Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran

Abstract Knowledge about distribution of soil properties over the landscape is required for a variety of land management applications and resources, modeling, and monitoring practices. The main aim of this research was to conduct a spatially prediction of the top soil properties such as soil organic carbon (SOC), calcium carbonate equivalent (CCE), and clay content using digital soil mapping (DSM) approaches in Borujen region, Chaharmahal-Va-Bakhtiari province, central Iran. To achieve this goal, a total of 334 soil samples were collected from 0 to 30 cm depth. Three non-linear models including Cubist (Cu), Random Forest (RF), Regression Tree (RT) and a Multiple Linear Regression (MLR) were used to link environmental covariates and the studied soil properties. The environmental covariates were obtained from a digital elevation model (DEM) and satellite imagery (Landsat Enhanced Thematic Mapper; ETM). The model was calibrated and validated by the 10-fold cross-validation approach. Root mean square error (RMSE) and coefficient of determination (R2) were used to determine the performance of the models, and relative RMSE (RMSE%) was used to define prediction accuracy. According to the RMSE and R2, Cu and RF resulted in the most accurate predictions for CCE (R2 = 0.30 and RMSE = 9.52) and clay contents (R2 = 0.15 and RMSE = 7.86), respectively, while both of RF and Cu models showed the highest performance to predict SOC content (R2 = 0.55). Results showed that remote sensing covariates (Ratio Vegetation Index and band 4) were the most important variables to explain the variability of SOC and CCE content, but only topographic attributes were responsible for clay content variation. According to RMSE% results, it could be concluded that the best model is not necessarily able to make the most accurate estimation. This study recommended that more observations and denser sampling should be carried out in the entire study area. Alternatively, stratified sampling by elevation in homogeneous sub-areas was recommended. The stratified sampling probably will increase the performance of models.

[1]  Budiman Minasny,et al.  Digital mapping of a soil drainage index for irrigated enterprise suitability in Tasmania, Australia , 2014 .

[2]  Zohreh Mosleh,et al.  The effectiveness of digital soil mapping to predict soil properties over low-relief areas , 2016, Environmental Monitoring and Assessment.

[3]  D. W. Nelson,et al.  Total Carbon, Organic Carbon, and Organic Matter , 1983, SSSA Book Series.

[4]  Budiman Minasny,et al.  A conditioned Latin hypercube method for sampling in the presence of ancillary information , 2006, Comput. Geosci..

[5]  M. R. Pahlavan-Rad,et al.  Spatial variability of soil texture fractions and pH in a flood plain (case study from eastern Iran) , 2018 .

[6]  The interaction between poisonous plants and soil quality in response to grassland degradation in the alpine region of the Qinghai-Tibetan Plateau , 2014, Plant Ecology.

[7]  J. Byrne,et al.  Spatial variability of soil magnetic susceptibility, organic carbon and total nitrogen from farmland in northern China , 2016 .

[8]  E. Bui,et al.  Modelling the abundance of soil calcium carbonate across Australia using geochemical survey data and environmental predictors , 2015 .

[9]  W. Tan,et al.  Effect of different vegetation cover on the vertical distribution of soil organic and inorganic carbon in the Zhifanggou Watershed on the loess plateau , 2016 .

[10]  Budiman Minasny,et al.  Quantitative models for pedogenesis — A review , 2008 .

[11]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[12]  L. Wilding,et al.  Spatial variability: its documentation, accommodation and implication to soil surveys , 1985 .

[13]  O. Chadwick,et al.  Modeling deep soil properties on California grassland hillslopes using LiDAR digital elevation models , 2016 .

[14]  N. Batjes,et al.  Total carbon and nitrogen in the soils of the world , 1996 .

[15]  D. W. Nelson,et al.  Total Carbon, Organic Carbon, and Organic Matter 1 , 1982 .

[16]  Z. Alijani,et al.  THE ROLE OF TOPOGRAPHY IN CHANGING OF SOIL CARBONATE CONTENT , 2014 .

[17]  E. Brevik,et al.  Modeling soil cation exchange capacity in multiple countries , 2017 .

[18]  F. Ziadat,et al.  Variation in soil chemical properties along toposequences in an arid region of the Levant. , 2010 .

[19]  Rattan Lal,et al.  Predicting Soil Organic Carbon Stock Using Profile Depth Distribution Functions and Ordinary Kriging , 2009 .

[20]  I. Creed,et al.  A topographic template for estimating soil carbon pools in forested catchments , 2011 .

[21]  Ahmad Jalalian,et al.  Relationships between soil depth and terrain attributes in a semi arid hilly region in western Iran , 2013, Journal of Mountain Science.

[22]  D. Weindorf,et al.  Relationship of potentially labile soil organic carbon with soil quality indicators in deforested areas of Iran. , 2013 .

[23]  R. Webster,et al.  Baseline map of organic carbon in Australian soil to support national carbon accounting and monitoring under climate change , 2014, Global Change Biology.

[24]  Karin Viergever,et al.  Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia , 2009 .

[25]  R. Kerry,et al.  Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran , 2016 .

[26]  Budiman Minasny,et al.  Mapping continuous depth functions of soil carbon storage and available water capacity , 2009 .

[27]  A. Hassanli,et al.  Quantitative assessment of desertification in south of Iran using MEDALUS method , 2007, Environmental monitoring and assessment.

