Research on the Lake Surface Water Temperature Downscaling Based on Deep Learning

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing 2021, Vol.14, p.5550-5558
• Main Authors: Yu, Zhenyu, Yang, Kun, Luo, Yi, Wang, Pei, Yang, Ze
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Artificial satellites; Climate change; Deep learning; DisTrad; downscaling; Earth; Global warming; High temperature; Human influences; Image resolution; Lake shores; lake surface water temperature (LSWT); Lakes; Landsat; Landsat satellites; MODIS; Neural networks; plateau lakes; Remote sensing; Residential areas; Resolution; Satellite imagery; Spatial discrimination; Spatial resolution; Statistical analysis; Statistical methods; super-resolution convolutional neural network (SRCNN); Surface temperature; Surface water; Temporal resolution; Water temperature
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2021.3079357

Lake surface water temperature (LSWT) is an important factor of water ecological environment. As global warming, LSWT is also on the rise. Research on the main reasons of LSWT rising is the basis for controlling and improving the regional ecological environment. However, it is difficult for the existing remote sensing images to take into account the temporal and spatial resolution. Low-resolution images have a serious impact on data accuracy and even produce incorrect results. Therefore, obtaining high temporal and spatial resolution images by downscaling is of great significance to more accurately analyze the temporal and spatial characteristics of LSWT. In this article, Dianchi Lake is selected as research area, and the high spatial resolution image (Landsat) and high temporal resolution image (MODIS) are taken as data. Based on the downscaling algorithm of statistics and learning, DisTrad- super-resolution convolutional neural network (SRCNN) downscaling model is proposed, and the monthly average dataset of LSWT with 50 m resolution is constructed. The results showed 1) DisTrad-SRCNN can reflect the most distribution characteristics of LSWT (SSIM day = 0.96, PSNR day = 23.97; SSIM night = 0.95, PSNR night = 24.99). 2) LSWT had an overall upward trend (CR day = 0.22 °C/10a, CR night = 0.21 °C/10a), showing a cyclical change of cold-warm-cold about 4 years. 3) The northern and lakeshore area were basically in the high temperature, and the whole lake presents a 4-5-year warm-cold-warm periodic change; the LSWT closer to the urban and residential areas and its change rate were relatively high, which indirectly reflected the serious impact of human activities on LSWT.