Virtual image pair-based spatio-temporal fusion

Wang, Qunming; Tang, Yijie; Tong, Xiaohua; Atkinson, Peter M.

doi:10.1016/j.rse.2020.112009

Cited by 91 publications

(49 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the network depth increases, computer performance requirements are higher. Larger scale settings will cause difficulty in convergence and memory overflow, unable to complete training, and difficult to learn effective features, so it is more difficult to directly achieve 1 km -> 50 m resolution improvement [36].…”

Section: A Downscaling Results 1) Discussion Of Distrad and Srcnnmentioning

confidence: 99%

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

Yang

Luo

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

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 study, 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-SRCNN downscaling model is proposed, and the monthly average data set of LSWT with 50 m resolution is constructed. The results showed: (1) DisTrad-SRCNN can reflect the most distribution characteristics of LSWT (SSIMday = 0.96, PSNRday = 23.97; SSIMnight = 0.95, PSNRnight = 24.99). (2) LSWT had an overall upward trend (CRday = 0.22℃/10a, CRnight = 0.21℃/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. Index Terms-DisTrad; Downscaling; Lake surface water temperature; Plateau lakes; SRCNN I. INTRODUCTION akes are important ecological resources. Lake ecological environment affects not only the quality of regional ecological environment, but also the sustainable development of cities [1]-[3]. The lake ecological environment can reflect the environmental conditions of the region [4]-[6]. Lake surface water temperature (LSWT) is one of the important physical parameters that characterize the lake ecosystem [7]. In the past

show abstract

Section: A Downscaling Results 1) Discussion Of Distrad and Srcnnmentioning

confidence: 99%

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

Yang

Luo

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Thus, we can also consider the use of other effective fine spatial resolution data. For example, Sentinel-2 is a program operated with twin satellites, which can acquire fine spatial resolution (i.e., 10 m) images with high quality and with a potential revisit interval as frequent as every to five days [48]. We can analyze these fine spatial resolution data to obtain the required land cover maps and further auxiliary proportion information, which can be used for STSU of real-time MODIS data.…”

Section: F Multisource Auxiliary Datamentioning

confidence: 99%

Real-Time Spatiotemporal Spectral Unmixing of MODIS Images

Wang

Ding

Tong³

et al. 2022

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

Mixed pixels are a ubiquitous problem in remote sensing images. Spectral unmixing has been used widely for mixed pixel analysis. However, up to now, most spectral unmixing methods require endmembers and cannot consider fully intraclass spectral variation. The recently proposed spatiotemporal spectral unmixing (STSU) method copes with the aforementioned problems through exploitation of the available temporal information. However, this method requires coarse-to-fine spatial image pairs both before and after the prediction time and is, thus, not suitable for important real-time applications (i.e., where the fine spatial resolution data after the prediction time are unknown). In this article, we proposed a real-time STSU (RSTSU) method for real-time monitoring. RSTSU requires only a single coarseto-fine spatial resolution image pair before, and temporally closest to, the prediction time, coupled with the coarse image at the prediction time, to extract samples automatically to train a learning model. By fully incorporating the multiscale spatiotemporal information, the RSTSU method inherits the key advantages of STSU; it does not need endmembers and can account for intraclass spectral variation. More importantly, RSTSU is suitable for real-time analysis and, thus, facilitates the timely monitoring of land cover changes. The effectiveness of the method was validated by experiments on four Moderate Resolution Imaging Spectroradiometer (MODIS) datasets. RSTSU utilizes and enriches the theory underpinning the advanced STSU method and enhances greatly the applicability of spectral unmixing for time-series data.

show abstract

“…Due to the discrepancies of the sensor system, such as orbit pass, viewing angle, and spatial scale [32], the NDVI curves from different satellite sensors are inconsistent, mainly reflected in the inconsistency of mean and variance of Gaussian functions. Therefore, this study adopts the Gaussian function to represent two kinds of NDVI data with different spatial resolutions.…”

Section: A Basic Principlementioning

confidence: 99%

A Gaussian Kernel-Based Spatiotemporal Fusion Model for Agricultural Remote Sensing Monitoring

Shen

Zhai

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Time series normalized difference vegetation index (NDVI) is the primary data for agricultural remote sensing monitoring. Due to the tradeoff between a single sensor's spatial and temporal resolutions and the impacts of cloud coverage, the time series NDVI data cannot sever well for precision agriculture. In this study, a Gaussian kernelbased spatiotemporal fusion model (GKSFM) was developed to fuse high-resolution NDVI (Landsat) and lowresolution NDVI (MODIS) to produce a daily NDVI product at a 30 m spatial resolution. Considering that the NDVI curve of crop in each growing season can be characterized by Gaussian function, GKSFM used the Gaussian kernel to fit the nonlinear relationship between the high-resolution NDVI and the low-resolution NDVI, to obtain a more reasonable temporal increment. The experimental results show that GKSFM outperformed the comparative models in different proportions of cropland/non-cropland and different crop phenology. In addition, GKSFM was also applied for crop mapping of Mishan county by fusing the NDVI images during the crop growing season. This study demonstrates that the accuracy of the proposed method can be improved in the mid-season of crops.

show abstract

Virtual image pair-based spatio-temporal fusion

Cited by 91 publications

References 48 publications

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

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

Real-Time Spatiotemporal Spectral Unmixing of MODIS Images

A Gaussian Kernel-Based Spatiotemporal Fusion Model for Agricultural Remote Sensing Monitoring

Contact Info

Product

Resources

About