A Data Fusion Modeling Framework for Retrieval of Land Surface Temperature from Landsat-8 and MODIS Data

Abstract

Land surface temperature (LST) is a critical state variable of land surface energy equilibrium and a key indicator of environmental change such as climate change, urban heat island, and freezing-thawing hazard. The high spatial and temporal resolution datasets are urgently needed for a variety of environmental change studies, especially in remote areas with few LST observation stations. MODIS and Landsat satellites have complementary characteristics in terms of spatial and temporal resolution for LST retrieval. To make full use of their respective advantages, this paper developed a pixel-based multi-spatial resolution adaptive fusion modeling framework (called pMSRAFM). As an instance of this framework, the data fusion model for joint retrieval of LST from Landsat-8 and MODIS data was implemented to generate the synthetic LST with Landsat-like spatial resolution and MODIS temporal information. The performance of pMSRAFM was tested and validated in the Heihe River Basin located in China. The results of six experiments showed that the fused LST was high similarity to the direct Landsat-derived LST with structural similarity index (SSIM) of 0.83 and the index of agreement (d) of 0.84. The range of SSIM was 0.65–0.88, the root mean square error (RMSE) yielded a range of 1.6–3.4 °C, and the averaged bias was 0.6 °C. Furthermore, the temporal information of MODIS LST was retained and optimized in the synthetic LST. The RMSE ranged from 0.7 °C to 1.5 °C with an average value of 1.1 °C. When compared with in situ LST observations, the mean absolute error and bias were reduced after fusion with the mean absolute bias of 1.3 °C. The validation results that fused LST possesses the spatial pattern of Landsat-derived LSTs and inherits most of the temporal properties of MODIS LSTs at the same time, so it can provide more accurate and credible information. Consequently, pMSRAFM can be served as a promising and practical fusion framework to prepare a high-quality LST spatiotemporal dataset for various applications in environment studies.

Estimation of Evapotranspiration from the People’s Victory Irrigation District Based on the Data Mining Sharpener Model

“…To verify the sharpened accuracy of the DMS model, the pixel values at the same latitude and longitude as the four-component radiometer erected on the flux tower were selected for comparison. Table 2 shows that the R 2 was 0.961, which was between the LST at 100 m spatial resolution and the measured surface temperature by the CNR4, the RMSE was 0.968 • C, and the MAE was 2.236 • C. The R 2 was 0.975, which was between the LST at 30 m spatial resolution and the measured surface temperature by the CNR4, the RMSE was 0.811 • C, and the MAE was 1.948 • C. The difference in surface temperature before and after sharpening was maintained between 1~2 • C. The correlation coefficients of the two thermal infrared images with different spatial resolutions were consistently above 0.9 [28]. Compared to the 100 m spatial resolution, the LST at 30 m spatial resolution showed improved accuracy.…”

Cross-Domain Transfer Learning for Natural Scene Classification of Remote-Sensing Imagery

“…Since then, AlexNet has been widely employed in a variety of applications, including natural scene categorization in remote-sensing data. Zhao G et al [23], for example, provided a multi-sensor data-fusion framework for natural scene categorization in which AlexNet was utilized as the classification model to combine information derived from various sensors.…”

Analysis of Long Time Series of Summer Surface Urban Heat Island under the Missing-Filled Satellite Data Scenario

“…The spatiotemporal fusion technique for LST data offers the opportunity to further understand the SUHI phenomenon [17,18]. In the present review, the spatial and temporal adaptive reflectance fusion model (STARFM) [14], the enhanced STARFM (ESTARFM) method [19], the bilateral filter [9], the spatiotemporal adaptive data fusion algorithm (SADFAT) [20], and the spatiotemporal integrated temperature fusion model (STITFM) [21] in the weight function-based category; the pixel-based multi-spatial resolution adaptive fusion modeling framework (pMSRAFM) [22] in the unmixing-based category; the sparse-representation-based spatiotemporal reflectance fusion model (SPS-FTM) [23] in the learning-based category; and the flexible spatiotemporal data fusion (FSDAF) method [24] in the hybrid category. Although great progress has been made, most of these spatiotemporal fusion methods are unable to accurately capture the spatial details of LSTs, predict abrupt events, and preserve the spatial continuity of LSTs within urban areas simultaneously [25].…”