欢迎访问《应用生态学报》官方网站,今天是 分享到:

应用生态学报

• 研究报告 • 上一篇    下一篇

基于神经网络模型和地统计学方法的土壤养分空间分布预测

李启权1,王昌全1**,张文江2,余勇3,李冰1,杨娟1,白根川1,蔡艳1   

  1. 1四川农业大学资源环境学院, 成都 611130; 2四川大学水力学与山区河流开发保护国家重点实验室, 成都 610065;3四川农业大学林学院, 四川雅安 625014)
  • 出版日期:2013-02-18 发布日期:2013-02-18

Prediction of soil nutrients spatial distribution based on neural network model combined with goestatistics.

LI Qi-quan1, WANG Chang-quan1, ZHANG Wen-jiang2, YU Yong3, LI Bing1, YANG Juan1, BAI Gen-chuan1, CAI Yan1   

  1. (1College of Resources and Environment, Sichuan Agricultural University, Chengdu 611130, China; 2State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu 610065, China; 3College of Forestry, Sichuan Agricultural University, Ya’an 625014, Sichuan, China)
  • Online:2013-02-18 Published:2013-02-18

摘要: 采用径向基函数神经网络模型与普通克里格法相结合的方法,预测川中丘陵区县域尺度土壤养分(有机质和全氮)的空间分布,并与普通克里格法和回归克里格法进行比较.结果表明:各方法对研究区土壤养分的预测结果相似.与多元回归模型相比,神经网络模型对验证样点土壤有机质和全氮的预测值与样点实测值的相关系数分别提高了12.3%和16.5%,表明神经网络模型能更准确地捕捉土壤养分与定量环境因子间的复杂关系.对469个验证样点预测结果的误差分析表明,神经网络模型与普通克里格法相结合的方法对土壤有机质和全氮预测结果的平均绝对误差、平均相对误差、均方根误差较普通克里格法分别降低了6.9%、7.4%、5.1%和4.9%、6.1%、4.6%,降低幅度达到极显著水平(P<0.01);与回归克里格法相比则分别降低了2.4%、2.6%、1.8%和2.1%、2.8%、2.2%,降低幅度达显著水平(P<0.05).

Abstract:

In this study, a radial basis function neural network model combined with ordinary kriging (RBFNN_OK) was adopted to predict the spatial distribution of soil nutrients (organic matter and total N) in a typical hilly region of Sichuan Basin, Southwest China, and the performance of this method was compared with that of ordinary kriging (OK) and regression kriging (RK). All the three methods produced the similar soil nutrient maps. However, as compared with those obtained by multiple linear regression model, the correlation coefficients between the measured values and the predicted values of soil organic matter and total N obtained by neural network model increased by 12.3% and 16.5%, respectively, suggesting that neural network model could more accurately capture the complicated relationships between soil nutrients and quantitative environmental factors. The error analyses of the prediction values of 469 validation points indicated that the mean absolute error (MAE), mean relative error (MRE), and root mean squared error (RMSE) of RBFNN_OK were 6.9%, 7.4%, and 5.1% (for soil organic matter), and 4.9%, 6.1%, and 4.6% (for soil total N) smaller than those of OK (P<0.01), and 2.4%, 2.6%, and 1.8% (for soil organic matter), and 2.1%, 2.8%, and 2.2% (for soil total N) smaller than those of RK, respectively (P<0.05).