国土资源遥感
國土資源遙感
국토자원요감
REMOTE SENSING FOR LAND & RESOURCES
2014年
2期
184-189
,共6页
土地覆盖%遥感%CA-Markov模型%模拟预测%秦淮河流域
土地覆蓋%遙感%CA-Markov模型%模擬預測%秦淮河流域
토지복개%요감%CA-Markov모형%모의예측%진회하류역
land cover%remote sensing%CA-Markov model%simulation and forecast%Qinhuai River Basin
以秦淮河流域为研究区,以2006和2009年ETM+图像土地覆盖分类结果为输入数据,采用CA-Markov模型,模拟预测研究区未来的土地覆盖格局。在模型建立过程中,通过Markov模型求出转移概率矩阵和转移面积矩阵,确定CA模型转换规则,限制CA模型迭代次数。利用CA-Markov模型模拟预测研究区2012和2018年土地覆盖格局,并采用2012年实际土地覆盖分类结果验证预测精度,得到2012年各土地覆盖类型栅格数预测误差均小于等于6.5%,空间位置预测精度达到76.5%。预测结果表明,2018年研究区水田比例将降为33.3%,不透水面比例将达31.1%,其中多数水田转变成为不透水面,南京城区、禄口镇、句容市、溧水县等城镇地区的不透水面明显扩张。该方法可以对秦淮河流域的土地覆盖动态监测以及可持续发展提供依据。
以秦淮河流域為研究區,以2006和2009年ETM+圖像土地覆蓋分類結果為輸入數據,採用CA-Markov模型,模擬預測研究區未來的土地覆蓋格跼。在模型建立過程中,通過Markov模型求齣轉移概率矩陣和轉移麵積矩陣,確定CA模型轉換規則,限製CA模型迭代次數。利用CA-Markov模型模擬預測研究區2012和2018年土地覆蓋格跼,併採用2012年實際土地覆蓋分類結果驗證預測精度,得到2012年各土地覆蓋類型柵格數預測誤差均小于等于6.5%,空間位置預測精度達到76.5%。預測結果錶明,2018年研究區水田比例將降為33.3%,不透水麵比例將達31.1%,其中多數水田轉變成為不透水麵,南京城區、祿口鎮、句容市、溧水縣等城鎮地區的不透水麵明顯擴張。該方法可以對秦淮河流域的土地覆蓋動態鑑測以及可持續髮展提供依據。
이진회하류역위연구구,이2006화2009년ETM+도상토지복개분류결과위수입수거,채용CA-Markov모형,모의예측연구구미래적토지복개격국。재모형건립과정중,통과Markov모형구출전이개솔구진화전이면적구진,학정CA모형전환규칙,한제CA모형질대차수。이용CA-Markov모형모의예측연구구2012화2018년토지복개격국,병채용2012년실제토지복개분류결과험증예측정도,득도2012년각토지복개류형책격수예측오차균소우등우6.5%,공간위치예측정도체도76.5%。예측결과표명,2018년연구구수전비례장강위33.3%,불투수면비례장체31.1%,기중다수수전전변성위불투수면,남경성구、록구진、구용시、률수현등성진지구적불투수면명현확장。해방법가이대진회하류역적토지복개동태감측이급가지속발전제공의거。
Based on the classified result of Landsat ETM+ remote sensing images of 2006 and 2009 , the paper simulated and forecasted land cover types of Qinhuai River Basin in the future by using the CA-Markov model. In the model-building process, the transition probability matrix and the transition area matrix were obtained through the Markov model, which determined the conversion rules and iterative times of the CA model. The land cover pattern of the study area in 2012 and 2018 was simulated and forecasted with the CA-Markov model. Then the forecast result was compared with the actual classified data of 2012 to verify the forecast accuracy. The raster number forecast error of each land cover type is not higher than 6. 5%, and the spatial location accuracy is 76. 5%. The forecast results show that the paddy field decreased to 33 . 3 % and the impervious surface reached 31 . 1 % of Qinhuai River Basin in 2018. Most of the paddy field converted into impervious surface. The impervious surface of urban areas expands obviously in such urban areas as Nanjing, Lukou, Jurong and Lishui. The methods can provide a basis for dynamic monitoring as well as sustainable development of Qinhuai River Basin.
