1990-2020年辽西地区土地利用变化及驱动力分析

Analysis of Land Use Variation and Driving Forces in Western Liaoning Province from 1990 to 2020

基于1990,1996,2002,2008,2014和2020年共6期LandSat系列遥感影像数据,探究辽西地区1990—2020年30年间的土地利用和土地覆盖(Land Use and Land Cover,LULC)格局及转移状况。基于支持向量机(Support Vector Machine,SVM)设计适用于辽西地区LULC的多分类器,实现该地区典型地物的分类;使用转移矩阵定量分析该地区LULC的转移情况;采用主成分分析(Principal Component Analysis,PCA)法,分析造成该地区30年间LULC类型转移的主要驱动力。研究表明,辽西地区主要是以耕地和林地为主,占总面积70%以上;建筑用地和未利用土地次之;草地和水域面积最小。30年间各类土地以耕地、林地、建筑用地、未利用土地为主导,发生不同程度的空间变化,其中建筑用地除了1996—2002年少量减少外,其余各期持续增加;耕地除1990-2002年增加了2041.73 km^(2)外,其余4期持续减少;林地增加最多,达到了3556.41 km^(2)。导致辽西地区LULC发生变化的主要驱动力是人口增长、经济发展以及气候因素。

Based on the serial remote sensing images from LandSat in 1990,1996,2002,2008,2014 and 2020,the land use and land cover(LULC)pattern and transfer in western Liaoning province from 1990 to 2020 are explored.Based on support vector machine(SVM),a multi-classifier method suitable for LULC in western Liaoning province is designed to realize the classification of typical features in this area.A transfer matrix is used to quantitatively analyze the transfer of LULC in this area.The principal component analysis(PCA)method is used to analyze the main driving forces of LULC type transfer in this area in the past 30 years.The results show that cultivated land and woodland constitute the main part of western Liaoning,accounting for more than 70%of the total area;construction land and unused land are the secondary part;grassland and water area are the smallest.In the past 30 years,all types of land,especially cultivated land,forest land,construction land and unused land,experienced different degrees of spatial variation.Except for a small decrease in 1996-2002,the construction land continuously increased in other periods;except for an increase of 2041.73 km^(2) in 1990-2002,the cultivated land continuously decreased in the other four periods;the woodland increased the most,reaching 3556.41 km^(2).The main driving forces of LULC variation in western Liaoning are population growth,economic development and climate factors.