Volume 29 Issue 2
Apr.  2019
Turn off MathJax
Article Contents

HUANG Yajie, LI Zhen, YE Huichun, ZHANG Shiwen, ZHUO Zhiqing, XING An, HUANG Yuanfang. Mapping Soil Electrical Conductivity Using Ordinary Kriging Combined with Back-propagation Network[J]. Chinese Geographical Science, 2019, 20(2): 270-282. doi: 10.1007/s11769-019-1027-1
Citation: HUANG Yajie, LI Zhen, YE Huichun, ZHANG Shiwen, ZHUO Zhiqing, XING An, HUANG Yuanfang. Mapping Soil Electrical Conductivity Using Ordinary Kriging Combined with Back-propagation Network[J]. Chinese Geographical Science, 2019, 20(2): 270-282. doi: 10.1007/s11769-019-1027-1

Mapping Soil Electrical Conductivity Using Ordinary Kriging Combined with Back-propagation Network

doi: 10.1007/s11769-019-1027-1
Funds:  Under the auspices of the National Natural Science Foundation of China (No. 41571217), the National Key Research and Development Program of China (No. 2016YFD0300801)
More Information
  • Corresponding author: HUANG Yuanfang
  • Received Date: 2017-11-29
  • Publish Date: 2019-04-01
  • Accurate mapping of soil salinity and recognition of its influencing factors are essential for sustainable crop production and soil health. Although the influencing factors have been used to improve the mapping accuracy of soil salinity, few studies have considered both aspects of spatial variation caused by the influencing factors and spatial autocorrelations for mapping. The objective of this study was to demonstrate that the ordinary kriging combined with back-propagation network (OK_BP), considering the two aspects of spatial variation, which can benefit the improvement of the mapping accuracy of soil salinity. To test the effectiveness of this approach, 70 sites were sampled at two depths (0-30 and 30-50 cm) in Ningxia Hui Autonomous Region, China. Ordinary kriging (OK), back-propagation network (BP) and regression kriging (RK) were used in comparison analysis; the root mean square error (RMSE), relative improvement (RI) and the decrease in estimation imprecision (DIP) were used to judge the mapping quality. Results showed that OK_BP avoided the both underestimation and overestimation of the higher and lower values of interpolation surfaces. OK_BP revealed more details of the spatial variation responding to influencing factors, and provided more flexibility for incorporating various correlated factors in the mapping. Moreover, OK_BP obtained better results with respect to the reference methods (i.e., OK, BP, and RK) in terms of the lowest RMSE, the highest RI and DIP. Thus, it is concluded that OK_BP is an effective method for mapping soil salinity with a high accuracy.
  • [1] Akramkhanov A, Martius C, Park S J et al., 2011. Environmental factors of spatial distribution of soil salinity on flat irrigated terrain. Geoderma, 163(1):55-62. doi:10.1016/j. ge-oderma.2011.04.001
    [2] Akramkhanov A, Vlek P L G, 2012. The assessment of spatial distribution of soil salinity risk using neural network. Envi-ronmental Monitoring and Assessment, 184(4):2475-2485. doi: 10.1007/s10661-011-2132-5
    [3] Aldakheel Y Y, 2011. Assessing NDVI spatial Pattern as related to irrigation and soil salinity management in Al-Hassa Oasis, Saudi Arabia. Journal of the Indian Society of Remote Sensing, 39(2):171-180. doi: 10.1007/s12524-010-0057-z
    [4] Bilgili A V, 2013. Spatial assessment of soil salinity in the Harran Plain using multiple kriging techniques. Environmental Moni-toring and Assessment, 185(1):777-795. doi: 10.1007/s10661-012-2591-3
    [5] Cambardella C A, Moorman T B, Parkin T B et al., 1994. Field-scale variability of soil properties in central low a soils. Soil Science Society of America Journal, 58(5):1501-1511. doi: 10.2136/sssaj1994.03615995005800050033x
    [6] Chen X H, Duan Z H, Luo T F, 2014. Changes in soil quality in the critical area of desertification surrounding the Ejina Oasis, Northern China. Environmental Earth Sciences, 72(7):2643-2654. doi: 1007/s12665-014-3171-3
    [7] Chi C M, Wang Z C, 2010. Characterizing salt-affected soils of Songnen Plain using saturated paste and 1:5 soil-to-water ex-traction methods. Arid Land Research and Management, 24(1):1-11. doi: 10.1080/15324980903439362
    [8] Dai F Q, Zhou Q G, Lv Z Q et al., 2014. Spatial prediction of soil organic matter content integrating artificial network and ordinary kriging in Tibetan Plateau. Ecological Indicators, 45:184-194. doi: 10.1016/j.ecolind.2014.04.003
