Adv Search

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison

LI Zhen,  LI Yong,  XING An,  ZHUO Zhiqing,  ZHANG Shiwen,  ZHANG Yuanpei,  HUANG Yuanfang

downloadPDF
文章导航 > Chinese Geographical Science  > 2019 >  20(5): 784-797
LI Zhen, LI Yong, XING An, ZHUO Zhiqing, ZHANG Shiwen, ZHANG Yuanpei, HUANG Yuanfang. Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison[J]. 中国地理科学, 2019, 20(5): 784-797. doi: 10.1007/s11769-019-1071-x
引用本文: LI Zhen, LI Yong, XING An, ZHUO Zhiqing, ZHANG Shiwen, ZHANG Yuanpei, HUANG Yuanfang. Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison[J]. 中国地理科学, 2019, 20(5): 784-797. doi: 10.1007/s11769-019-1071-x
shu
LI Zhen, LI Yong, XING An, ZHUO Zhiqing, ZHANG Shiwen, ZHANG Yuanpei, HUANG Yuanfang. Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison[J]. Chinese Geographical Science, 2019, 20(5): 784-797. doi: 10.1007/s11769-019-1071-x
Citation: LI Zhen, LI Yong, XING An, ZHUO Zhiqing, ZHANG Shiwen, ZHANG Yuanpei, HUANG Yuanfang. Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison[J]. Chinese Geographical Science, 2019, 20(5): 784-797. doi: 10.1007/s11769-019-1071-x
shu

Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison

doi: 10.1007/s11769-019-1071-x
  • 1.

    College of Resources and Environment Sciences, China Agricultural University, Beijing 100193, China;

  • 2.

    School of Earth and En-vironment, Anhui University of Science and Technology, Huainan 232001, China;

  • 3.

    Institute of Crop Sciences, Ningxia Academy of Agricultural and Forestry Sciences, Yinchuan 750002, China

基金项目: Under the auspices of National Natural Science Foundation of China (No. 41571217), National Program on Key Basic Research Project (No. 2016YFD0300801)
详细信息
    通讯作者:

    HUANG Yuanfang.E-mail:yfhuang@cau.edu.cn

Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison

  • 1.

    College of Resources and Environment Sciences, China Agricultural University, Beijing 100193, China;

  • 2.

    School of Earth and En-vironment, Anhui University of Science and Technology, Huainan 232001, China;

  • 3.

    Institute of Crop Sciences, Ningxia Academy of Agricultural and Forestry Sciences, Yinchuan 750002, China

Funds: Under the auspices of National Natural Science Foundation of China (No. 41571217), National Program on Key Basic Research Project (No. 2016YFD0300801)
More Information
    Corresponding author: HUANG Yuanfang.E-mail:yfhuang@cau.edu.cn

