基于OLI数据的滇中地区湿地信息提取研究

以研究滇中湿地分布情况为目的,基于Landsat8OLI遥感影像,分别采用最大似然法和决策树法提取研究区湿地信息,并从空间格局与地理学角度分析湿地分布情况及其与社会经济的相关性。结果表明:(1)采用决策树法可以有效提取湿地,其总体精度为81.10%,与最大似然法相比分类精度提高了9.19%;(2)滇中湿地呈现以库塘为主,河流和湖泊次之,水田和沼泽最少的格局,湿地分布与其形成的地貌、气候、水文等自然地理条件密切相关;(3)湿地面积与社会经济发展具有一定的相关关系,总体上4市(州)(包括昆明市、玉溪市、曲靖市和楚雄彝族自治州)湿地面积与人口、工业和地区生产总值呈正相关。

WETLAND INFORMATION EXTRACTION IN THE CENTRAL YUNNAN PROVINCE BASED ON OLI DATA

For the purpose of studying the distribution of wetlands in the Central Yunnan Province,based on the Landsat8 OLI remote sensing image,the maximum likelihood method and the decision tree method were used to extract the wetland information in the study area,and the distribution of wetlands and their correlation with social economy were analyzed from the perspective of spatial dimension and geography.The research results are as follows:(1)the decision tree method using the partition classification idea can extract the wetland effectively,the overall accuracy is 81.10%,and the classification accuracy was improved by 9.19%compared with the maximum likelihood method;(2)Wetlands in the Central Yunnan Province were dominated by reservoir and pond,followed by rivers and lakes,and the paddy fields and marshes were the least.The distribution of wetlands is closely related to the geomorphological,climatic,hydrological and other natural geographical conditions;(3)The wetland area had a certain correlation with the development of social economy,In generally,the wetland area of the four cities(states)is positively correlated with the population,industry and regional GDP.