingtong

QIAO Chenglong

GUAN Xiaoyu

Related Institution

School of Forestry and Grassland Science， Ningxia University

Key Laboratory for Restoration and Reconstruction of Degraded Ecosystem in Northwest China of Ministry of Education， Ningxia University

School of Ecology and Environment， Ningxia University

School of Soil and Water Conservation， Beijing Forestry University

College of Earth Sciences, Guilin University of Technology

⁰