  • 摘要: Timely monitoring and early warning of soil salinity are crucial for saline soil management. Environmental variables are commonly used to build soil salinity prediction model. However, few researches have been done to summarize the environmental sensitive variables for soil electrical conductivity (EC) estimation systematically. Additionally, the performance of Multiple Linear Regression (MLR), Geographically Weighted Regression (GWR), and Random Forest regression (RFR) model, the representative of current main methods for soil EC prediction, has not been explored. Taking the north of Yinchuan plain irrigation oasis as the study area, the feasibility and potential of 64 environmental variables, extracted from the Landsat 8 remote sensed images in dry season and wet season, the digital elevation model, and other data, were assessed through the correlation analysis and the performance of MLR, GWR, and RFR model on soil salinity estimation was compared. The results showed that:1) 10 of 15 imagery texture and spectral band reflectivity environmental variables extracted from Landsat 8 image in dry season were significantly correlated with soil EC, while only 3 of these indices extracted from Landsat 8 image in wet season have significant correlation with soil EC. Channel network base level, one of the terrain attributes, had the largest absolute correlation coefficient of 0.47 and all spatial location factors had significant correlation with soil EC. 2) Prediction accuracy of RFR model was slightly higher than that of the GWR model, while MLR model produced the largest error. 3) In general, the soil salinization level in the study area gradually increased from south to north. In conclusion, the remote sensed imagery scanned in dry season was more suitable for soil EC estimation, and topographic factors and spatial location also play a key role. This study can contribute to the research on model construction and variables selection for soil salinity estimation in arid and semiarid regions.
    Abstract: Timely monitoring and early warning of soil salinity are crucial for saline soil management. Environmental variables are commonly used to build soil salinity prediction model. However, few researches have been done to summarize the environmental sensitive variables for soil electrical conductivity (EC) estimation systematically. Additionally, the performance of Multiple Linear Regression (MLR), Geographically Weighted Regression (GWR), and Random Forest regression (RFR) model, the representative of current main methods for soil EC prediction, has not been explored. Taking the north of Yinchuan plain irrigation oasis as the study area, the feasibility and potential of 64 environmental variables, extracted from the Landsat 8 remote sensed images in dry season and wet season, the digital elevation model, and other data, were assessed through the correlation analysis and the performance of MLR, GWR, and RFR model on soil salinity estimation was compared. The results showed that:1) 10 of 15 imagery texture and spectral band reflectivity environmental variables extracted from Landsat 8 image in dry season were significantly correlated with soil EC, while only 3 of these indices extracted from Landsat 8 image in wet season have significant correlation with soil EC. Channel network base level, one of the terrain attributes, had the largest absolute correlation coefficient of 0.47 and all spatial location factors had significant correlation with soil EC. 2) Prediction accuracy of RFR model was slightly higher than that of the GWR model, while MLR model produced the largest error. 3) In general, the soil salinization level in the study area gradually increased from south to north. In conclusion, the remote sensed imagery scanned in dry season was more suitable for soil EC estimation, and topographic factors and spatial location also play a key role. This study can contribute to the research on model construction and variables selection for soil salinity estimation in arid and semiarid regions.