    [9] Ding J L, Yu D L, 2014. Monitoring and evaluating spatial varia-bility of soil salinity in dry and wet seasons in the Weri-gan-Kuqa Oasis, China, using remote sensing and electro-magnetic induction instruments. Geoderma, 235:316-322. doi: 10.1016/j.geoderma.2014.07.028
    [10] Eldeiry A A, Garcia L A, 2012. Evaluating the performance of ordinary kriging in mapping soil salinity. Journal of Irrigation and Drainage Engineering, 138(12):1046-1059. doi: 10.1061/(ASCE)IR.1943-4774.0000517
    [11] Emadi M, Baghernejad M, 2014. Comparison of spatial interpola-tion techniques for mapping soil pH and salinity in agricultural coastal areas, northern Iran. Archives of Agronomy and Soil Sci-ence, 60(9):1315-1327. doi:10.1080/03650340.2014. 880837
    [12] Fang H L, Liu G H, Kearney M, 2005. Georelational analysis of soil type, soil salt content, landform, and land use in the Yellow River Delta, China. Environmental Management, 35(1):72-83. doi: 10.1007/s00267-004-3066-2
    [13] He B, Cai Y L, Ran W R et al., 2015. Spatiotemporal heterogeneity of soil salinity after the establishment of vegetation on a coastal saline field. Catena, 127:129-134. doi:10.1016/j. ca-tena.2014.12.028
    [14] He Wenshou, Liu Yangchun, He Jinyu, 2010. Relationships be-tween soluble salt content and electrical conductivity for dif-ferent types of salt-affected soils in Ningxia. Agricultural Re-search in the Arid Areas, 28(1):111-116. (in Chinese)
    [15] Hengl T, Heuvelink G B M, Stein A, 2004. A generic framework for spatial prediction of soil variables based on regres-sion-kriging. Geoderma, 120:75-93. doi:10.1016/j.geoderma. 2003.08.018
    [16] Huang Yajie, Ye Hechun, Zhang Shiwen et al., 2015. Zoning of arable land productivity based on self-organizing map in China. Scientia Agricultura Sinica, 48(6):1136-1150. (in Chinese)
    [17] Huang Y J, Ye H C, Zhang S W et al., 2017. Prediction of soil organic mMatter using ordinary kriging combined with the clustering of self-organizing map:a case study in Pinggu Dis-trict, Beijing, China. Soil Science, 182:52-62. doi: 10.1097/SS.0000000000000196
    [18] Isaaks E H, Srivastava R M, 1989. An Introduction to Applied Geostatistics. New York:Oxford University Press.
    [19] IUSS Working Group WRB, 2007. World reference base for soil resources 2006, first update 2007. World Soil Resources Re-ports, FAO, Rome. Available at:http://www.fao.org.
    [20] Jordán M M, Navarro-Pedreno J, García-Sánchez E et al., 2004. Spatial dynamics of soil salinity under arid and semi-arid con-ditions:geological and environmental implications. Environ-mental Geology, 45(4):448-456. doi: 10.1007/s00254-003-0894-y
    [21] Lark R M, 1999. Soil-landform relationships at within-field scales:an investigation using continuous classification. Geoderma, 92(3-4):141-165. doi:10.1016/S0016-7061(99) 00028-2
    [22] Li Q Q, Yue T X, Wang C Q et al., 2013. Spatially distributed modeling of soil organic matter across China:an application of artificial neural network approach. Catena, 104:210-218. doi: 10.1016/j.catena.2012.11.012
    [23] Li Q Q, Zhang X, Wang C Q et al., 2016. Spatial prediction of soil nutrient in a hilly area using artificial neural network model combined with kriging. Archives of Agronomy and Soil Science, 62(11):1541-1553. doi:10.2136/sssaj1989.0361599 5005300030029x
    [24] Liu T L, Juang K W, Lee D Y, 2006. Interpolating soil properties using kriging combined with categorical information of soil maps. Soil Science Society of America Journal, 70(4):1200-1209. doi: 10.2136/sssaj2005.0126
    [25] Lu Rukun, 2000. Analysis methods of soil agricultural chemistry. China:Agricultural Science and Technology Publishing House, 85-89. (in Chinese)
    [26] McBratney A B, Santos M L M, Minasny B. 2003. On digital soil mapping. Geoderma, 17(1-2):3-52. doi:10.1016/S0016-7061 (03)00223-4
    [27] Mirakzehi K, Pahlavan-Rad M R, Shahriari A et al., 2018. Digital soil mapping of deltaic soils:a case of study from Hirmand (Helmand) river delta. Geoderma, 313:233-240. doi: 10.1016/j.scitotenv.2018.02.052
    [28] Mirlas V, 2012. Assessing soil salinity hazard in cultivated areas using MODFLOW model and GIS tools:a case study from the Jezre'el Valley, Israel. Agricultural Water Managemen, 109:144-154. doi: 10.1016/j.agwat.2012.03.003
