随机森林回归模型用于土壤重金属含量多光谱遥感反演

doi:10.13474/j.cnki.11-2246.2021.345

测绘通报 ›› 2021, Vol. 0 ›› Issue (11): 92-95.doi: 10.13474/j.cnki.11-2246.2021.345

随机森林回归模型用于土壤重金属含量多光谱遥感反演

王腾军^1,2, 方珂³, 杨耘^1,2, 张祥东⁴

1. 长安大学地质工程与测绘学院, 陕西西安 710054;
2. 地理信息工程国家重点实验室长安大学合作部, 陕西西安 710075;
3. 西安航天天绘数据技术有限公司, 陕西西安 710100;
4. 南通智能感知研究院, 江苏南通 226010

收稿日期:2021-01-21 修回日期:2021-08-07 出版日期:2021-11-25 发布日期:2021-12-02
作者简介:王腾军(1967-),男,博士,副教授,主要从事国土资源调查、资源环境承载力评价等方面的研究。E-mail:wangtj@chd.edu.cn
基金资助:
中央高校基本科研业务费（300102269205；300102269304）；国土资源部退化及未利用土地整治工程重点实验室开放基金（SXJD2017-3）

Multi-spectral remote sensing inversion of soil heavy metal content using random forest regression model

WANG Tengjun^1,2, FANG Ke³, YANG Yun^1,2, ZHENG Xiangdong⁴

1. College of Geology Engineering and Surveying, Chang'an University, Xi'an 710054, China;
2. Cooperation Department of Chang'an University, State Key Laboratory of Geographic Information Engineering, Xi'an 710075, China;
3. Xi'an Aerospace Remote Sensing Data Technology Corporation, Xi'an 710100, China;
4. Nantong Academy of Intelligent Sensing, Nantong 226010, China

Received:2021-01-21 Revised:2021-08-07 Online:2021-11-25 Published:2021-12-02

摘要/Abstract

摘要： 本文以陕西省柞水县大西沟矿区为研究区域，通过实地采集土壤样本，结合在Landsat 8多光谱遥感影像上提取的辐射亮度值和光谱衍生指数，以及从ASTER GDEM提取的3种地形因素，通过相关性分析确定了建模因子，并以K折交叉验证法建立了砷、铜、铅3种重金属元素的随机森林回归模型。试验结果表明，所建立模型的预测精度优于多元线性回归模型和CART模型，可见随机森林回归模型适用于在小样本情况下的矿区重金属含量反演。经现场调查，空间反演结果与实际情况较符合，证明了基于多光谱遥感的随机森林回归模型在矿区土壤重金属反演中的准确性。

关键词: 土壤重金属反演, 多光谱遥感, K折交叉验证, 随机森林回归模型

Abstract: This paper takes Daxigou mining area in Zhashui county, Shaanxi province as the research area. By collecting soil samples on the spot, combining with radiation luminance value and spectral derivative index extracted from Landsat 8 multi-spectral remote sensing images, and three topographic factors extracted from ASTER GDEM, modeling factors are determined through correlation analysis. The random forest regression model of arsenic, copper and lead is established by K-fold cross validation. The experimental results show that the prediction accuracy of the established model is better than that of the multiple linear regression model and the CART model, which verifies that the random forest regression model is suitable for the heavy metal content inversion in the case of small samples. Through the field investigation, the spatial inversion results are in good agreement with the actual situation, which proves the accuracy of the random forest regression model based on multi-spectral remote sensing in the soil heavy metal inversion of mining area.

Key words: soil heavy metal inversion, multispectral remote sensing, K-fold cross validation, random forest regression model

中图分类号:

王腾军, 方珂, 杨耘, 张祥东. 随机森林回归模型用于土壤重金属含量多光谱遥感反演[J]. 测绘通报, 2021, 0(11): 92-95.

WANG Tengjun, FANG Ke, YANG Yun, ZHENG Xiangdong. Multi-spectral remote sensing inversion of soil heavy metal content using random forest regression model[J]. Bulletin of Surveying and Mapping, 2021, 0(11): 92-95.

参考文献

[1] CAI L M, XU Z C, REN M Z, et al. Source identification of eight hazardous heavy metals in agricultural soils of Huizhou, Guangdong province, China[J]. Ecotoxicology and Environmental Safety, 2012, 78(3):2-8.
[2] 张甘霖, 赵玉国, 杨金玲, 等. 城市土壤环境问题及其研究进展[J].土壤学报,2007,44(5):925-933.
[3] 陈雅丽, 翁莉萍, 马杰, 等. 近十年中国土壤重金属污染源解析研究进展[J]. 农业环境科学学报,2019,38(10):2219-2238.
[4] KOOISTRA L, SALAS E, CLEVERS J, et al. Exploring field vegetation reflectance as an indicator of soil contamination in river floodplains[J]. Environmental Pollution, 2004, 127:281-290.
[5] KOOISTRA L, LEUVENJR S, WEHRENSI R, et al. A comparison of methods to relate grass reflectance to soil metal contamination[J]. International Journal of Remote Sensing, 2003, 20:4995-5010.
[6] YI P, RANIA K,KABINDRA A, et al. Digital mapping of toxic metals in qatari soils using remote sensing and ancillary data[J]. Remote Sensing, 2016, 8(12):37-43.
[7] 屈永华, 焦思红, 刘素红, 等. 从高光谱卫星数据中提取植被覆盖区铜污染信息[J].光谱学与光谱分析,2015, 35(11):3176-3181.
[8] 郭云开, 钱佳, 蒋明, 等. 基于核偏最小二乘的矿区土壤Cu含量高光谱反演[J]. 土壤通报, 2019, 50(1):58-62.
[9] 魏钰, 陈奕云, 徐璐, 等. 基于鲜土反射光谱的农田土壤重金属含量估算[J].国土资源科技管理,2021,38(1):118-129.
[10] 袁自然, 魏立飞, 张杨熙, 等.优化CARS结合PSO-SVM算法农田土壤重金属砷含量高光谱反演分析[J].光谱学与光谱分析,2020,40(2):567-573.
[11] BREIMAN L. Random forests[J]. Machine Learning, 2001,45(1):5-32.
[12] 程彬, 姜琦刚, 湛邵斌. 利用可见光/近红外-短波红外光谱预测土壤总氮含量的研究[J]. 安徽农业科学, 2007, 35(10):3009-3014.
[13] 代鹏飞, 黄德娟, 王帅, 等. 某铀矿区农田土壤重金属污染综合评价[J].土壤通报,2021,52(1):198-202.
[14] 张素梅,王宗明,张柏,等. 利用地形和遥感数据预测土壤养分空间分布[J].农业工程学报,2010,26(5):188-194.
[15] 李航.统计学习方法[M].北京:清华大学出版社,2019:67-83.

随机森林回归模型用于土壤重金属含量多光谱遥感反演

Multi-spectral remote sensing inversion of soil heavy metal content using random forest regression model

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	孔瑞瑶, 谢涛, 马明, 孔瑞林. CatBoost模型在水深反演中的应用[J]. 测绘通报, 2022, 0(7): 33-37.
[2]	马腾, 刘全明, 孙红. 多源遥感技术在土地利用分类中的应用[J]. 测绘通报, 2018, 0(8): 56-61.