基于遥感与随机森林算法的陕西省土壤有机质空间预测

doi:10.11849/zrzyxb.20160623

自然资源学报 ›› 2017, Vol. 32 ›› Issue (6): 1074-1086.doi: 10.11849/zrzyxb.20160623

• 资源研究方法 • 上一篇

基于遥感与随机森林算法的陕西省土壤有机质空间预测

齐雁冰^{1, 2}, 王茵茵¹, 陈洋¹, 刘姣姣¹, 张亮亮¹

1. 西北农林科技大学资源环境学院,陕西杨凌 712100；
2. 农业部西北植物营养与农业环境重点实验室,陕西杨凌 712100

收稿日期:2016-06-14 修回日期:2016-07-15 出版日期:2017-06-20 发布日期:2017-06-20
作者简介:齐雁冰（1976- ）,男,河南淮阳人,博士,副教授,主要从事土地资源与空间信息技术研究。E-mail: ybiq@nwsuaf.edu.cn
基金资助:
国家科技基础性工作专项项目（2014FY110200A08）

Soil Organic Matter Prediction Based on Remote Sensing Data and Random Forest Model in Shaanxi Province

QI Yan-bing^{1, 2}, WANG Yin-yin¹, CHEN Yang¹, LIU Jiao-jiao¹, ZHANG Liang-liang¹

1. College of Natural Resources and Environment, Northwest A & F University, Yangling 712100, China;
2. Key Laboratory of Plant Nutrition and the Agri-environment in Northwest China, Ministry of Agriculture, Yangling 712100, China

Received:2016-06-14 Revised:2016-07-15 Online:2017-06-20 Published:2017-06-20
Supported by:
Special Foundation of National Science and Technology Basic Work Project of China, No. 2014FY110200A08.

摘要/Abstract

摘要：

遥感数据作为反映土壤组成结构及植被生长状况的数据源,借助辅助环境因子的土壤属性预测在数字土壤制图中日益受到重视。论文运用随机森林（Random Forest,RF）算法,基于AWIFS（分辨率56 m）和MODIS（分辨率250 m）遥感数据及501个实测样点数据对陕西省土壤有机质空间分布状况进行预测,并对预测精度进行估算。结果表明陕西省土壤有机质含量以南部的秦岭山地区和大巴山区为最高,土壤有机质含量大于25 g·kg^-1,黄土高原南部处于中等水平,大部分在16~25 g·kg^-1之间,关中平原和汉中低山丘陵区含量偏低,大部分在13~25 g·kg^-1,而黄土高原北部和风沙滩区含量大部分低于10 g·kg^-1。基于AWIFS影像的预测效果要优于MODIS影像,成像日期对有机质预测的影响不大。基于RF模型的土壤有机质预测精度在设定的不同抽样百分比条件下,独立验证数据集的平均误差大部分不超过3 g·kg^-1,预测值与实测值的相关系数在0.7以上。高程是影响土壤有机质预测的最重要因子,当影像的分辨率降低时,样点分布的地理经纬度和坡度对土壤有机质预测的影响上升,植被因子的影响程度下降。

关键词: 多分辨率遥感数据, 陕西省, 随机森林算法, 土壤有机质预测

Abstract:

There exists deviation of predication of soil organic matter (SOM) with observed data in special local topography units. The accuracy of SOM predication can be improved by combining observed data and remote sensing (RS) data, especially for SOM predication in large scale. In this study, AWIFS (Advanced Wide Field Sensor) and MODIS (Moderate Resolution Imaging Spectroradiometer) data, whose spatial resolution are 56 and 250 meters respectively, were combined with observed sample data to predict the spatial distribution of SOM in Shaanxi Province with RF (Random Forest) model. The spatial distribution of SOM in six types of topographical units were summarized, and the prediction accuracies of SOM based on RF model and OK (Ordinary Kriging) model were compared. The results indicated that the spatial differentiation of SOM is obvious in north-south direction in Shaanxi Province. It is the highest in Qinling and Daba mountain areas with SOM content higher than 25 g·kg^-1, and it is medium high in the south of Loess Plateau area with the SOM content 22-30 g·kg^-1. The content of SOM is lower in Guanzhong Plain and Hanzhong basin areas with SOM content among 13-25 g·kg^-1, while it is the lowest in north Loess Plateau and the blown-sand areas with SOM content less than 10 g·kg^-1. The prediction results based on AWIFS data (with higher spatial resolution) were better than those based on MODIS (with lower spatial resolution) data. The acquired data of images has little influence on SOM prediction. It is shown that the predicted value of SOM is a bit lower in autumn than in spring. With different percentages of sampling, the SOM prediction based on RF model is always better than that based on Ordinary Kriging model. The prediction accuracy in this study is reliable, because the mean error in independent validation set is no more than 3 g·kg^-1,and the correlation coefficient of the predicted values and the observed values are higher than 0.7. Elevation is the most importance factor influencing SOM prediction in Shaanxi Province. When the spatial resolution of RS data decreases, the importance of geographic location of sampling points increase and the importance of vegetation decrease.

Key words: multi-resolution remote sensing data, random forest algorithm, Shaanxi Province, soil organic matter prediction

中图分类号:

S158

齐雁冰, 王茵茵, 陈洋, 刘姣姣, 张亮亮. 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.

QI Yan-bing, WANG Yin-yin, CHEN Yang, LIU Jiao-jiao, ZHANG Liang-liang. 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.