    [29] Moore I D, Gessler P E, Nielsen G A et al., 1993. Soil attribute prediction using terrain analysis. Soil Science Society of America Journal, 57(2):443-452. doi:10.2136/sssaj1993. 03615995005700020026x
    [30] Mora-Vallejo A, Claessens L, Stoorvogel J et al., 2008. Small scale digital soil mapping in Southeastern Kenya. Catena, 76(1):44-53. doi: 10.1016/j.catena.2008.09.008
    [31] Motaghian H R, Mohammadi J, 2011. Spatial estimation of satu-rated hydraulic conductivity from terrain attributes using re-gression, kriging, and artificial neural networks. Pedosphere, 21(2):170-177. doi: 10.1016/S1002-0160(11)60115-X
    [32] Mozumder R A, Laskar A I, 2015. Prediction of unconfined com-pressive strength of geopolymer stabilized clayey soil using Artificial Neural Network. Computers and Geotechnics, 69:291-300. doi: 10.1016/j.compgeo.2015.05.021
    [33] Mueller T G, Mijatovic B, Sears B G et al., 2004. Soil electrical conductivity map quality. Soil Science, 169(12):841-851. doi: 10.1097/00010694-200412000-00003
    [34] Mueller T G, Pierce F J, 2003. Soil carbon maps:Enhancing spatial estimates with simple terrain attributes at multiple scales. Soil Science Society of America Journal, 67(1):258-267. doi: 10.2136/sssaj2003.2580
    [35] Nielsen D R, Bouma J, 1985. Soil Spatial Variability:Proceedings of a Workshop of the ISSS and the SSSA, Las Vegas, USA/Pdc296. Pudoc Wageningen, Netherlands:Center Agricultural Pub and Document.
    [36] Nosetto M D, Acosta A M, Jayawickreme D H et al., 2013. Land-use and topography shape soil and groundwater salinity in central Argentina. Agricultural Water Management, 129:120-129. doi: 10.1016/j.agwat.2013.07.017
    [37] Nosetto M D, Jobbágy E G, Tóth T et al., 2008. Regional patterns and controls of ecosystem salinization with grassland affor-estation along a rainfall gradient. Global Biogeochemical Cy-cles, 22(2):1-12. doi: 10.1029/2007GB003000
    [38] Olden J D, Jackson D A, 2002. Illuminating the ‘black box’:a randomization approach for understanding variable contribu-tions in artificial neural networks. Ecological Modelling, 154(1-2):135-50. doi: 10.1016/S0304-3800(02)00064-9
    [39] Patel R M, Prasher S O, God P K, et al., 2002. Soil Salinity Pre-diction Using Artificial Neural Networks. Journal of the American Water Resources Association, 38(1):91-100. doi: 10.1111/j.1752-688.2002.tb01537.x
    [40] Park S J, Vlek P L G, 2002. Environmental correlation of three-dimensional soil spatial variability:a comparison of three adaptive techniques. Geoderma, 109(1-2):117-140. doi: 10.1016/S0016-7061(02)00146-5
    [41] Raczko E, Zagajewski B, 2017. Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images. European Journal of Remote Sensing, 50(1):144-154. doi: 10.1080/22797254.2017.1299557
    [42] Sarangi A, Singh M, Bhattacharya A K et al., 2006. Subsurface drainage performance study using SALTMOD and ANN mod-els. Agricultural Water Management, 84(3):240-248. doi: 10.1016/j.agwat.2006.02.009
    [43] Sedaghat A, Bayat H, Sinegani A A S, 2016. Estimation of soil saturated hydraulic conductivity by artificial neural networks ensemble in smectitic soils. Eurasian Soil Science, 49(3):347-357. doi: 10.1134/S106422931603008X
    [44] Shah S H H, Vervoort R W, Suweis S et al., 2011. Stochastic modeling of salt accumulation in the root zone due to capillary flux from brackish groundwater. Water Resources Research, 47(9):09506-09522. doi: 10.1029/2010WR009790
    [45] Shahabi M, Jafarzadeh A A, Neyshabouri M R et al., 2017. Spatial modeling of soil salinity using multiple linear regression, Ordinary kriging and artificial neural network methods. Ar-chives of Agronomy and Soil Science, 63(2):151-160. doi: 10.1080/03650340.2016.1193162
    [46] Sheng J, Ma L, Jiang P et al., 2010. Digital soil mapping to enable classification of the salt-affected soils in desert agro-ecological zones. Agricultural Water Management, 97(12):1944-51. doi: 10.1016/j.agwat.2009.04.011
    [47] 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
    [48] Takata Y, Funakawa S, Akshalov K et al., 2007. Spatial prediction of soil organic matter in northern Kazakhstan based on topo-graphic and vegetation information. Soil Science and Plant Nu-trition, 53(3):289-299. doi:10.1111/j.1747-0765.2007.001 42.x
