Mapping Surficial Soil Particle Size Fractions in Alpine Permafrost Regions of the Qinghai-Tibet Plateau

Spatial information of particle size fractions (PSFs) is primary for understanding the thermal state of permafrost in the Qinghai-Tibet Plateau (QTP) in response to climate change. However, the limitation of field observations and the tremendous spatial heterogeneity hamper the digital mapping of PSF. This study integrated log-ratio transformation approaches, variable searching methods, and machine learning techniques to map the surficial soil PSF distribution of two typical permafrost regions. Results showed that the Boruta technique identified different covariates but retained those covariates of vegetation and land surface temperature in both regions. Variable selection techniques effectively decreased the data redundancy and improved model performance. In addition, the spatial distribution of soil PSFs generated by four log-ratio models presented similar patterns. Isometric log-ratio random forest (ILR-RF) outperformed the other models in both regions (i.e., R2 ranged between 0.36 to 0.56, RMSE ranged between 0.02 and 0.10). Compared with three legacy datasets, our prediction better captured the spatial pattern of PSFs with higher accuracy. Although this study largely improved the accuracy of spatial distribution of soil PSFs, further endeavors should also be made to improve model accuracy and interpretability for a better understanding of the interaction and processes between environmental predictors and soil PSFs at permafrost regions.

[1]  C. Ballabio,et al.  Mapping topsoil physical properties at European scale using the LUCAS database , 2016 .

[2]  Arwyn Jones,et al.  The LUCAS topsoil database and derived information on the regional variability of cropland topsoil properties in the European Union , 2013, Environmental Monitoring and Assessment.

[3]  B. Minasny,et al.  Some practical aspects of predicting texture data in digital soil mapping , 2019, Soil and Tillage Research.

[4]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[5]  John H. Kalivas,et al.  Comparison of Forward Selection, Backward Elimination, and Generalized Simulated Annealing for Variable Selection , 1993 .

[6]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[7]  Jesper Tegnér,et al.  Consistent Feature Selection for Pattern Recognition in Polynomial Time , 2007, J. Mach. Learn. Res..

[8]  Deliang Chen,et al.  Remote sensing spatiotemporal patterns of frozen soil and the environmental controls over the Tibetan Plateau during 2002–2016 , 2020 .

[9]  Wei Zhou,et al.  Comparison of additive and isometric log-ratio transformations combined with machine learning and regression kriging models for mapping soil particle size fractions , 2020 .

[10]  Cees G. M. Snoek,et al.  Variable Selection , 2019, Model-Based Clustering and Classification for Data Science.

[11]  W. Shi,et al.  Mapping soil particle-size fractions: A comparison of compositional kriging and log-ratio kriging , 2017 .

[12]  I. Odeh,et al.  SPATIAL PREDICTION OF SOIL PARTICLE-SIZE FRACTIONS AS COMPOSITIONAL DATA , 2003 .

[13]  A-Xing Zhu,et al.  Case-based knowledge formalization and reasoning method for digital terrain analysis – application to extracting drainage networks , 2016 .

[14]  Y. Sheng,et al.  Changing climate and the permafrost environment on the Qinghai–Tibet (Xizang) plateau , 2020, Permafrost and Periglacial Processes.

[15]  Y. Sheng,et al.  Soil organic carbon and total nitrogen pools in permafrost zones of the Qinghai-Tibetan Plateau , 2018, Scientific Reports.

[16]  Yongjiu Dai,et al.  A review of the global soil property maps for Earth system models , 2019, SOIL.

[17]  Hua Yuan,et al.  A soil particle-size distribution dataset for regional land and climate modelling in China , 2012 .

[18]  Stephen E. Fick,et al.  WorldClim 2: new 1‐km spatial resolution climate surfaces for global land areas , 2017 .

[19]  Dominique Arrouays,et al.  Digital soil mapping and GlobalSoilMap. Main advances and ways forward , 2020 .

[20]  Zhaolin,et al.  Spatial Variation in Biomass and Its Relationships to Soil Properties in the Permafrost Regions Along the Qinghai-Tibet Railway , 2017 .

[21]  Yoan Fourcade,et al.  Paintings predict the distribution of species, or the challenge of selecting environmental predictors and evaluation statistics , 2018 .

[22]  Yones Khaledian,et al.  Selecting appropriate machine learning methods for digital soil mapping , 2020, Applied Mathematical Modelling.

[23]  Budiman Minasny,et al.  Pedology and digital soil mapping (DSM) , 2019, European Journal of Soil Science.