参考文献

[1] 张法升, 曲威, 尹光华, 等. 基于多光谱遥感影像的表层土壤有机质空间格局反演 [J]. 应用生态学报, 2010, 21(4): 883-888. [ZHANG F S, QU W, YIN G H, et al. Spatial pattern of surface soil organic matter based on remotely sensed multispectral image. Chinese Journal of Applied Ecology, 2010, 21(4): 883-888. ]
[2] 方斌, 吴金凤. 作物种植前后土壤有机质及养分因子的空间变异分析 [J]. 生态学报,2014, 34(4): 983-992. [FANG B, WU J F. Spatial variation analysis of soil organic matter and nutrient factor for before and after planting crops. Acta Ecologica Sinica, 2014, 34(4): 983-992. ]
[3] 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. [WANG Y Y, QI Y B, CHEN Y, et al. Prediction of soil organic matter based on multi-resolution remote sensing data and random forest algorithm. Acta Pedologica Sinica, 2016, 53(2): 342-354. ]
[4] SREENIVAS K, DADHWAL V K, KUMAR S, et al. Digital mapping of soil organic and inorganic carbon status in India [J]. Geoderma, 2016, 269: 160-173.
[5] CONDIT H R. The spectral reflectance of American soils [J]. Photogrammetric Engineering, 1970, 36: 955-966.
[6] STONER E R, BAUMGARDNER M F. Characteristic variations in reflectance of surface soils [J]. Soil Science Society of American Journal, 1982, 45: 1161-1165.
[7] BEN-DOR E, INBAR Y, CHEN Y. The reflectance spectra of organic matter in the visible near infrared and short wave infrared region (400-2 500 nm) during a control decomposition process [J]. Remote Sensing of Environment, 1997, 61: 1-15.
[8] BEN-DOR E, CHABRILLAT S, DEMATTÊ J A M, et al. Using imaging spectroscopy to study soil properties [J]. Remote Sensing of Environment, 2009, 113: S38-S55.
[9] MADANI A A. Soil salinity detection and monitoring using Landsat data: A case study from Siwa Oasis, Egypt [J]. GIS Science and Remote Sensing, 2005, 42: 171-181.
[10] TAYLOR G R, DAY M, MITCHEKK A, et al. Hyperspectral imagery as a tool for the assessment of stubble content in a fallow soil [C]// Proceedings Workshop on Hyperspectral Remote Sensing and Field Spectroscopy of Agricultural Crops and Forest Vegetation. University of Southern Queensland, Toowoomba, Queensland, Australia, 2006.
[11] DEMATTÊ J A M, NANNI M R, FORMAGGIO A R, et al. Spectral reflectance for the mineralogical evaluation of Brazilian low clay activities soils [J]. Geoderma, 2007, 28: 4537-4559.
[12] BEN-DOR E, LEVIN, N, SINGER A, et al. Quantitative mapping of the soil rubification process on sand dunes using an airborne hyperspectral sensor [J]. Geoderma, 2006, 131: 1-21.
[13] KEMPER T, SOMMER S. Estimate of heavy metal contamination in soils after a mining accident using reflectance spectroscopy [J]. Environment Science Technology, 2002, 36: 2742-2747.
[14] DEMATTÊ J A M, SOUSA A A, ALVES M C, et al. Determining soil water status and other soil characteristics by spectral proximal sensing [J]. Geoderma, 2006, 135: 179-195.
[15] STEVENS A, WESEMAEL B, VANDENSCHRICK G, et al. Detection of carbon stock change in agricultural soils using spectroscopic techniques [J]. Soil Science Society of America Journal, 2006, 70: 844-850.
[16] WIESMEIER M, BARTHOLD F, BLANK B, et al. Digital mapping of soil organic matter stocks using Random forest modeling in a semi-arid steppe ecosystem [J]. Plant Soil, 2011, 340: 7-24.
[17] DI NEZIO M S, PISTONESI M F, FRAGOSO W D, et al. Successive projections algorithm improving the multivariate simultaneous direct spectrophotometric determination of five phenolic compounds in sea water [J]. Microchemical Journal, 2007, 85(2): 194-200
[18] 刘二永, 刘健, 余坤勇, 等. 基于环境因子和R-STPS 的林地土壤有机质预测模型 [J]. 农业机械学报, 2015, 46(1): 133-137. [LIU E R, LIU J, YU K Y, et al. Spatial prediction of forest soil organic matter based on environmental factors and R-STPS interpolation methods. Transactions of the CSAM, 2015, 46(1): 133-137. ]
[19] BREIMAN L. Random forests [J]. Machine Learning, 2001, 45: 5-32.
[20] 方匡南, 吴见彬, 朱建平, 等. 随机森林方法研究综述 [J]. 统计与信息论坛, 2011, 26(3): 32-37. [FANG K N, WU J B, ZHU J P, et al. A review of technologies on random forests. Statistics & Information Forum, 2011, 26(3): 32-37. ]
[21] 李龙, 姚云峰, 秦富仓, 等. 小流域土壤有机碳密度空间变异特征的尺度效应研究 [J]. 土壤, 2014, 46(5): 787-792. [LI L, YAO Y F, QIN F C, et al. Scale-dependency of spatial variability of soil organic carbon density in small watershed. Soils, 2014, 46(5): 787-792. ]
[22] SOMARATHNA P D S N, MALONE B P, MINASNY B. Mapping soil organic carbon content over New South Wales, Australia using local regression Kriging [J]. Geoderma Regional, 2016, 7: 38-48.
[23] COHEN W B. Response of vegetation indices to changes in three measures of leaf water stress [J]. Photogrammetric Engineering and Remote Sensing, 1991, 57: 195-202.
[24] ROUSE J W, HAAS R H, SCHELL J A, et al. Monitoring vegetation systems in the Great Plains with ERTS [C]// Proceedings of the Third ERTS Symposium. NASA SP-351. Washington, DC, USA, 1973: 309-317.
[25] BROWN L, CHEN J M, LEBLANC S G, et al. A shortwave infrared modification to the simple ratio for LAI retrieval in boreal forests: An image and model analysis [J]. Remote Sensing of Environment, 2000, 71: 16-25.
[26] NELLIS M D, BRIGGS J M. Transformed vegetation index for measuring spatial variation in drought impacted biomass on Konza Prairie, Kansas [J]. Transactions of the Kansas Academy of Science, 1992, 95: 93-99.
[27] BREIMAN L. Random forests [J]. Machine Learning, 2001, 45: 5-32.
[28] MULDER V L, DE BRUIN S, SCHAEPMAN M E, et al. The use of remote sensing in soil and terrain mapping—A review [J]. Geoderma, 2011, 162: 1-19.
[29] BEN-DOR E, GOLDSHALAGER N, BRAUN O, et al. Monitoring of infiltration rate in semiarid soils using airborne hyperspectral technology [J]. International Journal of Remote Sensing, 2004, 25: 1-18.
[30] 巫振富, 赵彦锋, 齐力, 等. 复杂景观区土壤有机质预测模型的尺度效应 [J]. 土壤学报, 2013, 50(2): 296-305. [WU Z F, ZHAO Y F, QI L, et al. Effect of scale of model on prediction of soil organic matter in complex landscape region. Acta Pedologica Sinica, 2013, 50(2): 296-305. ]
[31] 刘京. 陕西省土壤信息系统的建立及应用 [D]. 杨凌: 西北农林科技大学, 2010. [LIU J. Establishment and Application of Soil Information System in Shaanxi Province. Yangling: Northwest A&F University, 2010. ]
[32] 赵业婷. 基于GIS的陕西省关中地区耕地土壤养分空间特征及其变化研究 [D]. 杨凌: 西北农林科技大学, 2015. [ZHAO Y T. Spatial Characteristics and Changes of Soil Nutrients in Cultivated Land of Guanzhong Region in Shaanxi Province Based on GIS. Yangling: Northwest A&F University, 2015. ]
[33] CROFT H, KUHN N J, ANDERSON K. On the use of remote sensing techniques for monitoring spatio-temporal soil organic carbon dynamics in agricultural systems [J]. Catena, 2012, 94: 64-74.
[34] SUG H. Applying randomness effectively based on random forests for classification task of datasets of insufficient information [J]. Journal of Applied Mathematics, 2012, 2012: 1239-1257.

