基于优化随机森林回归模型的土壤盐渍化反演

doi:10.12082/dqxxkx.2021.200711

地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (9): 1662-1674.doi: 10.12082/dqxxkx.2021.200711

基于优化随机森林回归模型的土壤盐渍化反演

杨练兵¹^,²^,³(), 陈春波¹^,²^,³^,⁴, 郑宏伟¹^,²^,³^,⁴^,^*(), 罗格平¹^,²^,³^,⁴, 尚白军¹^,³, Olaf Hellwich¹^,⁵

1. 中国科学院新疆生态与地理研究所荒漠与绿洲生态国家重点实验室,乌鲁木齐 830011
2. 新疆维吾尔自治区遥感与地理信息系统应用重点实验室,乌鲁木齐 830011
3. 中国科学院大学,北京 100049
4. 中国科学院中亚生态与环境研究中心, 乌鲁木齐 830011
5. 德国柏林工业大学计算机视觉和遥感研究所,柏林 10623

收稿日期:2020-11-26 出版日期:2021-09-25 发布日期:2021-11-25
通讯作者: *郑宏伟（1972— ）,男,山东潍坊人,博士,研究员,主要从事机器智能和模式分析,生态与地理及气候效应、遥感与GIS应用研究。E-mail: hzheng@ms.xjb.ac.cn
作者简介:杨练兵（1993— ）,男,湖北鄂州人,硕士生,主要从事遥感与地理信息系统应用研究。E-mail: yanglianbing18@mails. ucas.ac.cn
基金资助:
国家自然科学基金项目(41877012);中国科学院一带一路项目(2018-YDYLTD-002);中国科学院特色研究所项目(TSS-2015-014-FW-1-3)

Retrieval of Soil Salinity Content based on Random Forests Regression Optimized by Bayesian Optimization Algorithm and Genetic Algorithm

YANG Lianbing¹^,²^,³(), CHEN Chunbo¹^,²^,³^,⁴, ZHENG Hongwei¹^,²^,³^,⁴^,^*(), LUO Geping¹^,²^,³^,⁴, SHANG Baijun¹^,³, Olaf Hellwich¹^,⁵

1. State Key Laboratory of Dessert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi 830011, China
2. Key Laboratory of GIS & RS Application Xinjiang Uygur Autonomous Region, Urumqi 830011, China
3. University of Chinese Academy of Sciences, Beijing 100049, China
4. Research Center for Ecology and Environment of Central Asia, Chinese Academy of Sciences, Urumqi 830011, China
5. Technical University of Berlin Tech Univ Berlin, Comp Vis & Remote Sensing, Berlin 10623, Germany

Received:2020-11-26 Online:2021-09-25 Published:2021-11-25
Supported by:
National Natural Science Foundation of China(41877012);The Belt and Road program of Chinese academy of sciences(2018-YDYLTD-002);Characteristic Institutes Main Service Program（Program1,Topic3） of Chinese Academy of Sciences(TSS-2015-014-FW-1-3)

摘要/Abstract

摘要：

当前应用于土壤盐分含量（Soil Salinity Content, SSC）反演的随机森林回归（Random Forests Regression, RFR）较少关注对模型精度影响较大的反演参数子集和模型参数的同步优化。本研究选择渭-库绿洲和奇台绿洲为实验区,基于Landsat-5 TM、SRTM、MOD11A2.006遥感数据构建反演参数。首先,利用弹性网络（Elastic Net, EN）筛选出反演参数子集,然后利用遗传算法（Genetic Algorithm, GA）和贝叶斯优化算法（Bayesian Optimization Algorithm, BOA）分别优化随机森林回归（Random Forests Regression, RFR）参数,建立反演参数子集和模型参数分步优化的RFR模型（EN-GA-RFR、EN-BOA-RFR）。建立利用GA和BOA分别同步优化反演参数子集和模型参数的RFR模型（GA-RFR、BOA-RFR）。在每个实验区,对比EN-GA-RFR、EN-BOA-RFR、GA-RFR、BOA-RFR的预测精度。最后分析每个实验区各类盐渍土的空间分布,并对2个实验区的反演参数进行对比分析。结果表明：每个实验区模型预测精度由高到低的排序均为BOA-RFR>GA-RFR>EN-BOA-RFR=EN-GA-RFR,整体上BOA的优化性能均好于GA;渭-库绿洲和奇台绿洲面积占比最大的盐渍土类型分别为盐渍土和中度盐渍土;反演参数对SSC的表征能力存在空间分异性。