  • [1] Abbas A, Khan S, 2007. Using remote sensing techniques for appraisal of irrigated soil salinity. MODSIM 2007:International Congress on Modelling and simulation:Land, Water and Environmental Management:Integrated Systems for Sustaina-bility.
    [2] Abou Samra Rasha M, Ali R R, 2018. The development of an overlay model to predict soil salinity risks by using remote sensing and GIS techniques:a case study in soils around Idku Lake, Egypt. Environmental Monitoring and Assessment, 190(12):706-722. doi: 10.1007/s10661-018-7079-3
    [3] Aldabaa A A A, Weindorf D C, Chakraborty S et al., 2015. Com-bination of proximal and remote sensing methods for rapid soil salinity quantification. Geoderma, 239:34-46. doi: 10.1016/j.geoderma.2014.09.011
    [4] Allbed A, Kumar L, 2013. Soil salinity mapping and monitoring in arid and semi-arid regions using remote sensing technology:a review. Advances in Remote Sensing, 2:373-385. doi:10.4236/ars. 2013.24040
    [5] Allbed A, Kumar L, Sinha P, 2014. Mapping and modelling spatial variation in soil salinity in the Al Hassa oasis based on remote sensing indicators and regression techniques. Remote Sensing, 6:1137-1157. doi: 10.3390/rs6021137
    [6] Bannari A, Guedon A M, El-Harti A et al., 2008. Characterization of slightly and moderately saline and sodic soils in irrigated agricultural land using simulated data of advanced land imaging (EO-1) sensor. Communications in Soil Science and Plant Analysis, 39:2795-2811. doi: 10.1080/0010362080243271
    [7] Bao Shidan, 2000. Soil and Agricultural Chemistry Analysis. Bei-jing:Chinese Agricultural press. (in Chinese)
    [8] Bouaziz M, Matschullat J, Gloaguen R, 2011. Improved remote sensing detection of soil salinity from a semi-arid climate in Northeast Brazil. Comptes Rendus Geoscience, 343:795-803. doi: 10.1016/j.crte.2011.09.003
    [9] Breiman L, 2001. Classification and regression by randomForest. Machine Learning, 45(1):5-32. doi: 10.1023/a:1010933404324
    [10] Cai S M, Zhang R Q, Liu L M et al., 2010. A method of salt-affected soil information extraction based on a support vector machine with texture features. Mathematical and Computer Modelling, 51:1319-1325. doi:10.1016/j.mcm. 2009.10.037
    [11] Conrad O, Bechtel B, Bock M et al., 2015. System for Automated Geoscientific Analyses (SAGA) v. 2.1.4. Geoscientific Model Development Discussions. 8(2):2271-2312. doi: 10.5194/gmdd-8-2271-2015
    [12] Dou C Y, Kang Y H, Wan S Q et al., 2011. Soil salinity changes under cropping with lycium barbarum l. and irrigation with sa-line-sodic water. Pedosphere, 21:539-548. doi: 10.1016/S1002-0160(11)60156-2
    [13] Douaoui A E K, Nicolas H, Walter C, 2006. Detecting salinity hazards within a semiarid context by means of combining soil and remote-sensing data. Geoderma, 134:217-230. doi:10.1016/j.geod erma.2005.10.009
    [14] El Harti A, Lhissou R, Chokmani K et al., 2016. Spatiotemporal monitoring of soil salinization in irrigated Tadla plain (Morocco) using satellite spectral indices. International Journal of Applied Earth Observation and Geoinformation, 50:64-73. doi:10.1016/j.jag. 2016.03.008
    [15] Elnaggar Abdelhamid A, Noller Jay S, 2010. Application of re-mote-sensing data and decision tree analysis to mapping salt-affected soils over large areas. Remote Sensing, 2:151-165. doi: 10.3390/rs2010151
    [16] Fan X W, Liu Y B, Tao J M et al., 2015. Soil salinity retrieval from advanced multi-spectral sensor with partial least square regression. Remote Sensing, 7:488-511. doi: 10.3390/rs70100488
    [17] Farifteh J, Van der Meer F, Atzberger C et al., 2007. Quantitative analysis of salt-affected soil reflectance spectra:a comparison of two adaptive methods (PLSR and ANN). Remote Sensing of Environment, 110:59-78. doi: 10.1016/j.rse.2007.02.005
