Welcome to the InfoSci Platform
Reference Hub3
Introducing a Hybrid Model SAE-BP for Regression Analysis of Soil Temperature With Hyperspectral Data

Introducing a Hybrid Model SAE-BP for Regression Analysis of Soil Temperature With Hyperspectral Data

Miaomiao Ji, Keke Zhang, Qiufeng Wu
Copyright: © 2020 |Volume: 11 |Issue: 3 |Pages: 14
ISSN: 1941-6237|EISSN: 1941-6245|EISBN13: 9781799805731|DOI: 10.4018/IJACI.2020070104
Cite Article Cite Article

MLA

Ji, Miaomiao, et al. "Introducing a Hybrid Model SAE-BP for Regression Analysis of Soil Temperature With Hyperspectral Data." IJACI vol.11, no.3 2020: pp.66-79. http://doi.org/10.4018/IJACI.2020070104

APA

Ji, M., Zhang, K., & Wu, Q. (2020). Introducing a Hybrid Model SAE-BP for Regression Analysis of Soil Temperature With Hyperspectral Data. International Journal of Ambient Computing and Intelligence (IJACI), 11(3), 66-79. http://doi.org/10.4018/IJACI.2020070104

Chicago

Ji, Miaomiao, Keke Zhang, and Qiufeng Wu. "Introducing a Hybrid Model SAE-BP for Regression Analysis of Soil Temperature With Hyperspectral Data," International Journal of Ambient Computing and Intelligence (IJACI) 11, no.3: 66-79. http://doi.org/10.4018/IJACI.2020070104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Soil temperature, as one of the critical meteorological parameters, plays a key role in physical, chemical and biological processes in terrestrial ecosystems. Accurate estimation of dynamic soil temperature is crucial for underground soil ecological research. In this work, a hybrid model SAE-BP is proposed by combining stacked auto-encoders (SAE) and back propagation (BP) algorithm to estimate soil temperature using hyperspectral remote sensing data. Experimental results show that the proposed SAE-BP model achieves a more stable and effective performance than the existing logistic regression (LR), support vector regression (SVR) and BP neural network with an average value of mean square error (MSE) = 1.926, mean absolute error (MAE) = 0.962 and coefficient of determination (R2) = 0.910. In addition, the effect of hidden structures and labeled training data ratios in SAE-BP is further explored. The SAE-BP model demonstrates the potential in high-dimensional and small hyperspectral datasets, representing a significant contribution to soil remote sensing.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.