基于多源数据的土壤越野通行性评估  

Evaluation of Soil Trafficability Based on Multi-Source Data

作　　者：李坤伟[1] 游雄[1] 张欣[1] 汤奋 LI Kunwei;YOU Xiong;ZHANG Xin;TANG Fen(Information Engineering University,Zhengzhou 450001,China)

机构地区：[1]信息工程大学,河南郑州450001

出　　处：《测绘科学技术学报》2018年第2期206-210,共5页Journal of Geomatics Science and Technology

摘　　要：针对现有土壤通行性评估方法的不足,基于多源环境数据,以圆锥指数为指标对土壤通行性进行定量分析。高精度的USCS(Unified Soil Classification System)类型土壤数据和降雨数据是定量分析土壤通行性的基础。首先采用随机森林方法将已有的土壤数据转换成USCS类型;然后将气象站降雨数据和卫星降雨进行融合,构建高精度的降雨数据;最后利用圆锥指数模型计算土壤的圆锥指数,通过比较车辆圆锥指数和土壤圆锥指数的大小对土壤的通行性能进行评价。对比现有的方法,该方法精度更高,适应性更强。In view of the shortcomings of the existing soil trafficability assessment method,the cone index is used as an index to quantitatively analyze the soil trafficability based on the existing environmental data. High precision USCS type soil data and rainfall data are the basis for quantitative analysis of soil trafficability. Firstly,the existing soil data are converted into USCS using the random forest method,and then the weather station rainfall data and satellite rainfall are merged to build high-precision rainfall data. Finally,the soil cone index is calculated by using the cone index model and the trafficability of the soil is evaluated by comparing vehicle cone index and soil cone index. Compared with the existing method,this method in the paper is more accurate and more adaptable.

关 键 词：越野机动 多源数据 圆锥指数 土壤通行性 随机森林 

分 类 号：P208[天文地球—地图制图学与地理信息工程] E991[天文地球—测绘科学与技术]