关键词: 土壤质地, 空间分布, 因素分析, 随机森林, 宁夏

Abstract: 【Objective】Based on historical soil data, this paper studied the spatial variability of soil texture and its relationship with environmental factors in the loess region using machine learning.【Method】Classification and regression tree (CART), random forest (RF) and traditional statistical methods were used to explore the main environmental factors that affect the soil texture types and predict the spatial distribution of soil texture types in southern Ningxia, based on 428 soil profiles from the second soil survey in the 1980s, combined with topographic factors, soil types, and normalized vegetation Index. And the accuracy of the models were verified by the validating set of soil profiles and the soil samples in Haiyuan County, Ningxia.【Result】The accuracy rates of RF and CART on the soil texture type of the verification set of soil profiles were 62.36% and 55.29%, respectively. The area under the receiver operating characteristic (ROC) curve (Area Under ROC Curve, AUC) are 0.7515 and 0.6933, respectively. The accuracy rates on soil samples in Haiyuan County are 54.10% and 48.36% respectively, and the AUC are 0.6599 and 0.5981 respectively. Soil type (ST) is the most important predictor variable, followed by elevation (Ele), the higher elevation, the heavier and the soil texture. And finally wind exposition index (WEI) and slope (Slo). Results predicted by two methods show a spatial distribution trend that the soil texture is heavy in the southern area but light in the northern area of southern Ningxia.【Conclusion】The prediction accuracy of RF for soil texture type in southern Ningxia is higher than CART. Making full use of historical data, combined with field sampling, can meet the accuracy requirements of digital mapping. In the loess region, soil types and elevation are the environmental factors which have strong correlation with spatial variation of soil texture.

Key words: soil texture, spatial distribution, factor analysis, random forest