Predicting soil property in hilly regions by using landscape and multiscale micro-landform features

doi:10.13287/j.1001-9332.202202.013

Abstract

Abstract: To assess the high-resolution digital soil mapping method for small watersheds in hilly areas, we explored the role of landscape classification and multiscale micro-landform features in predicting soil pH, soil clay content (SCC), and cation exchange capacity (CEC). Geomorphons (GM) terrain classification method was used to create landform units. The traditional digital elevation model (DEM) derivatives and remote sensing variables were employed for different combinations with landscape and micro-landform classification variables, with further compa-rison and analysis being conducted. In addition, three machine learning techniques, including support vector machine (SVM), partial least squares regression (PLSR), and random forest (RF), were used to build prediction models. The best method was then selected, and then combined with regression kriging by modeling spatial structure of the model residuals. The results showed that the application of landscape and multiscale micro-landform classification variables effectively improved the prediction accuracy of pH, SCC, and CEC by 18.8%, 8.2% and 8.7%, respectively. The map of landscape classification that contained vegetation coverage information had greater model contribution than land use data. The GM classification map with 5 m resolution was more suitable for high-precision DSM than those with lower resolution. The composite model of RF performed the best in predicting SCC, while the pH and CEC were not suitable for adding the residual regression kriging on the basis of RF model. Finally, the combination of landscape and multiscale micro-landform classification variables, DEM derivatives and remote sensing variables had the highest prediction accuracy for all the three soil properties. This result indicated that multivariable contained more effective soil information than single data source for rolling areas. The landscape variables composed of GM and surface classified data explained about 40% of the spatial variation of tested soil attributes in hilly area. Therefore, multi-resolution GM and landscape classified variables could be included into the construction of prediction model in research of soil mapping.

Key words: landscape classification, micro-landform, digital soil mapping, random forest, machine learning

WEI Yu-chen, ZHAO Mei-fang, ZHU Chang-da, ZHANG Xiu-xiu, PAN Jian-jun. Predicting soil property in hilly regions by using landscape and multiscale micro-landform features[J]. Chinese Journal of Applied Ecology, 2022, 33(2): 467-476.

