Quantitative research on soil erosion based on BP artificial neural network

Tingting Dong; Zengxiang Zhang; Lijun Zuo

doi:10.1117/12.748770

14 November 2007 Quantitative research on soil erosion based on BP artificial neural network

Tingting Dong, Zengxiang Zhang, Lijun Zuo

Proceedings Volume 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications; 67901E (2007) https://doi.org/10.1117/12.748770
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China

Abstract

It's well known that soil erosion is a complicated phenomenon. It's hard to express it with a uniform equation, however BP artificial neural network has great advantages of solving non-linear problems, so it can use BP artificial neural network to research on soil erosion quantitatively. In this research it lays out experiment in the east and west of Liaoning province. It measures 4 factors which mainly influence soil erosion except quantity of soil erosion. They are rainfall erosivity, slop, soil water content before rainfall and crop coverage. These data are composed of 85 samples in total. This paper builds double-layer BP artificial neural network for east region and west region respectively. It uses some samples to train BP artificial neural network and others to verify it. Research results show that judging from the errors these two BP artificial neural networks can be applied to research on soil erosion quantitatively. Simulative results can be used to confirm the rank of soil erosion. Comparing with the results of multi-factor orthogonal regression analysis using BP artificial neural network is much more approaching the real value. Besides it discusses the problems on BP artificial neural network application.

Citation Download Citation

Tingting Dong, Zengxiang Zhang, and Lijun Zuo "Quantitative research on soil erosion based on BP artificial neural network", Proc. SPIE 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications, 67901E (14 November 2007); https://doi.org/10.1117/12.748770

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available