    [18] Gill Bruce C, Terry Alister D, 2016. Keeping salt on the farm-Evaluation of an on-farm salinity management system in the Shepparton irrigation region of South-East Australia. Agricul-tural Water Management, 164:291-303. doi: 10.1016/j.agwat.2015.10.014
    [19] Huang Yajie, Li Zhen, Ye Huichun et al., 2019. Mapping soil electrical conductivity using Ordinary Kriging combined with Back-propagation network. Chinese Geographical Science, 29(2):270-282. doi: 10.1007/s11769-019-1027-1
    [20] Immitzer M, Atzberger C, Koukal T, 2012. Tree Species Classifi-cation with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data. Remote Sensing, 4:2661-2693. doi: 10.3390/rs4092661
    [21] Jiang H, Rusuli Y, Amuti T, et al., 2019. Quantitative assessment of soil salinity using multi-source remote sensing data based on the support vector machine and artificial neural network. International Journal of Remote Sensing, 40(1):284-306, doi: 10.1080/01431161.2018.1513180
    [22] Khan N M, Rastoskuev V V, Sato Y et al., 2005. Assessment of hydrosaline land degradation by using a simple approach of remote sensing indicators. Agricultural Water Management, 77:96-109. doi:10.1016/j. agwat.2004.09.038
    [23] Konukcu F, Gowing J W, Rose D A, 2006. Dry drainage:A sus-tainable solution to waterlogging and salinity problems in irri-gation areas? Agricultural Water Management, 83:1-12. doi: 10.1016/j.agwat.2005.09.003
    [24] Koohafkan P, Stewart B A, 2008. Water and Cereals in Drylands. The Food and Agriculture Organization of the United Nations and Earth scan.
    [25] Wang K, Zhang C R, Li W D, 2012. Comparison of geographically weighted regression and regression kriging for estimating the spatial distribution of soil organic matter. GIScience and Remote Sensing, 49:915-932. doi:10.2747/1548-1603. 49.6.915
    [26] Li Zhen, Zhang Shiwen, Cao Meng et al., 2018. Spatial interpola-tion of soil mechanical composition based on the spherical co-ordinate transform method. Transactions of the Chinese society for Agricultural Machinery, 49(03):295-302. (in Chinese)
    [27] Liu M L, Liu X N, Jiang J L et al., 2013. Artificial Neural Network and Random Forest Approaches for Modeling of Sea Surface Salinity. International Journal of Remote Sensing Applications, 3(4):229-235. doi: 10.14355/ijrsa.2013.0304.08
    [28] Lu D S, Li G Y, Moran E et al., 2014. The roles of textural images in improving land-cover classification in the Brazilian Amazon. International Journal of Remote Sensing, 35:8188-8207. doi: 10.1080/01431161.2014.980920
    [29] Lu W, Lu D S, Wang G X G et al., 2018. Examining soil organic carbon distribution and dynamic change in a hickory plantation region with Landsat and ancillary data. Catena, 165:576-589. doi: 10.1016/j.catena.2018.03.007
    [30] Ma L G, Yang S T, Simayi Z et al., 2018. Modeling variations in soil salinity in the oasis of Junggar Basin, China. Land Deg-radation and Development, 29:551-562. doi: 10.1002/ldr.2890
    [31] Nanni M R, Demattê J A M, 2006. Spectral reflectance method-ology in comparison to traditional soil analysis. Soil Science Society of America Journal, 70:393-407. doi: 10.2136/sssaj2003.0285
    [32] Peng J, Biswas A, Jiang Q S et al., 2019. Estimating soil salinity from remote sensing and terrain data in southern Xinjiang Province, China. Geoderma, 337:1309-1349. doi:10.1016/j.geoderma. 2018.08.006
    [33] Rodriguez-Galiano V, Sanchez-Castillo M, Chica-Olmo M et al., 2015. Machine learning predictive models for mineral pro-spectivity:An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geology Reviews, 71:804-818. doi: 10.1016/j.oregeorev.2015.01.001
    [34] Shrestha R P, 2006. Relating soil electrical conductivity to remote sensing and other soil properties for assessing soil salinity in northeast Thailand. Land Degradation and Development, 17:677-689. doi: 10.1002/ldr.752
    [35] Sidike A, Zhao S H, Wen Y M, 2014. Estimating soil salinity in Pingluo county of China using QuickBird data and soil reflec-tance spectra. International Journal of Applied Earth Obser-vation and Geoinformation, 26:156-175. doi:10.1016/j.jag. 2013.06.002