关键词: 土壤盐分含量, 同步优化, 随机森林回归, 贝叶斯优化算法, 遗传算法, 弹性网络, 反演参数子集, 模型参数

Abstract:

Random Forests Regression (RFR) is often used to inverse Soil Salinity Content (SSC)nowadays. However, the most important impact factors on the model accuracy such as the synchronization optimization of the inversion parameters subset and the model parameters have not been studied carefully in the applications of RFR. In this study, we selected Weiku Oasis and Qitai Oasis as experiment areas. The inversion parameters were constructed based on remote sensing data, including Landsat-5 TM, SRTM, and MOD11A2.006. Firstly, we applied Elastic Net (EN) to select a subset of the inversion parameters, developed Genetic Algorithm (GA) and Bayesian Optimization Algorithm (BOA) to optimize RFR, and established RFR models (EN-GA-RFR, EN-BOA-RFR) for stepwise optimization of inversion parameters subset and model parameters. Then we used GA and BOA to simultaneously optimize the inversion parameters subset and model parameters based on the combination methods of RFR, including GA-RFR and BOA-RFR methods. Furthermore, in each experiment area, we compared the prediction accuracy of EN-GA-RFR, EN-BOA-RFR, GA-RFR, and BOA-RFR. In this way, the spatial distributions of various saline soils in each experiment area were analyzed. The inversion parameters of the two experiment areas were also compared and analyzed. The results show that the order of model prediction accuracy in each study area from high to low is BOA-RFR>GA-RFR>EN-BOA-RFR=EN-GA-RFR. Overall, BOA had a better optimization performance than GA. Finally, the results show that the types of saline soils with the largest area in Ku Oasis and Qitai Oasis are saline soil and moderate saline soil, respectively. The inversion parameters have spatial differentiation in the characterization ability of SSC.

Key words: soil salinity content, synchronization optimization, Random Forests Regression, Bayesian Optimization Algorithm, Genetic Algorithm, Elastic Net, inversion parameters subset, model parameters

杨练兵, 陈春波, 郑宏伟, 罗格平, 尚白军, Olaf Hellwich. 基于优化随机森林回归模型的土壤盐渍化反演[J]. 地球信息科学学报, 2021, 23(9): 1662-1674.DOI:10.12082/dqxxkx.2021.200711

YANG Lianbing, CHEN Chunbo, ZHENG Hongwei, LUO Geping, SHANG Baijun, Olaf Hellwich. Retrieval of Soil Salinity Content based on Random Forests Regression Optimized by Bayesian Optimization Algorithm and Genetic Algorithm[J]. Journal of Geo-information Science, 2021, 23(9): 1662-1674.DOI:10.12082/dqxxkx.2021.200711