基于遥感与随机森林算法的陕西省土壤有机质空间预测

Soil Organic Matter Prediction Based on Remote Sensing Data and Random Forest Model in Shaanxi Province

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

Metrics

本文评价

推荐阅读 0

[1]	耿甜伟, 陈海, 张行, 史琴琴, 刘迪. 基于GWR的陕西省生态系统服务价值时空演变特征及影响因素分析[J]. 自然资源学报, 2020, 35(7): 1714-1727.
[2]	李可利, 张鑫. 基于ANFIS的陕西省参考作物蒸散量计算[J]. 自然资源学报, 2020, 35(6): 1472-1483.
[3]	张浩, 冯淑怡, 曲福田. 耕地保护、建设用地集约利用与城镇化耦合协调性研究[J]. 自然资源学报, 2017, 32(6): 1002-1015.
[4]	张欣莹, 解建仓, 刘建林, 朱记伟, 姜仁贵. 基于熵权法的节水型社会建设区域类型分析[J]. 自然资源学报, 2017, 32(2): 301-309.
[5]	任怡, 王义民, 畅建霞, 黄强. 陕西省水资源供求指数和综合干旱指数及其时空分布[J]. 自然资源学报, 2017, 32(1): 137-151.
[6]	周丹, 张勃, 任培贵, 张春玲, 杨尚武, 季定民. 基于标准化降水蒸散指数的陕西省近50 a干旱特征分析[J]. 自然资源学报, 2014, 29(4): 677-688.
[7]	贺三维, 潘鹏, 诸云强, 陈鹏飞. 农用地集约利用评价的新模型研究[J]. 自然资源学报, 2012, 27(3): 460-467.
[8]	畅建霞, 姜瑾. 引汉济渭调水工程水资源配置研究[J]. 自然资源学报, 2011, 26(1): 110-118.
[9]	王雁林, 王文科, 杨泽元. 陕西省渭河流域生态环境需水量探讨[J]. 自然资源学报, 2004, 19(1): 69-78.