    [36] Taghizadeh-Mehrjardi R, Ayoubi S, Namazi Z et al., 2016. Pre-diction of soil surface salinity in arid region of central Iran using auxiliary variables and genetic programming. Arid Land Research and Management, 30(1):49-64. doi:10.1080/15324982. 2015.1046092
    [37] Vermeeulen D, Van Niekert A, 2017. Machine learning perfor-mance for predicting soil salinity using different combinations of geomorphometric covariates. Geoderma, 299:1-12. doi:10.1016/j. geoderma.2017.03.013
    [38] Wang B, Waters C, Orgill S et al., 2018a. Estimating soil organic carbon stocks using different modelling techniques in the semi-arid rangelands of eastern Australia. Ecological Indicators, 88:425-438. doi:10.1016/j. ecolind.2018.01.049
    [39] Wang B, Waters C, Orgill S et al., 2018b. High resolution mapping of soil organic carbon stocks using remote sensing variables in the semi-arid rangelands of eastern Australia. Science of Total Environment, 630:367-378. doi: 10.1016/j.scitotenv.2018.02.204
    [40] Whitney K, Scudiero E, El-Askary H M et al., 2018. Validating the use of MODIS time series for salinity assessment over ag-ricultural soils in California, USA. Ecological Indicators, 93:889-898. doi: 10.1016/j.ecolind.2018.05.069
    [41] Wu C S, Liu G H, Huang C, 2016. Prediction of soil salinity in the Yellow River Delta using geographically weighted regression. Archives of Agronomy and Soil Science, 63:928-941. doi: 10.1080/03650340.2016.1249475
    [42] Yu R H, Liu T X, Xu Y P et al., 2010. Analysis of salinization dynamics by remote sensing in Hetao Irrigation District of North China. Agriculture Water Management. 97:1952-1960. Doi: 10.1016/j.agwat.2010.03.009
    [43] Zhang T T, Qi J G, Gao Y et al., 2015. Detecting soil salinity with MODIS time series VI data. Ecological Indicators, 52:480-489. doi: 10.1016/j.ecolind.2015.01.004
    [44] Zhang Y P, Hu K L, Li B G et al., 2009. Spatial distribution pattern of soil salinity and saline soil in Yinchuan plain of China. Transactions of the CSAE, 25(7):19-24. (in Chinese)
    [45] Zhou D, Lin Z L, Liu L M, 2012. Regional land salinization as-sessment and simulation through cellular Automaton-Markov modeling and spatial pattern analysis. Science of Total Envi-ronment, 439:260-274. doi: 10.1016/j.scitotenv.2012.09.013
  • [1] Xiaoliang SHI, Jiajun CHEN, Hao DING, Yuanqi YANG, Yan ZHANG.  Winter Wheat Yield Estimation Based on Sparrow Search Algorithm Combined with Random Forest: A Case Study in Henan Province, China . Chinese Geographical Science, 2024, 34(2): 342-356. doi: 10.1007/s11769-024-1421-1
    [2] Kumar RAI Dil, Donghong XIONG, Wei ZHAO, Dongmei ZHAO, Baojun ZHANG, Mani DAHAL Nirmal, Yanhong WU, Aslam BAIG Muhammad.  An Investigation of Landslide Susceptibility Using Logistic Regression and Statistical Index Methods in Dailekh District, Nepal . Chinese Geographical Science, 2022, 32(5): 834-851. doi: 10.1007/s11769-022-1304-2
    [3] Lu XU, Hongyuan MA, Zhichun WANG.  Soil Salinity and Soil Water Content Estimation Using Digital Images in Coastal Field: A Case Study in Yancheng City of Jiangsu Province, China . Chinese Geographical Science, 2022, 32(4): 676-685. doi: 10.1007/s11769-022-1293-1
    [4] Yao ZHANG, Jiafu LIU, Zhuyun WEN.  Predicting Surface Urban Heat Island in Meihekou City, China: A Combination Method of Monte Carlo and Random Forest . Chinese Geographical Science, 2021, 31(4): 659-670. doi: 10.1007/s11769-021-1215-7
    [5] WEI Zongcai, ZHEN Feng, MO Haitong, WEI Shuqing, PENG Danli, ZHANG Yuling.  Travel Behaviours of Sharing Bicycles in the Central Urban Area Based on Geographically Weighted Regression: The Case of Guangzhou, China . Chinese Geographical Science, 2021, 31(1): 54-69. doi: 10.1007/s11769-020-1159-3