图/表 15

图1

图2

图3

图4

图5

图6

表1

表2

SSC反演参数

反演参数类型	名称
植被指数	归一化植被指数（NDVI）^[28]、扩展的归一化植被指数（ENDVI）^[29]、增强植被指数（EVI）^[28]、扩展的增强植被指数（EEVI）^[29]、差值植被指数（DVI）^[30]、修改型土壤调节植被指数（MSAVI）^[30]、比值植被指数（RVI）^[30]、大气阻抗植被指数（ARVI）^[30]、广义差分植被指数（GDVI）^[28]、非线性植被指数（NLI）^[28]、联合光谱响应指数（COSRI）^[31]、绿色大气阻抗指数（GARI）^[28]、转换型植被指数（TVI）^[32]、增强型差值植被指数（EDVI）^[29]、三波段差分指数（TGDVI）^[29]
盐分指数	盐分指数（SI_T）^[33]、盐分指数（SI）^[28]、盐分指数（SI1）^[28]、盐分指数（SI2）^[28]、盐分指数（SI3）^[28]、盐分指数（S1）^[28]、盐分指数（S2）^[28]、盐分指数（S3）^[28]、盐分指数（S5）^[28]、盐分指数（S6）^[28]、盐分指数（INT1）^[28]、盐分指数（INT2）^[28]、归一化盐分指数（NDSI）^[28]、冠层响应盐度指数（CRSI）^[34]
下垫面反射特性	短波红外地表反照度（Albedo_short）^[35]、可见光地表反照度（Albedo_visible）^[35]
缨帽变换因子	绿度指数（GVI）^[36]、亮度指数（BI）^[36]、湿度指数（WI）^[36]
特征空间	植被指数-盐分指数特征空间（MSI）^[37]、植被指数-湿度指数特征空间（MWI）^[38]、湿度指数-盐分指数特征空间（WSI）^[38]、反照率-植被指数特征空间（AVI）^[39]、植被指数-盐分指数特征空间（NSI）^[38]
地形参数	高程（Elevation）^[40]、坡度（Slop）^[40]、坡向（Aspect）^[40]、地表粗糙度（Roughness）^[40]
原始波段反射率	蓝波段（Blue）、绿波段（Green）、红波段（Red）、近红外波段（Nir）、短波红外波段1（Swir1）、短波红外波段2（Swir2）
温度变量	非生长季最大值（LST1_max）、非生长季最小值（LST1_min）、非生长季均值（LST1_mean）、生长季最大值（LST2_max）、生长季最小值（LST2_min）、生长季均值（LST2_mean）、全年均值（LST_mean）

