Super-resolution reconstruction of sea surface pollutant diffusion images based on deep learning models: a case study of thermal discharge from a coastal power plant

被引:0
作者
Duan, Yafei [1 ,2 ,3 ]
Liu, Zhaowei [1 ,2 ,3 ]
Li, Manjie [4 ]
机构
[1] Tsinghua Univ, State Key Lab Hydrosci & Engn, Beijing, Peoples R China
[2] Tsinghua Univ, Key Lab Hydrosphere Sci, Minist Water Resources, Beijing, Peoples R China
[3] Tsinghua Univ, Dept Hydraul Engn, Beijing, Peoples R China
[4] Tsinghua Univ, Shenzhen Int Grad Sch, Shenzhen, Peoples R China
基金
中国国家自然科学基金;
关键词
super resolution (SR); deep learning; thermal discharge; transport and diffusion field; thermal infrared remote sensing; NETWORK;
D O I
10.3389/fmars.2023.1211981
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
While remote sensing images could convey essential information of surface water environment, the low spatial resolution limits their application. This study carried out a series of experiment tests of thermal discharge from a coastal power plant and constructed an image dataset HY_IRS, representing the transport and diffusion of discharged heated water in tidal waters. Two image super-resolution (SR) reconstruction models based on deep learning (DL), ESPCN and ESRGAN, were trained based on this dataset and then used to reconstruct high-resolution remote sensing images. It shows that the two DL models can markedly improve the spatial resolution of the surface diffusion image of thermal discharging, with the PSNR improved by 8.3% on average. The trained two models were successfully used to improve the spatial resolution of thermal infrared remote sensing SST images from Landsat8 TIRS, indicating that the SR model based on DL has a good effect and a crucial application prospect in the field of improving the resolution of pollutant diffusion remote sensing images.
引用
收藏
页数:9
相关论文
共 18 条
[1]  
Barsi JA, 2003, INT GEOSCI REMOTE SE, P3014
[2]   A comprehensive review of deep learning-based single image super-resolution [J].
Bashir, Syed Muhammad Arsalan ;
Wang, Yi ;
Khan, Mahrukh ;
Niu, Yilong .
PEERJ COMPUTER SCIENCE, 2021,
[3]   Learning a Deep Convolutional Network for Image Super-Resolution [J].
Dong, Chao ;
Loy, Chen Change ;
He, Kaiming ;
Tang, Xiaoou .
COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 :184-199
[4]   Remote Sensing Image Super-Resolution Using Novel Dense-Sampling Networks [J].
Dong, Xiaoyu ;
Sun, Xu ;
Jia, Xiuping ;
Xi, Zhihong ;
Gao, Lianru ;
Zhang, Bing .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (02) :1618-1633
[5]  
ESRGAN, ENH SUP RES GEN ADV
[6]   Remote sensing image super-resolution using cascade generative adversarial nets [J].
Guo, Dongen ;
Xia, Ying ;
Xu, Liming ;
Li, Weisheng ;
Luo, Xiaobo .
NEUROCOMPUTING, 2021, 443 :117-130
[7]  
[胡德勇 Hu Deyong], 2017, [武汉大学学报. 信息科学版, Geomatics and Information Science of Wuhan University], V42, P869
[8]   Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [J].
Ledig, Christian ;
Theis, Lucas ;
Huszar, Ferenc ;
Caballero, Jose ;
Cunningham, Andrew ;
Acosta, Alejandro ;
Aitken, Andrew ;
Tejani, Alykhan ;
Totz, Johannes ;
Wang, Zehan ;
Shi, Wenzhe .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :105-114
[9]   Image super-resolution: A comprehensive review, recent trends, challenges and applications [J].
Lepcha, Dawa Chyophel ;
Goyal, Bhawna ;
Dogra, Ayush ;
Goyal, Vishal .
INFORMATION FUSION, 2023, 91 :230-260
[10]   Hyperspectral Image Super-Resolution by Band Attention Through Adversarial Learning [J].
Li, Jiaojiao ;
Cui, Ruxing ;
Li, Bo ;
Song, Rui ;
Li, Yunsong ;
Dai, Yuchao ;
Du, Qian .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (06) :4304-4318