Laser & Optoelectronics Progress, Volume. 58, Issue 20, 2001001(2021)
Inversion of Suspended Particulate Matter Concentration in Maozhou River Based on Band Selection of Hyperspectral Data
Aiming at the inversion of suspended particulate matter (SPM) concentration using hyperspectral data, this paper proposes a supervised band selection method based on pre-trained neural networks (PNNs), and employs the random forest and neural network to establish an inversion model of SPM concentration. The PNN method needs to perform multiple repeated experiments to obtain sufficient and low-noise expression of band importance. In each experiment, an appropriate number of bands is selected as the features of input data of neural networks. Then, we train a neural network and obtain weights of the first layer in the last training epoch. Finally, we use the L1 norm, L2 norm, and ReLU (Rectified Linear Unit) function of the weights to represent the importance of the bands. The experiment results show that the PNN method using L1 norm and L2 norm can obtain a more informative band set, and perform better when used for SPM concentration inversion.
Get Citation
Copy Citation Text
Zhongkai Chen, Xiaorun Li, Liaoying Zhao. Inversion of Suspended Particulate Matter Concentration in Maozhou River Based on Band Selection of Hyperspectral Data[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2001001
Category: Atmospheric Optics and Oceanic Optics
Received: Oct. 26, 2020
Accepted: Jan. 7, 2021
Published Online: Oct. 12, 2021
The Author Email: Li Xiaorun (lxr@zju.edu.cn)