表2

图7

表3

图8

表4

表5

图9

图10

参考文献 45

[1]	Daliakopoulos I N, Tsanis I K, Koutroulis A, et al. The threat of soil salinity: A European scale review[J]. Science of the Total Environment, 2016, 573:727-739. doi: 10.1016/j.scitotenv.2016.08.177
[2]	朱宏伟, 夏军, 曹国栋, 等. 盐渍化弃耕地土壤盐分动态及其影响因素[J]. 土壤, 2013, 45(2):1339-1345.
	[ Zhu H W, Xia J, Cao G D, et al. Dynamic change of soil salinity in salinization abandoned farmland and affecting factors[J]. Soils, 2013, 45(2):1339-1345. ]
[3]	Xu H T, Chen C B, Zheng H W, et al. AGA-SVR-based selection of feature subsets and optimization of parameter in regional soil salinization monitoring[J]. International Journal of Remote Sensing, 2020, 41(12):4470-4495. doi: 10.1080/01431161.2020.1718239
[4]	Wang X P, Zhang F, Ding J L, et al. Estimation of soil salt content (SSC) in the Ebinur Lake Wetland National Nature Reserve (ELWNNR), Northwest China, based on a Bootstrap-BP neural network model and optimal spectral indices[J]. Science of the Total Environment, 2018, 615:918-930. doi: 10.1016/j.scitotenv.2017.10.025
[5]	王飞, 杨胜天, 丁建丽, 等. 环境敏感变量优选及机器学习算法预测绿洲土壤盐分[J]. 农业工程学报, 2018, 34(22):102-110.
	[ Wang F, Yang S T, Ding J L, et al. Environmental sensitive variable optimization and machine learning algorithm using in soil salt prediction at oasis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(22):102-110. ]
[6]	张智韬, 韩佳, 王新涛, 等. 基于全子集-分位数回归的土壤含盐量反演研究[J]. 农业机械学报, 2019, 50(10):142-152.
	[ Zhang Z T, Han J, Wang X T, et al. Soil salinity inversion based on best subsets-quantile regression model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(10):142-152. ]
[7]	王丹阳, 陈红艳, 王桂峰, 等. 无人机多光谱反演黄河口重度盐渍土盐分的研究[J]. 中国农业科学, 2019, 52(10):1698-1709.
	[ Wang D Y, Chen H Y, Wang G F, et al. Salinity inversion of severe saline soil in the Yellow River estuary based on UAV multi-spectra[J]. Scientia Agricultura Sinica, 2019, 52(10):1698-1709. ]
[8]	Wei G F, Li Y, Zhang Z T, et al. Estimation of soil salt content by combining UAV-borne multispectral sensor and machine learning algorithms[J]. Peer Journal, 2020, 8:e9087. doi: 10.7717/peerj.9087
[9]	Pang G J, Wang T, Liao J E, et al. Quantitative model based on field-derived spectral characteristics to estimate soil salinity in Minqin County, China[J]. Soil Science Society of America Journal, 2014, 78(2):546-555. doi: 10.2136/sssaj2013.06.0241
[10]	徐红涛, 陈春波, 郑宏伟, 等. 基于相关分析和自适应遗传算法的盐渍化建模变量和参数优选[J]. 地球信息科学学报, 2020, 22(7):1497-1509.
	[ Xu H T, Chen C B, Zheng H W, et al. Correlation analysis and adaptive genetic algorithm based feature subset and model parameter optimization in salinization monitoring[J]. Journal of Geo-information Science, 2020, 22(7):1497-1509. ]
[11]	Wang F, Yang S T, Wei Y, et al. Characterizing soil salinity at multiple depth using electromagnetic induction and remote sensing data with random forests: A case study in Tarim River Basin of southern Xinjiang, China[J]. Science of the Total Environment, 2021, 754:142030. doi: 10.1016/j.scitotenv.2020.142030
[12]	Wu W C, Zucca C, Muhaimeed A S, et al. Soil salinity prediction and mapping by machine learning regression in Central Mesopotamia, Iraq[J]. Land Degradation & Development, 2018, 29(11):4005-4014. doi: 10.1002/ldr.3148
[13]	蒙莉娜, 丁建丽, 王敬哲, 等. 基于环境变量的渭干河-库车河绿洲土壤盐分空间分布[J]. 农业工程学报, 2020, 36(1):175-181.
	[ Meng L N, Ding J L, Wang J Z, et al. Spatial distribution of soil salinity in Ugan-Kuqa River delta oasis based on environmental variables[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(1):175-181. ]
[14]	Zou H, Hastie T. Regularization and variable selection via the elastic net[J]. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2005, 67(2):301-320. doi: 10.1111/rssb.2005.67.issue-2
