草原露天矿区草地沙化的遥感分析——以霍林河矿区为例

Research on Desertification of Grassland in Prairie Coalmine Based on Remote Sensing Data ——Case study of Huolinhe Coalmine

研究了霍林河矿区1987—2003年的草地沙化情况;探讨了露天煤矿区草地沙化的影响因子;采用线性光谱混合分解模型(LSMM)完成了草地沙化信息的提取,对引发草地沙化的直接破坏信息则采用决策树和BP神经网络相结合的方法进行了提取.结果表明:随着累计原煤产量的增加,草地破坏面积和草地沙化面积在逐年扩大;矿区建设期内草地沙化速率远高于生产期;草地直接破坏面积与草地沙化面积具有明显的正相关关系,故可将草地直接破坏面积作为评价、预测该区煤炭开发对周围草地沙化影响的重要依据.

The desertification of grassland from 1987 to 2003 in Huolinhe coalmine is studied. Factors inducing desertification of grassland in opencast coalmine are discussed. The information of grassland desertification is extracted by linear spectral mixture model while the direct destruction information inducing grassland desertification is extracted by decision-making tree and back-propagation neural network. The result shows that with the increase of coal output, the area of destruction and desertification of grassland keep enlarging year by year. The expanding of grassland desertification during the construction period of coalmine is more rapider than that during the production period. There is a positive correlation between the area of direct destruction and the area of desertification. So the area of direct destruction can be used as an important assessment and prediction indicator for grassland desertification around coalmines.