Inversion analysis of chlorophyll a concentration in Wuliangsuhai based on GA-BP neural network

Ren Dawei; Fu Xueliang; Li Honghui; Hu Hua; Gao Ge

doi:10.1117/12.2638804

17 May 2022 Inversion analysis of chlorophyll a concentration in Wuliangsuhai based on GA-BP neural network

Ren Dawei, Fu Xueliang, Li Honghui, Hu Hua, Gao Ge

Proceedings Volume 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022); 122595B (2022) https://doi.org/10.1117/12.2638804
Event: 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing, 2022, Kunming, China

Abstract

In order to invert the concentration of chlorophyll a in the water of Wuliangsuhai, based on the remote sensing image data of Sentinel-2 satellite, the data on the concentration of chlorophyll in Wuliangsuhai from the School of Water Conservancy and Civil Engineering of Inner Mongolia Agricultural University were used. The GA-BP neural network is constructed to improve the crossover operator and mutation operator of genetic algorithm by adding new decisions. At the same time, a new strategy is added to avoid the genetic algorithm falling into the local optimal solution. Finally, the inversion effect is compared with that of BP neural network. After BP neural network inversion, the determination coefficient 𝑅² = 0.876, mean square error MSE = 6.713 and mean absolute error MAE = 1.966 are obtained. GA-BP neural network shows that 𝑅² = 0.923, mean square error MSE = 4.619, mean absolute error MAE = 1.795. The above results can prove that GA-BP neural network has less error and high inversion accuracy as the model of chlorophyll a inversion in Wuliangsuhai water body.

Citation Download Citation

Ren Dawei, Fu Xueliang, Li Honghui, Hu Hua, and Gao Ge "Inversion analysis of chlorophyll a concentration in Wuliangsuhai based on GA-BP neural network", Proc. SPIE 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022), 122595B (17 May 2022); https://doi.org/10.1117/12.2638804

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