[15]	Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32. doi: 10.1023/A:1010933404324
[16]	Holland J H. Genetic algorithms and the optimal allocation of trials[J]. SIAM Journal on Computing, 1973, 2(2):88-105. doi: 10.1137/0202009
[17]	席裕庚, 柴天佑, 恽为民. 遗传算法综述[J]. 控制理论与应用, 1996, 13(6):697-708.
	[ Xi Y G, Chai T Y, Yun W M. Survey on genetic algorithm[J]. Control Theory & Applications, 1996, 13(6):697-708. ]
[18]	Pelikan M, Goldberg D E, Cantu-Paz E. BOA: The Bayesian optimization algorithm [C]. Gecco-99: Proceedings Of the Genetic And Evolutionary Computation Conference, 1999,525-532.
[19]	王圣尧, 王凌, 方晨, 等. 分布估计算法研究进展[J]. 控制与决策, 2012, 27(7):961-966,974.
	[ Wang S Y, Wang L, Fang C, et al. Advances in estimation of distribution algorithms[J]. Control and Decision, 2012, 27(7):961-966,974. ]
[20]	崔佳旭, 杨博. 贝叶斯优化方法和应用综述[J]. 软件学报, 2018, 29(10):3068-3090.
	[ Cui J X, Yang B. Survey on Bayesian optimization methodology and applications[J]. Journal of Software, 2018, 29(10):3068-3090. ]
[21]	樊爱宛, 时合生. 基于特征选择和SVM参数同步优化的网络入侵检测[J]. 北京交通大学学报, 2013, 37(5):58-61.
	[ Fan A W, Shi H S. Network intrusion detection based on simultaneous optimization of features selection and parameters of support vector machine[J]. Journal of Beijing Jiaotong University, 2013, 37(5):58-61. ]
[22]	阿布都沙拉木·吐鲁甫, 买买提·沙吾提, 马春玥, 等. 基于SEBAL模型的渭-库绿洲蒸散量特征及影响因子研究[J]. 地球信息科学学报, 2018, 20(9):1361-1372. doi: 180043/dqxxkx.2018.180043
	[ Abdusalam T, Mamat S, Ma C Y, et al. Characteristics and impact factors of evapotranspiration in Ugan and Kuqa Rivers Delta Oasis based on SEBAL model[J]. Journal of Geo-information Science, 2018, 20(9):1361-1372.]
[23]	高婷婷, 丁建丽, 哈学萍, 等. 基于流域尺度的土壤盐分空间变异特征——以渭干河-库车河流域三角洲绿洲为例[J]. 生态学报, 2010, 30(10):2695-2705.
	[ Gao T T, Ding J L, Ha X P, et al. The spatial variability of salt content based on river basin scale: A case study of the delta oasis in Weigan-Kuqa Watershed[J]. Acta Ecologica Sinica, 2010, 30(10):2695-2705. ]
[24]	李根生, 曾强, 董敬宣, 等. 准东矿区邻近奇台绿洲地下水位变化趋势分析[J]. 中国矿业, 2017, 26(5):148-153.
	[ Li G S, Zeng Q A, Dong J X, et al. Analysis of the change of ground water level in Qitai oasis nearby eastern Junggar coalfield[J]. China Mining Magazine, 2017, 26(5):148-153. ]
[25]	Gorelick N, Hancher M, Dixon M, et al. Google Earth Engine: Planetary-scale geospatial analysis for everyone[J]. Remote Sensing of Environment, 2017, 202:18-27. doi: 10.1016/j.rse.2017.06.031
[26]	孟阳阳, 刘冰, 刘婵. 荒漠绿洲湿地土壤水热盐动态过程及其影响机制[J]. 中国沙漠, 2019, 39(1):149-160.
	[ Meng Y Y, Liu B, Liu C. Dynamic process of water-heat-salt in soil and the mechanism in the desert oasis wetland[J]. Journal of Desert Research, 2019, 39(1):149-160. ]
[27]	何宝忠, 丁建丽, 李焕, 等. 新疆植被物候时空变化特征[J]. 生态学报. 2018, 38(6):2139-2155.
	[ He B Z, Ding J L, Li H, et al. Spatiotemporal variation of vegetation phenology in Xinjiang from 2001 to 2016[J]. Acta Ecologica Sinica, 2018, 38(6):2139-2155. ]
[28]	Peng J E, Biswas A, Jiang Q S, 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
[29]	王飞, 丁建丽, 魏阳, 等. 基于Landsat系列数据的盐分指数和植被指数对土壤盐度变异性的响应分析——以新疆天山南北典型绿洲为例[J]. 生态学报, 2017, 37(15):5007-5022.
	[ Wang F, Ding J L, Wei Y, et al. Sensitivity analysis of soil salinity and vegetation indices to detect soil salinity variation by using Landsat series images: Applications in different oases in Xinjiang, China[J]. Acta Ecologica Sinica, 2017, 37(15):5007-5022. ]
[30]	Guo S S, Ruan B Q, Chen H R, et al. Characterizing the spatiotemporal evolution of soil salinization in Hetao Irrigation District (China) using a remote sensing approach[J]. International Journal of Remote Sensing, 2018, 39(20):6805-6825. doi: 10.1080/01431161.2018.1466076