    [49] Visconti F, de Paz J M, Rubio J L, 2010. What information does the electrical conductivity of soil water extracts of 1 to 5 ratio (w/v) provide for soil salinity assessment of agricultural irri-gated lands? Geoderma, 154 (3-4):387-397. doi:10.1016/j. geoderma.2009.11.012
    [50] Wang S Q, Song X F, Wang Q X et al., 2012. Shallow groundwa-ter dynamics and origin of salinity at two sites in salinated and water-deficient region of North China Plain, China. Environ-mental Earth Sciences, 66(3):729-739. doi: 10.1007/s12665-011-1280-9
    [51] Wang S, Adhikari K, Wang Q B et al., 2018. Role of environmental variables in the spatial distribution of soil carbon (C), nitrogen (N), and C:N ratio from the northeastern coastal agroecosystems in China. Ecological Indicators, 84:263-272. doi: 10.1016/j.ecolind.2017.08.046
    [52] Were K, Bui D T, Dick Ø B et al., 2015. A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. Ecological Indicators, 52:394-403. doi: 10.1016/j.ecolind.2014.12.028
    [53] Wu J H, Li P Y, Qian H et al., 2014. Assessment of soil saliniza-tion based on a low-cost method and its influencing factors in a semi-arid agricultural area, northwest China. Environmental Earth Sciences, 71(8):3465-3475. doi: 10.1007/s12665-013-2736-x
    [54] Yahiaoui I, Douaoui A, Zhang Q et al., 2015. Soil salinity predic-tion in the Lower Cheliff plain (Algeria) based on remote sensing and topographic feature analysis. Journal of Arid Land, 7(6):794-805. doi: 10.1007/s40333-015-0053-9
    [55] Yang Q Y, Jiang Z C, Li W J et al., 2014. Prediction of soil organic matter in peak-cluster depression region using kriging and terrain indices. Soil and Tillage Research, 144:126-132. doi: 10.1016/j.still.2014.07.011
    [56] Ye H C, Huang W J, Huang S Y et al., 2017. Effects of different sampling densities on geographically weighted regression kriging for predicting soil organic carbon. Spatial Statistics, 20:76-91. doi: 10.1016/j.spasta.2017.02.001
    [57] Ye H C, Huang Y F, Chen P F et al., 2016. Effects of land use change on the spatiotemporal variability of soil organic carbon in an urban-rural ecotone of Beijing. Journal of Integrative Ag-riculture, 15(4):918-928. doi:10.1016/S2095-3119(15) 61066-8
    [58] Yu J B, Li Y Z, Han G X et al., 2014. The spatial distribution characteristics of soil salinity in coastal zone of the Yellow River Delta. Environmental Earth Sciences, 72(2):589-599. doi: 10.1007/s12665-013-2980-0
    [59] Yu S H, Liu J T, Eneji A E et al., 2015. Spatial Variability of Soil Salinity under Subsurface Drainage. Communications in Soil Science and Plant Analysis, 46(2):259-270. doi: 10.1080/00103624.2014.967863
    [60] Zhang F, Tiyip T, Ding J L et al., 2009. The effects of the chemical components of soil salinity on electrical conductivity in the region of the Delta Oasis of Weigan and Kuqa Rivers. Agri-cultural Sciences in China, 8(8):985-993. doi: 10.1016/S1671-2927(08)60304-1
    [61] Zhang S W, Huang Y F, Shen C Y et al., 2012. Spatial prediction of soil organic matter using terrain indices and categorical variables as auxiliary information. Geoderma, 171:35-43. doi: 10.1016/j.geoderma.2011.07.012
    [62] Zhang S W, Shen C Y, Chen X Y et al., 2013. Spatial interpolation of soil texture using compositional kriging and regression kriging with consideration of the characteristics of composi-tional data and environment variables. Journal of Integrative Agriculture, 12(9):1673-1683. doi:10.1016/S2095-3119(13) 60395-0
    [63] Zhao Y, Feng Q, Yang H D, 2016. Soil salinity distribution and its relationship with soil particle size in the lower reaches of Heihe River, Northwestern China. Environmental Earth Sciences, 75(9):1-18. doi: 10.1007/s12665-016-5603-8
    [64] Zhao Z Y, Yang Q, Benoy G et al., 2010. Using artificial neural network models to produce soil organic carbon content distri-bution maps across landscapes. Canadian Journal of Soil Sci-ence, 90(1):75-87. doi: 10.4141/CJSS08057
    [65] Zhu A X, 2000. Mapping soil landscape as spatial continua:the neural network approach. Water Resources Research, 36(3):663-677. doi: 10.1016/S1671-2927(08)60349-1
    [66] Zou P, Yang J S, Fu J R et al., 2010. Artificial neural network and time series models for predicting soil salt and water content. Agricultural Water Management, 97(12):2009-2019. doi: 10.1016/j.agwat.2010.02.011
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article Metrics

