How to cite this WIREs title:
WIREs Data Mining Knowl Discov
WIREs Data Mining Knowl Discov
Impact Factor: 4.476
Predicting land surface temperature with geographically weighed regression and deep learning
Focus Article
Published Online: Nov 03 2020
DOI: 10.1002/widm.1396
Can't access this content? Tell your librarian.
Abstract For prediction of urban remote sensing surface temperature, cloud, cloud shadow and snow contamination lead to the failure of surface temperature inversion and vegetation‐related index calculation. A time series prediction framework of urban surface temperature under cloud interference is proposed in this paper. This is helpful to solve the problem of the impact of data loss on surface temperature prediction. Spatial and temporal variation trends of surface temperature and vegetation index are analyzed using Landsat 7/8 remote sensing data of 2010 to 2019 from Beijing. The geographically weighed regression (GWR) method is used to realize the simulation of surface temperature based on the current date. The deep learning prediction network based on convolution and long short‐term memory (LSTM) networks was constructed to predict the spatial distribution of surface temperature on the next observation date. The time series analysis shows that the NDBI is less than −0.2, which indicates that there may be cloud contamination. The land surface temperature (LST) modeling results show that the precision of estimation using GWR method on impervious surface and water bodies is superior compared to the vegetation area. For LST prediction using deep learning methods, the result of the prediction on surface temperature space distribution was relatively good. The purpose of this study is to make up for the missing data affected by cloud, snow, and other interference factors, and to be applied to the prediction of the spatial and temporal distributions of LST. This article is categorized under: Technologies > Machine Learning
Study area in Beijing. (a) Jiufeng Forest Park, (b) the Imperial Palace, (c) Huairou Reservoir
[
Normal View
|
Magnified View
]
Land surface temperature (LST) prediction at the Imperial Palace using conv2DLSTM
[
Normal View
|
Magnified View
]
Relations between NDBI, NDVI, NDWI, and land surface temperature (LST) for all years at the Imperial Palace
[
Normal View
|
Magnified View
]
Land surface temperature (LST) analysis results obtained using geographically weighed regression (GWR) and ordinary least squares (OLS) at Imperial Palace on January 04, 2010
[
Normal View
|
Magnified View
]
Land surface temperature (LST) predicted using geographically weighed regression (GWR) in a pixel level
[
Normal View
|
Magnified View
]
Temporal and spatial difference of land surface temperature (LST) between different seasons in Beijing
[
Normal View
|
Magnified View
]
Remote sensing indices extracted from Landsat observed at Jiufeng forest park between 2010 and 2019. (a) Year‐wise box plot for Normalized Difference Vegetation Index at Jiufeng forest park. (b) Month‐wise box plot for Normalized Difference Vegetation Index at Jiufeng forest park; (c) Year‐wise box plot for Normalized Difference Water Index at Huairou reservoir. (d) Month‐wise box plot for Normalized Difference Water Index at Huairou reservoir. (e) Year‐wise box plot for Normalized Difference Built‐up Index at Imperial Palace. (f) Month‐wise box plot for Normalized Difference Built‐up Index at Imperial Palace
[
Normal View
|
Magnified View
]
Structure of conv2DLSTM. The Model 1, Model 2, and Model 3 are defined as S1, S2, and S3, respectively. If not specified, the model used in this paper is the S1 model
[
Normal View
|
Magnified View
]