[31]	Fernández-Buces N, Siebe C, Cram S, et al. Mapping soil salinity using a combined spectral response index for bare soil and vegetation: A case study in the former lake Texcoco, Mexico[J]. Journal of Arid Environments, 2006, 65(4):644-667. doi: 10.1016/j.jaridenv.2005.08.005
[32]	贺中华, 陈晓翔, 梁虹, 等. 基于植被指数的喀斯特流域赋水动态变化遥感监测研究——以贵州省为例[J]. 国土与自然资源研究, 2012(4):48-51.
	[ He Z H, Chen X X, Liang H, et al. Study of remote sensing monitoring of Karst basin water-holding dynamic changing based on vegetation indices—taking Guizhou Province as a case[J]. Territory & Natural Resources Study, 2012(4):48-51. ]
[33]	Tripathi N K, Brijesh K R. Spatial modelling of soil alkalinity in GIS environment using IRS data [C]// Kuala Lumpur:the 18th Asian Conference in Remote Sensing, 1997:81-86.
[34]	Scudiero E, Skaggs T H, Corwin D L. Regional-scale soil salinity assessment using Landsat ETM+ canopy reflectance[J]. Remote Sensing of Environment, 2015, 169:335-343. doi: 10.1016/j.rse.2015.08.026
[35]	Liang S L. Narrowband to broadband conversions of land surface albedo I: Algorithms[J]. Remote Sensing of Environment, 2001, 76(2):213-238. doi: 10.1016/S0034-4257(00)00205-4
[36]	Crist E P. A TM Tasseled Cap equivalent transformation for reflectance factor data[J]. Remote Sensing of Environment, 1985, 17(3):301-306. doi: 10.1016/0034-4257(85)90102-6
[37]	边玲玲, 王卷乐, 郭兵, 等. 基于特征空间的黄河三角洲垦利县土壤盐分遥感提取[J]. 遥感技术与应用, 2020, 35(1):211-218.
	[ Bian L L, Wang J L, Guo B, et al. Remote sensing extraction of soil salinity in Yellow River Delta Kenli County based on feature space[J]. Remote Sensing Technology and Application, 2020, 35(1):211-218. ]
[38]	李艳华, 丁建丽, 孙永猛, 等. 基于三维特征空间的土壤盐渍化遥感模型[J]. 水土保持研究, 2015, 22(4):113-117,121.
	[ Li Y H, Ding J L, Sun Y M, et al. Remote sensing monitoring models of soil salinization based on the three dimensional feature space of MSAVI-WI-SI[J]. Research of Soil and Water Conservation, 2015, 22(4):113-117,121. ]
[39]	冯娟, 丁建丽, 魏雯瑜. 基于Albedo-MSAVI特征空间的渭库绿洲土壤盐渍化研究[J]. 中国农村水利水电, 2018(2):147-152.
	[ Feng J A, Ding J L, Wei W Y. A study of soil salinization in Weigan and kuqa rivers oasis based on albedo-MSAVI feature space[J]. China Rural Water and Hydropower, 2018(2):147-152. ]
[40]	Vermeulen D, Van Niekerk A. Machine learning performance for predicting soil salinity using different combinations of geomorphometric covariates[J]. Geoderma, 2017, 299:1-12. doi: 10.1016/j.geoderma.2017.03.013
[41]	李敏, 卡米力·木依丁.特征选择方法与算法的研究[J]. 计算机技术与发展, 2013, 23(12):16-21.
	[ Li M, Kamil M. Research on feature selection methods and algorithms[J]. Computer Technology and Development, 2013, 23(12):16-21. ]
[42]	乔木, 周生斌, 卢磊, 等. 新疆渭干河流域土壤盐渍化时空变化及成因分析[J]. 地理科学进展, 2012, 31(7):904-910.
	[ Qiao M, Zhou S B, Lu L, et al. Causes and spatial-temporal changes of soil salinization in weigan river basin, Xinjiang[J]. Progress in Geography, 2012, 31(7):904-910. ]
[43]	丁建丽, 陈文倩, 陈芸. 干旱区土壤盐渍化灾害预警——以渭-库绿洲为例[J]. 中国沙漠, 2016, 36(4):1079-1086.
	[ Ding J L, Chen W Q, Chen Y. Soil salinization disaster warning in Arid Zones: A case study in the Ugan-Kuqa Oasis[J]. Journal of Desert Research, 2016, 36(4):1079-1086.]
[44]	张芳, 熊黑钢, 田源, 等. 区域尺度地形因素对奇台绿洲土壤盐渍化空间分布的影响[J]. 环境科学研究, 2011, 24(7):731-739.
	[ Zhang F, Xiong H G, Tian Y A, et al. Impacts of regional topographic factors on spatial distribution of soil salinization in Qitai oasis[J]. Research of Environmental Sciences, 2011, 24(7):731-739. ]
[45]	Gregorutti B, Michel B, Saint-Pierre P. Correlation and variable importance in random forests[J]. Statistics and Computing, 2017, 27(3):659-678. doi: 10.1007/s11222-016-9646-1

