Identification of Phragmites australis and Spartina alterniflora in the Yangtze Estuary between Bayes and BP neural network using hyper-spectral data

Pudong Liu; Jiayuan Zhou; Runhe Shi; Chao Zhang; Chaoshun Liu; Zhibin Sun; Wei Gao

doi:10.1117/12.2236772

19 September 2016 Identification of Phragmites australis and Spartina alterniflora in the Yangtze Estuary between Bayes and BP neural network using hyper-spectral data

Pudong Liu, Jiayuan Zhou, Runhe Shi, Chao Zhang, Chaoshun Liu, Zhibin Sun, Wei Gao

Author Affiliations +

Proceedings Volume 9975, Remote Sensing and Modeling of Ecosystems for Sustainability XIII; 99750H (2016) https://doi.org/10.1117/12.2236772
Event: SPIE Optical Engineering + Applications, 2016, San Diego, California, United States

Abstract

The aim of this work was to identify the coastal wetland plants between Bayes and BP neural network using hyperspectral data in order to optimize the classification method. For this purpose, we chose two dominant plants (invasive S. alterniflora and native P. australis) in the Yangtze Estuary, the leaf spectral reflectance of P. australis and S. alterniflora were measured by ASD field spectral machine. We tested the Bayes method and BP neural network for the identification of these two species. Results showed that three different bands (i.e., 555 nm，711 nm and 920 nm) could be identified as the sensitive bands for the input parameters for the two methods. Bayes method and BP neural network prediction model both performed well (Bayes prediction for 88.57% accuracy, BP neural network model prediction for about 80% accuracy), but Bayes theorem method could give higher accuracy and stability.

Citation Download Citation

Pudong Liu, Jiayuan Zhou, Runhe Shi, Chao Zhang, Chaoshun Liu, Zhibin Sun, and Wei Gao "Identification of Phragmites australis and Spartina alterniflora in the Yangtze Estuary between Bayes and BP neural network using hyper-spectral data", Proc. SPIE 9975, Remote Sensing and Modeling of Ecosystems for Sustainability XIII, 99750H (19 September 2016); https://doi.org/10.1117/12.2236772

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