论文部分内容阅读
利用2000~2014年统计数据,分析了宁夏近15 a来的耕地动态变化特征,采用主成分分析法提取影响耕地变化的主要驱动因子,将驱动因子作为输入数据,构建了预测耕地资源变化趋势的BP神经网络,并开展预测研究。结果表明:宁夏耕地资源变化经历了增加—迅速减少—波动增长—迅速增长4个阶段,人均耕地经历了迅速减少—缓慢减少—迅速增加3个阶段;其中,2002~2004年和2010~2012年的土地利用动态度K<0,2003年动态度最小(K=-7.673%),2005~2010年和2012~2014年的土地利用动态度K>0,2014年动态度最大(K=11.424%);宁夏耕地资源主要驱动因子概括为农业发展、经济发展及退耕还林,经济发展对耕地产生巨大压力,而农业科技进步某种程度减小了人口对耕地的压力,退耕还林也是宁夏耕地减少的重要原因,三者相互作用共同对宁夏耕地产生影响;预测宁夏耕地资源的BP神经网络模型为3层(3×16×1),对2011~2014年的耕地资源预测取得较好效果,最小误差仅为376 hm~2。
Using the statistical data from 2000 to 2014, the dynamic characteristics of cultivated land in Ningxia were analyzed in the past 15 years. Principal components analysis (PCA) was used to extract the main driving factors that affected the changes of cultivated land. The driving factors were used as input data to construct a forecasting trend of cultivated land resources BP neural network and carry out prediction research. The results showed that: the change of cultivated land resources in Ningxia experienced four stages of rapid increase, rapid decrease, fluctuating growth and rapid growth, the per capita cultivated land experienced three stages of rapid reduction, slow decrease and rapid increase. Among them, from 2002 to 2004 and from 2010 to 2012 (K = -7.673%) in 2003 and K> 0 in 2005 ~ 2010 and 2012 ~ 2014. The highest dynamic degree of land use was in 2014 (K = 11.424% ). The main driving forces of cultivated land resources in Ningxia are summarized as agricultural development, economic development and returning farmland to forests. The economic development exerts tremendous pressure on cultivated land. The progress of agricultural science and technology has reduced the population pressure on cultivated land to a certain extent. The interaction between the three factors has an impact on cultivated land in Ningxia. The BP neural network model for predicting the cultivated land resources in Ningxia is 3 layers (3 × 16 × 1), which has a good effect on the prediction of cultivated land resources from 2011 to 2014, The minimum error is only 376 hm ~ 2.