    [6] LI Yungang, ZHANG Yueyuan, HE Daming, LUO Xian, JI Xuan.  Spatial Downscaling of the Tropical Rainfall Measuring Mission Pre-cipitation Using Geographically Weighted Regression Kriging over the Lancang River Basin, China . Chinese Geographical Science, 2019, 20(3): 446-462. doi: 10.1007/s11769-019-1033-3
    [7] WANG Peijiang, ZHENG Haifeng, REN Zhibin, ZHANG Dan, ZHAI Chang, MAO Zhixia, TANG Ze, HE Xingyuan.  Effects of Urbanization, Soil Property and Vegetation Configuration on Soil Infiltration of Urban Forest in Changchun, Northeast China . Chinese Geographical Science, 2018, 28(3): 482-494. doi: 10.1007/s11769-018-0953-7
    [8] YANG Jun, BAO Yajun, ZHANG Yuqing, LI Xueming, GE Quansheng.  Impact of Accessibility on Housing Prices in Dalian City of China Based on a Geographically Weighted Regression Model . Chinese Geographical Science, 2018, 28(3): 505-515. doi: 10.1007/s11769-018-0954-6
    [9] Samad EMAMGHOLIZADEH, Shahin SHAHSAVANI, Mohamad Amin ESLAMI.  Comparison of Artificial Neural Networks, Geographically Weighted Regression and Cokriging Methods for Predicting the Spatial Distribution of Soil Macronutrients (N, P, and K) . Chinese Geographical Science, 2017, 27(5): 747-759. doi: 10.1007/s11769-017-0906-6
    [10] SHA Di, GAO Meixiang, SUN Xin, WU Donghui, ZHANG Xueping.  Relative Contributions of Spatial and Environmental Processes and Biotic Interactions in a Soil Collembolan Community . Chinese Geographical Science, 2015, 25(5): 582-590. doi: 10.1007/s11769-015-0778-6
    [11] YANG Lin, HUANG Chong, LIU Gaohuan, LIU Jing, ZHU A-Xing.  Mapping Soil Salinity Using a Similarity-based Prediction Approach:A Case Study in Huanghe River Delta, China . Chinese Geographical Science, 2015, 25(3): 283-294. doi: 10.1007/s11769-015-0740-7
    [12] ZHANG Haitao, GUO Long, CHEN Jiaying, FU Peihong, GU Jianli, LIAO Guangyu.  Modeling of Spatial Distributions of Farmland Density and Its Temporal Change Using Geographically Weighted Regression Model . Chinese Geographical Science, 2014, 0(2): 191-204. doi: 10.1007/s11769-013-0631-8
    [13] ZHANG Dan, WANG Guoli, ZHOU Huicheng.  Assessment on Agricultural Drought Risk Based on Variable Fuzzy Sets Model . Chinese Geographical Science, 2011, 21(2): 167-175.
    [14] WANG Xili, FU Li, MA Lei.  Semi-supervised support vector regression model for remote sensing water quality retrieving . Chinese Geographical Science, 2011, 21(1): 57-64.
    [15] JIANG Yan, LIU Changming, ZHENG Hongxing, LI Xuyong, WU Xianing.  Responses of River Runoff to Climate Change Based on Nonlinear Mixed Regression Model in Chaohe River Basin of Hebei Province, China . Chinese Geographical Science, 2010, 20(2): 152-158. doi: 10.1007/s11769-010-0152-7
    [16] LIU Dianwei, WANG Zongming, SONG Kaishan, ZHANG Bai, HU Liangjun, HUANG Ni, ZHANG Sumei, LUO Ling, ZHANG Chunhua, JIANG Guangjia.  Land Use/Cover Changes and Environmental Consequences in Songnen Plain, Northeast China . Chinese Geographical Science, 2009, 19(4): 299-305. doi: 10.1007/s11769-009-0299-2
    [17] SONG Bo, YIN Xiuqin, ZHANG Yu, DONG Weihua.  Dynamics and Relationships of Ca, Mg, Fe in Litter, Soil Fauna and Soil in Pinus koraiensis-Broadleaf Mixed Forest . Chinese Geographical Science, 2008, 18(3): 284-290. doi: 10.1007/s11769-008-0284-1
    [18] GU Feng-xue, ZHANG Yuan-dong, CHU Yu, SHI Qing-dong, PAN Xiao-ling.  PRIMARY ANALYSIS ON GROUNDWATER, SOIL MOISTURE AND SALINITY IN FUKANG OASIS OF SOUTHERN JUNGGAR BASIN . Chinese Geographical Science, 2002, 12(4): 333-338.
    [19] 刘刚才, 刘淑珍.  IMPACT OF WATER ENVIRONMENTAL CHARACTERISTICS IN DRY HOT VALLEY OF JINSHA RIVER ON SOIL DESERTIFICATION . Chinese Geographical Science, 1999, 9(2): 189-192.
    [20] 张晓平, 科扬川.  RESEARCHES ON SOIL ENVIRONMENTAL BACKGROUND VALUES IN TIBET . Chinese Geographical Science, 1995, 5(1): 56-65.
  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  408
  • HTML全文浏览量:  45
  • PDF下载量:  172
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-12-20
  • 修回日期:  2019-04-10
  • 刊出日期:  2019-10-01

Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison

doi: 10.1007/s11769-019-1071-x
  • 1. College of Resources and Environment Sciences, China Agricultural University, Beijing 100193, China;
  • 2. School of Earth and En-vironment, Anhui University of Science and Technology, Huainan 232001, China;
  • 3. Institute of Crop Sciences, Ningxia Academy of Agricultural and Forestry Sciences, Yinchuan 750002, China
    • 基金项目:  Under the auspices of National Natural Science Foundation of China (No. 41571217), National Program on Key Basic Research Project (No. 2016YFD0300801)
    通讯作者: HUANG Yuanfang.E-mail:yfhuang@cau.edu.cn
  • 收稿日期: 2018-12-20
  • 修回日期: 2019-04-10
  • 刊出日期: 2019-10-01

摘要: Timely monitoring and early warning of soil salinity are crucial for saline soil management. Environmental variables are commonly used to build soil salinity prediction model. However, few researches have been done to summarize the environmental sensitive variables for soil electrical conductivity (EC) estimation systematically. Additionally, the performance of Multiple Linear Regression (MLR), Geographically Weighted Regression (GWR), and Random Forest regression (RFR) model, the representative of current main methods for soil EC prediction, has not been explored. Taking the north of Yinchuan plain irrigation oasis as the study area, the feasibility and potential of 64 environmental variables, extracted from the Landsat 8 remote sensed images in dry season and wet season, the digital elevation model, and other data, were assessed through the correlation analysis and the performance of MLR, GWR, and RFR model on soil salinity estimation was compared. The results showed that:1) 10 of 15 imagery texture and spectral band reflectivity environmental variables extracted from Landsat 8 image in dry season were significantly correlated with soil EC, while only 3 of these indices extracted from Landsat 8 image in wet season have significant correlation with soil EC. Channel network base level, one of the terrain attributes, had the largest absolute correlation coefficient of 0.47 and all spatial location factors had significant correlation with soil EC. 2) Prediction accuracy of RFR model was slightly higher than that of the GWR model, while MLR model produced the largest error. 3) In general, the soil salinization level in the study area gradually increased from south to north. In conclusion, the remote sensed imagery scanned in dry season was more suitable for soil EC estimation, and topographic factors and spatial location also play a key role. This study can contribute to the research on model construction and variables selection for soil salinity estimation in arid and semiarid regions.

English Abstract

LI Zhen, LI Yong, XING An, ZHUO Zhiqing, ZHANG Shiwen, ZHANG Yuanpei, HUANG Yuanfang. Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison[J]. 中国地理科学, 2019, 20(5): 784-797. doi: 10.1007/s11769-019-1071-x
引用本文: LI Zhen, LI Yong, XING An, ZHUO Zhiqing, ZHANG Shiwen, ZHANG Yuanpei, HUANG Yuanfang. Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison[J]. 中国地理科学, 2019, 20(5): 784-797. doi: 10.1007/s11769-019-1071-x
shu
LI Zhen, LI Yong, XING An, ZHUO Zhiqing, ZHANG Shiwen, ZHANG Yuanpei, HUANG Yuanfang. Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison[J]. Chinese Geographical Science, 2019, 20(5): 784-797. doi: 10.1007/s11769-019-1071-x
Citation: LI Zhen, LI Yong, XING An, ZHUO Zhiqing, ZHANG Shiwen, ZHANG Yuanpei, HUANG Yuanfang. Spatial Prediction of Soil Salinity in a Semiarid Oasis: Environmental Sensitive Variable Selection and Model Comparison[J]. Chinese Geographical Science, 2019, 20(5): 784-797. doi: 10.1007/s11769-019-1071-x
shu

    全文HTML

参考文献 (45)

目录

    /

    返回文章
    返回

    Copyright © Editorial office of Chinese Geographical Science

    Tel: +86-0431-85542219   Email: egeoscien@neigae.ac.cn