面向越野通行分析的土壤数据分类方法研究  

Soil Data Construction Method for Cross-country Trafficability Analysis

作　　者：李坤伟[1] 游雄[1] 张欣[1] 汤奋[1] Li Kunwei;You Xiong;Zhang Xin;Tang Fen(Institute of Surveying and Mapping,Information Engineering University,Zhengzhou 450052,China)

机构地区：[1]信息工程大学地理空间信息学院

出　　处：《系统仿真学报》2019年第1期158-165,共8页Journal of System Simulation

摘　　要：土壤是影响部队越野机动的重要因素,土壤与气象因素相结合使得越野通行性分析变得异常复杂。基于统一土壤分类系统(Unified Soil Classification System,USCS)的土壤数据是定量分析土壤通行性的基础,采用随机森林方法,利用土壤的多种属性信息来预测土壤的USCS类型。从已有的USCS土壤数据中提取样本数据构建8种随机森林模型,对不同随机森林模型的精度和特征变量的重要性进行分析,根据土壤数据集的特点采用第三种随机森林模型对其进行处理,构建适合越野通行分析的土壤数据。相比以往的方法,这种方法精度更高,更能满足越野通行分析的需要。Soil is one of the most important factors influencing the off-road maneuver of the army.The combination of soil and weather factors makes cross-country trafficability analysis extremely complicated.The soil data from unified soil classification system(USCS) are the basis for the analysis of soil trafficability.In this paper,the random forest method is used to predict the type of soil by using various attribute information.The method extracts sample data from existing USCS soil data to construct multiple random forest models,then analyses the accuracy of random forests and the importance of characteristic variables,and finally uses the third random forest model to process soil database according to the characteristics of the data.Compared with the previous methods,this method is more accurate and can meet the requirements of cross-country trafficability analysis.

关 键 词：越野机动 土壤数据 随机森林 圆锥指数 

分 类 号：S153[农业科学—土壤学]