[28]  V. L. Mulder,et al.  The use of remote sensing in soil and terrain mapping — A review , 2011 .

[29]  Mohsen Jalali,et al.  The combination of geostatistics and geochemical simulation for the site-specific management of soil salinity and sodicity , 2016, Comput. Electron. Agric..

[30]  Alireza Karimi,et al.  Digital soil mapping using remote sensing indices, terrain attributes, and vegetation features in the rangelands of northeastern Iran , 2017, Environmental Monitoring and Assessment.

[31]  Dan A. Nath.  Soil landscape modeling in the Northwest Iowa Plains region of O'Brien County, Iowa , 2006 .

[32]  Alfred E. Hartemink,et al.  Predicting soil properties in the tropics , 2011 .

[33]  Budiman Minasny,et al.  High resolution 3D mapping of soil organic carbon in a heterogeneous agricultural landscape , 2014 .

[34]  A. Page.  Methods of soil analysis. Part 2. Chemical and microbiological properties. , 1982 .

[35]  Abdolrassoul Salmanmahiny,et al.  Predicting soil organic carbon density using auxiliary environmental variables in northern Iran , 2016 .

[36]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[37]  N. Draper,et al.  Applied Regression Analysis. , 1967 .

[38]  Anònim Anònim.  Keys to Soil Taxonomy , 2010 .

[39]  Alfred E. Hartemink,et al.  Digital Mapping of Soil Organic Carbon Contents and Stocks in Denmark , 2014, PloS one.

[40]  Mohammad Taghi Dastorani,et al.  The survey of climatic drought trend in Iran , 2011 .

[41]  Budiman Minasny,et al.  Digital mapping of soil salinity in Ardakan region, central Iran , 2014 .

[42]  Yang Liu,et al.  An introduction to decision tree modeling , 2004 .

[43]  G. Heuvelink,et al.  Mapping Soil Properties of Africa at 250 m Resolution: Random Forests Significantly Improve Current Predictions , 2015, PloS one.

[44]  Inakwu O. A. Odeh,et al.  Catchment scale mapping of measureable soil organic carbon fractions , 2014 .

[45]  E. Brevik,et al.  Spatial distribution of soil chemical properties in an organic farm in Croatia. , 2017, The Science of the total environment.

[46]  J. Mbagwu,et al.  Prediction of engineering properties of tropical soils using intrinsic pedological parameters , 1998 .

[47]  A. Prasad,et al.  Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction , 2006, Ecosystems.

[48]  Paul L. G. Vlek,et al.  Environmental correlation of three-dimensional soil spatial variability: a comparison of three adaptive techniques , 2002 .

[49]  David J. Chittleborough,et al.  The effect of terrain and management on the spatial variability of soil properties in an apple orchard , 2012 .

[50]  I C Edmundson,et al.  Particle size analysis , 2013 .

[51]  A. McBratney,et al.  A soil science renaissance , 2008 .

[52]  A. Cerda,et al.  The multidisciplinary origin of soil geography: A review , 2018 .

[53]  Jean-Michel Poggi,et al.  Variable selection using random forests , 2010, Pattern Recognit. Lett..

[54]  E. Mahmoudabadi,et al.  Spatial distribution of soil heavy metals in different land uses of an industrial area of Tehran (Iran) , 2015, International Journal of Environmental Science and Technology.

[55]  H. Elsenbeer,et al.  Soil organic carbon concentrations and stocks on Barro Colorado Island — Digital soil mapping using Random Forests analysis , 2008 .

[56]  Spatial prediction of soil organic carbon of Crete by using geostatistics , 2012 .

[57]  A. Klute,et al.  Methods of soil analysis , 2015, American Potato Journal.

[58]  J. Rinklebe,et al.  Estimation of soil properties with geostatistical methods in floodplains , 2008 .

[59]  Budiman Minasny,et al.  Digital mapping of soil carbon , 2013 .

[60]  Peter Finke,et al.  Comparing the efficiency of digital and conventional soil mapping to predict soil types in a semi-arid region in Iran , 2017 .

[61]  Budiman Minasny,et al.  On digital soil mapping , 2003 .

[62]  H. Ahmadib,et al.  Hazard Assessment of Desertification as a Result of Soil and Water Recourse Degradation in Kashan Region, Iran , 2014 .

[63]  A. Moulin,et al.  Soil phosphorus spatial variability due to landform, tillage, and input management: A case study of small watersheds in southwestern Manitoba , 2016 .

[64]  Michael Thiel,et al.  High Resolution Mapping of Soil Properties Using Remote Sensing Variables in South-Western Burkina Faso: A Comparison of Machine Learning and Multiple Linear Regression Models , 2017, PloS one.

[65]  R. Lark,et al.  Carbon losses from all soils across England and Wales 1978–2003 , 2005, Nature.

[66]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[67]  G. Heuvelink,et al.  A generic framework for spatial prediction of soil variables based on regression-kriging , 2004 .

[68]  Travis W. Nauman,et al.  Semi-automated disaggregation of conventional soil maps using knowledge driven data mining and classification trees , 2014 .

[69]  N. Toomanian,et al.  Assessing geopedological soil mapping approach by statistical and geostatistical methods: A case study in the Borujen region, Central Iran , 2010 .