Article views(321) PDF downloads(356) Cited by()

Proportional views
Related

Mapping Soil Electrical Conductivity Using Ordinary Kriging Combined with Back-propagation Network

doi: 10.1007/s11769-019-1027-1
Funds:  Under the auspices of the National Natural Science Foundation of China (No. 41571217), the National Key Research and Development Program of China (No. 2016YFD0300801)
    Corresponding author: HUANG Yuanfang

Abstract: Accurate mapping of soil salinity and recognition of its influencing factors are essential for sustainable crop production and soil health. Although the influencing factors have been used to improve the mapping accuracy of soil salinity, few studies have considered both aspects of spatial variation caused by the influencing factors and spatial autocorrelations for mapping. The objective of this study was to demonstrate that the ordinary kriging combined with back-propagation network (OK_BP), considering the two aspects of spatial variation, which can benefit the improvement of the mapping accuracy of soil salinity. To test the effectiveness of this approach, 70 sites were sampled at two depths (0-30 and 30-50 cm) in Ningxia Hui Autonomous Region, China. Ordinary kriging (OK), back-propagation network (BP) and regression kriging (RK) were used in comparison analysis; the root mean square error (RMSE), relative improvement (RI) and the decrease in estimation imprecision (DIP) were used to judge the mapping quality. Results showed that OK_BP avoided the both underestimation and overestimation of the higher and lower values of interpolation surfaces. OK_BP revealed more details of the spatial variation responding to influencing factors, and provided more flexibility for incorporating various correlated factors in the mapping. Moreover, OK_BP obtained better results with respect to the reference methods (i.e., OK, BP, and RK) in terms of the lowest RMSE, the highest RI and DIP. Thus, it is concluded that OK_BP is an effective method for mapping soil salinity with a high accuracy.

HUANG Yajie, LI Zhen, YE Huichun, ZHANG Shiwen, ZHUO Zhiqing, XING An, HUANG Yuanfang. Mapping Soil Electrical Conductivity Using Ordinary Kriging Combined with Back-propagation Network[J]. Chinese Geographical Science, 2019, 20(2): 270-282. doi: 10.1007/s11769-019-1027-1
Citation: HUANG Yajie, LI Zhen, YE Huichun, ZHANG Shiwen, ZHUO Zhiqing, XING An, HUANG Yuanfang. Mapping Soil Electrical Conductivity Using Ordinary Kriging Combined with Back-propagation Network[J]. Chinese Geographical Science, 2019, 20(2): 270-282. doi: 10.1007/s11769-019-1027-1
Reference (66)

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return