[24]  Linking thaw depth with soil moisture and plant community composition: effects of permafrost degradation on alpine ecosystems on the Qinghai-Tibet Plateau , 2013, Plant and Soil.

[25]  Raimon Tolosana-Delgado,et al.  "compositions": A unified R package to analyze compositional data , 2008, Comput. Geosci..

[26]  Lin Zhao,et al.  A new map of permafrost distribution on the Tibetan Plateau , 2016 .

[27]  B. Minasny,et al.  Regression rules as a tool for predicting soil properties from infrared reflectance spectroscopy , 2008 .

[28]  Witold R. Rudnicki,et al.  Feature Selection with the Boruta Package , 2010 .

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

[30]  Marvin N. Wright,et al.  SoilGrids250m: Global gridded soil information based on machine learning , 2017, PloS one.

[31]  Jun Qin,et al.  Parameterizing soil organic carbon’s impacts on soil porosity and thermal parameters for Eastern Tibet grasslands , 2012, Science China Earth Sciences.

[32]  Yongxia Ding,et al.  1 km monthly temperature and precipitation dataset for China from 1901 to 2017 , 2019, Earth System Science Data.

[33]  P. Filzmoser,et al.  Outlier Detection for Compositional Data Using Robust Methods , 2008 .

[34]  Y. Sheng,et al.  Mapping the permafrost stability on the Tibetan Plateau for 2005–2015 , 2020, Science China Earth Sciences.

[35]  S. Marchenko,et al.  Impacts of climate-induced permafrost degradation on vegetation: A review , 2020 .

[36]  M. C. Jones,et al.  The Statistical Analysis of Compositional Data , 1986 .

[37]  Xiaodong Wu,et al.  Soil taxonomy and distribution characteristics of the permafrost region in the Qinghai-Tibet Plateau, China , 2015, Journal of Mountain Science.

[38]  Alex B. McBratney,et al.  Machine learning for digital soil mapping: Applications, challenges and suggested solutions , 2020 .

[39]  Xin Li,et al.  A new three-band spectral index for mitigating the saturation in the estimation of leaf area index in wheat , 2017 .

[40]  Laura Poggio,et al.  A note on knowledge discovery and machine learning in digital soil mapping , 2019, European Journal of Soil Science.

[41]  V. Adamchuk,et al.  Three-dimensional digital soil mapping of multiple soil properties at a field-scale using regression kriging , 2020 .

[42]  Alfred E. Hartemink,et al.  Digital Mapping of Soil Particle-Size Fractions for Nigeria Pedology , 2022 .

[43]  Thorsten Behrens,et al.  On the interpretability of predictors in spatial data science: the information horizon , 2020, Scientific Reports.

[44]  Thorsten Behrens,et al.  The relevant range of scales for multi-scale contextual spatial modelling , 2019, Scientific Reports.

[45]  Fei Yang,et al.  High-resolution and three-dimensional mapping of soil texture of China , 2020 .

[46]  Lin Zhao,et al.  Soil distribution modeling using inductive learning in the eastern part of permafrost regions in Qinghai–Xizang (Tibetan) Plateau , 2015 .

[47]  Zamir Libohova,et al.  GlobalSoilMap: Basis of the Global Spatial Soil Information System , 2015 .

[48]  A. Zhu,et al.  A China data set of soil properties for land surface modeling , 2013 .

[49]  Jongsung Kim,et al.  Holistic environmental soil-landscape modeling of soil organic carbon , 2014, Environ. Model. Softw..

[50]  Lin Zhao,et al.  Modeling permafrost changes on the Qinghai–Tibetan plateau from 1966 to 2100: A case study from two boreholes along the Qinghai–Tibet engineering corridor , 2019, Permafrost and Periglacial Processes.

[51]  Guo Zheng,et al.  Changes of grassland ecosystem due to degradation of permafrost frozen soil in the Qinghai-Tibet Plateau , 2007 .

[52]  Gan‐Lin Zhang,et al.  Mapping Soil Particle Size Fractions Using Compositional Kriging, Cokriging and Additive Log-ratio Cokriging in Two Case Studies , 2014, Mathematical Geosciences.

[53]  Hailiang Dong,et al.  Shifts of methanogenic communities in response to permafrost thaw results in rising methane emissions and soil property changes , 2018, Extremophiles.

[54]  Zne-Jung Lee,et al.  Parameter determination of support vector machine and feature selection using simulated annealing approach , 2008, Appl. Soft Comput..