采样点类别	采样点/个	最大值/（g/kg）	最小值/（g/kg）	均值/（g/kg）	变异系数/%
渭-库绿洲	32	131.50	0.10	37.98	97.52
奇台绿洲	58	45.23	0.11	16.84	61.79

超参数类型	参数标识	取值区间
决策树数量	N_est	[2,200]
决策树最大深度	D_tre	[2,80]

采样点区域	模型	基于建模集的精度统计		基于测试集的精度统计
采样点区域	模型	RMSE/ （g/kg）	R²	RMSE/ （g/kg）	R²	RPD
渭-库绿洲	EN-BOA-RFR	13.77	0.86	13.77	0.85	2.75
	EN-GA-RFR	13.77	0.86	13.77	0.85	2.75
	BOA-RFR	11.30	0.90	11.25	0.90	3.38
	GA-RFR	13.27	0.87	13.10	0.87	2.92
奇台绿洲	EN-BOA-RFR	5.60	0.68	5.26	0.67	2.41
	EN-GA-RFR	5.60	0.68	5.26	0.67	2.41
	BOA-RFR	4.83	0.76	4.52	0.75	2.87
	GA-RFR	5.11	0.73	4.80	0.72	2.66

基于优化随机森林回归模型的土壤盐渍化反演

Retrieval of Soil Salinity Content based on Random Forests Regression Optimized by Bayesian Optimization Algorithm and Genetic Algorithm

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 45

相关文章 13

Metrics

本文评价

推荐阅读 0

采样点区域	模型	目标函数值	收敛代数	反演参数个数	N_est	D_tre
渭-库绿洲	EN-BOA-RFR	0.12	90	35	6	13
	EN-GA-RFR	0.12	136	35	6	13
	BOA-RFR	0.16	137	27	11	29
	GA-RFR	0.14	163	30	5	23
奇台绿洲	EN-BOA-RFR	0.25	205	36	32	42
	EN-GA-RFR	0.25	180	36	32	42
	BOA-RFR	0.31	143	25	37	45
	GA-RFR	0.29	231	22	182	15

[1]	张菊, 房世波, 刘汉湖. 基于微波数据与光学数据集成的机器学习技术在作物产量估算中的应用[J]. 地球信息科学学报, 2021, 23(6): 1082-1091.
[2]	张毅, 朱攀. 电动出租车专用充电场站选址模型研究[J]. 地球信息科学学报, 2021, 23(5): 802-811.
[3]	朱守杰, 杜世宏, 李军, 商硕硕, 杜守基. 融合多源空间数据的城镇人口分布估算[J]. 地球信息科学学报, 2020, 22(8): 1607-1616.
[4]	杨露, 颉耀文, 宗乐丽, 邱天, 焦继宗. 基于多目标遗传算法和FLUS模型的西北农牧交错带土地利用优化配置[J]. 地球信息科学学报, 2020, 22(3): 568-579.
[5]	龙诗科, 孙山林, 赵海盟. 基于滑模和ESO的四旋翼飞行器遥感机动观测姿态控制[J]. 地球信息科学学报, 2019, 21(4): 532-541.
[6]	高会然, 秦承志, 朱良君, 朱阿兴, 刘军志, 吴辉. 以坡位为空间配置单元的流域管理措施情景优化方法[J]. 地球信息科学学报, 2018, 20(6): 781-790.
[7]	曲小康, 芮小平, 韩莹, 李祥琛, 伍彬. 栅格成本距离计算的改进蚁群算法[J]. 地球信息科学学报, 2016, 18(8): 1052-1059.
[8]	熊伟成, 杨必胜, 董震. 面向车载激光扫描数据的道路目标精细化鲁棒提取[J]. 地球信息科学学报, 2016, 18(3): 376-385.
[9]	栾元重, 范玉红, 王永, 葛仁华, 张东. 塌陷区地形分形生成方法与应用[J]. 地球信息科学学报, 2006, 8(4): 111-116.
[10]	陈锁忠, 闾国年, 朱莹, 杨春霞. 基于GIS的地下水流有限差数值模拟参数自动提取研究[J]. 地球信息科学学报, 2006, 8(2): 77-83.
[11]	冯春, 马建文, 戴芹, 陈雪, 李启青. 多维参数反演遗传算法的元胞自动机模型与应用[J]. 地球信息科学学报, 2005, 7(1): 71-75.
[12]	黄玲, 柳宗伟. 基于神经网络的选址区位评价模型分析应用[J]. 地球信息科学学报, 2004, 6(2): 37-41.
[13]	骆剑承, 周成虎, 梁怡. 空间逐步寻优的数据挖掘法的多波段影像分类研究[J]. 地球信息科学学报, 1999, 1(1): 52-59.