References

[1] Amundson R, Berhe AA, Hopmans JW, et al. Soil and human security in the 21st century. Science, 2015, 348: 1261071
[2] Montanarella L, Pennock DJ, McKenzie N, et al. World's soils are under threat. Soil, 2016, 2: 79-82
[3] Scull P, Franklin J, Chadwick OA, et al. Predictive soil mapping: A review. Progress in Physical Geography: Earth and Environment, 2003, 27: 171-197
[4] Camera C, Zomeni Z, Noller JS, et al. A high resolution map of soil types and physical properties for Cyp-rus: A digital soil mapping optimization. Geoderma, 2017, 285: 35-49
[5] McBratney A, Mendonça SM, Minasny B. On digital soil mapping. Geoderma, 2003, 117: 3-52
[6] Pahlavan-Rad MR, Akbarimoghaddam A. Spatial variability of soil texture fractions and pH in a flood plain (case study from eastern Iran). Catena, 2018, 160: 275-281
[7] Dong W, Wu T, Luo J, et al. Land parcel-based digital soil mapping of soil nutrient properties in an alluvial-diluvia plain agricultural area in China. Geoderma, 2019, 340: 234-248
[8] Guo L, Zhang H, Chen YW, et al. Combining environmental factors and lab VNIR spectral data to predict SOM by geospatial techniques. Chinese Geographical Science, 2019, 29: 258-269
[9] Wen W, Wang Y, Yang L, et al. Mapping soil organic carbon using auxiliary environmental covariates in a typical watershed in the Loess Plateau of China: A comparative study based on three kriging methods and a soil land inference model (SoLIM). Environmental Earth Sciences, 2015, 73: 239-251
[10] Lizaga I, Quijano L, Gaspar L, et al. Linking land use changes to variation in soil properties in a Mediterranean mountain agroecosystem. Catena, 2019, 172: 516-527
[11] Malone BP, Hughes P, Mcbratney AB, et al. A model for the identification of terrons in the Lower Hunter. Geoderma Regional, 2015, 1: 31-47
[12] 卢浩东, 潘剑君, 付传城, 等. 面向土系调查制图的小尺度区域景观分类——以宁镇丘陵区中-小区域为例. 生态学报, 2014, 34(9): 2356-2366
[13] Mueller TG, Pierce FJ. Soil carbon maps. Soil Science Society of America Journal, 2003, 67: 258-267
[14] Brabyn L. Landscape classification using GIS and national digital databases. Landscape Research, 1996, 21: 277-300
[15] Iwahashi J, Pike RJ. Automated classifications of topography from DEMs by an unsupervised nested-means algorithm and a three-part geometric signature. Geomorphology, 2007, 86: 409-440
[16] Jasiewicz J, Stepinski TF. Geomorphons: A pattern reco-gnition approach to classification and mapping of landforms. Geomorphology, 2013, 182: 147-156
[17] 康鑫, 王彦文, 秦承志, 等. 多分析尺度下综合判别的地形元素分类方法. 地理研究, 2016, 35(9): 1637-1646
[18] Flynn T, Rozanov A, Ellis F, et al. Farm-scale soil patterns derived from automated terrain classification. Catena, 2020, 185: 104311
[19] Jiang Q, Hao Q, Peng S, et al. Grain-size evidence for the transport pathway of the Xiashu loess in northern subtropical China and its linkage with fluvial systems. Aeolian Research, 2020, 46: 100613
[20] 中国科学院南京土壤研究所土壤系统分类课题组, 中国土壤系统分类课题研究协作组. 中国土壤系统分类检索(第三版). 合肥: 中国科学技术大学出版社, 2001
[21] 全国农业技术推广服务中心. 土壤分析技术规范(第三版). 北京: 中国农业出版社, 2006
[22] Ngunjiri MW, Libohova Z, Owens PR, et al. Landform pattern recognition and classification for predicting soil types of the Uasin Gishu Plateau, Kenya. Catena, 2020, 188: 104390
[23] Atkinson J, de Clercq W, Rozanov A. Multi-resolution soil-landscape characterisation in KwaZulu Natal: Using geomorphons to classify local soilscapes for improved digital geomorphological modelling. Geoderma Regional, 2020, 22: e00291
[24] Grafius DR, Corstanje R, Warren PH, et al. The impact of land use/land cover scale on modelling urban ecosystem services. Landscape Ecology, 2016, 31: 1509-1522
[25] Chi Y, Shi H, Zheng W, et al. Simulating spatial distribution of coastal soil carbon content using a comprehensive land surface factor system based on remote sensing. Science of the Total Environment, 2018, 628-629: 384-399
[26] Cai W, Zhao S, Zhang Z, et al. Comparison of different crop residue indices for estimating crop residue cover using field observation data. 2018 7th International Conference on Agro-geoinformatics, Hangzhou, 2018: 1-4
[27] Zhou T, Zhao M, Sun C, et al. Exploring the impact of seasonality on urban land-cover mapping using multi-season Sentinel-1A and GF-1 WFV images in a subtropical monsoon-climate region. ISPRS International Journal of Geo-Information, 2017, 7: 3
[28] Pellikka P, Rees WG. Remote sensing of glaciers: Techniques for topographic, spatial, and thematic mapping of glaciers. Los Angeles, CA, USA: CRC Press, 2009
[29] Van GT, Suykens JAK, Baesens B, et al. Benchmar-king least squares support vector machine classifiers. Machine Learning, 2004, 54: 5-32
[30] Guo L, Sun X, Fu P, et al. Mapping soil organic carbon stock by hyperspectral and time-series multispectral remote sensing images in low-relief agricultural areas. Geoderma, 2021, 398: 115118
[31] Breiman L. Random Forest, Machine Learning. Los Angeles, CA, USA: CRC Press, 2001
[32] Behnamian A, Millard K, Banks SN, et al. A systema-tic approach for variable selection with random forests: Achieving stable variable importance values. IEEE Geoscience and Remote Sensing Letters, 2017, 14: 1988-1992
[33] Liaw A, Wiener M. Classification and Regression by RandomForest [EB/OL]. (2002-10-10) [2021-02-02]. http://cran. r-projec. org/web/packages/randomForest
[34] Zhou T, Geng Y, Chen J, et al. High-resolution digital mapping of soil organic carbon and soil total nitrogen using DEM derivatives, Sentinel-1 and Sentinel-2 data based on machine learning algorithms. Science of the Total Environment, 2020, 729: 138244
[35] Wang Y, Wang S, Adhikari K, et al. Effect of cultivation history on soil organic carbon status of arable land in northeastern China. Geoderma, 2019, 342: 55-64
[36] Essington ME. Soil and Water Chemistry: An Integrative Approach. Los Angeles, CA, USA: CRC Press, 2004
[37] Makungwe M, Chabala LM, Chishala BH, et al. Performance of linear mixed models and random forests for spatial prediction of soil pH. Geoderma, 2021, 397: 115079
[38] Odeh IOA, McBratney AB, Chittleborough DJ. Further results on prediction of soil properties from terrain attri-butes: Heterotopic cokriging and regression-Kriging. Geoderma, 1995, 67: 215-226
[39] 杜国华, 张甘霖, 赵文君. 土系的基本特点与划分. 土壤通报, 1999, 30(3-4): 10-12
[40] Libohova Z, Winzeler HE, Lee B, et al. Geomorphons: Landform and property predictions in a glacial moraine in Indiana landscapes. Catena, 2016, 142: 66-76
[41] 蔡祖聪, 马毅杰. 土壤有机质与土壤阳离子交换量的关系. 土壤学进展, 1988, 16(3): 10-15