论文信息 - The Study on Estimating Grassland NPP based on BP Neural Network Algorithm

The Study on Estimating Grassland NPP based on BP Neural Network Algorithm

Grassland NPP is an important component of the carbon cycle of terrestrial ecosystems, which can directly measure the carrying capacity of grassland ecosystem. Considering the disadvantages of the existing NPP estimated models, this study adopt BP neural network model to estimate the NPP for XilinGol grassland based on the meteorological, field sample, DEM and remote sensing data. Our results showed that: (1) The trained BPNN not only has excellent performance for estimating NPP for the trained dataset, but also has good generation and portability, which can be applied for other pixels; (2)The spatial pattern of the grassland NPP has obviously horizontal zonal regularity, which rises from 0 to >300gC/m2 from west to east.

Zhijun Tong | Jiquan Zhang | Xiangqian Li | Xingpeng Liu

[1] D. Marcek. Risk Scenes of Managerial Decision-Making with Incomplete Information: An Assessment in Forecasting Models Based on Statistical and Neural Networks Approach , 2013 .

[2] M. Tamura,et al. Integrating remotely sensed data with an ecosystem model to estimate net primary productivity in East Asia , 2002 .

[3] Taylor H. Ricketts,et al. The consequences of urban land transformation on net primary productivity in the United States , 2004 .

[4] Kun Yang,et al. BP neural network integration model research for hydraulic metal structure health diagnosing , 2014, Int. J. Comput. Intell. Syst..

[5] J. Randerson,et al. Primary production of the biosphere: integrating terrestrial and oceanic components , 1998, Science.