Filling Gaps of Monthly Terra/MODIS Daytime Land Surface Temperature Using Discrete Cosine Transform Method

Deep Interpolation of Remote Sensing Land Surface Temperature Data with Partial Convolutions

Land Surface Temperature (LST) is an important resource for a variety of tasks. The data are mostly free of charge and combine high spatial and temporal resolution with reliable data collection over a historical timeframe. When remote sensing is used to provide LST data, such as the MODA11 product using information from the MODIS sensors attached to NASA satellites, data acquisition can be hindered by clouds or cloud shadows, occluding the sensors' view on different areas of the world. This makes it difficult to take full advantage of the high resolution of the data. A common solution to interpolating LST data is statistical interpolation methods, such as fitting polynomials or thin plate spine interpolation. These methods have difficulties in incorporating additional knowledge about the research area and learning local dependencies that can help with the interpolation process. We propose a novel approach to interpolating remote sensing LST data in a fixed research area considering local ground-site air temperature measurements. The two-step approach consists of learning the LST from air temperature measurements, where the ground-site weather stations are located, and interpolating the remaining missing values with partial convolutions within a U-Net deep learning architecture. Our approach improves the interpolation of LST for our research area by 44% in terms of RMSE, when compared to state-of-the-art statistical methods. Due to the use of air temperature, we can provide coverage of 100%, even when no valid LST measurements were available. The resulting gapless coverage of high resolution LST data will help unlock the full potential of remote sensing LST data.

Gap-Free LST Generation for MODIS/Terra LST Product Using a Random Forest-Based Reconstruction Method

Land surface temperature (LST) is a crucial input parameter in the study of land surface water and energy budgets at local and global scales. Because of cloud obstruction, there are many gaps in thermal infrared remote sensing LST products. To fill these gaps, an improved LST reconstruction method for cloud-covered pixels was proposed by building a linking model for the moderate resolution imaging spectroradiometer (MODIS) LST with other surface variables with a random forest regression method. The accumulated solar radiation from sunrise to satellite overpass collected from the surface solar irradiance product of the Feng Yun-4A geostationary satellite was used to represent the impact of cloud cover on LST. With the proposed method, time-series gap-free LST products were generated for Chongqing City as an example. The visual assessment indicated that the reconstructed gap-free LST images can sufficiently capture the LST spatial pattern associated with surface topography and land cover conditions. Additionally, the validation with in situ observations revealed that the reconstructed cloud-covered LSTs have similar performance as the LSTs on clear-sky days, with the correlation coefficients of 0.92 and 0.89, respectively. The unbiased root mean squared error was 2.63 K. In general, the validation work confirmed the good performance of this approach and its good potential for regional application.

Variance of vegetation coverage and its sensitivity to climatic factors in the Irtysh River basin

Background

Climate change is an important factor driving vegetation changes in arid areas. Identifying the sensitivity of vegetation to climate variability is crucial for developing sustainable ecosystem management strategies. The Irtysh River is located in the westerly partition of China, and its vegetation cover is more sensitive to climate change. However, previous studies rarely studied the changes in the vegetation coverage of the Irtysh River and its sensitivity to climate factors from a spatiotemporal perspective.

Methods

We adopted a vegetation sensitivity index based on remote sensing datasets of high temporal resolution to study the sensitivity of vegetation to climatic factors in the Irtysh River basin, then reveal the driving mechanism of vegetation cover change.

Results

The results show that 88.09% of vegetated pixels show an increasing trend in vegetation coverage, and the sensitivity of vegetation to climate change presents spatial heterogeneity. Sensitivity of vegetation increases with the increase of coverage. Temperate steppe in the northern mountain and herbaceous swamp and broadleaf forest in the river valley, where the normalized difference vegetation index is the highest, show the strongest sensitivity, while the desert steppe in the northern plain, where the NDVI is the lowest, shows the strongest memory effect (or the strongest resilience). Relatively, the northern part of this area is more affected by a combination of precipitation and temperature, while the southern plains dominated by desert steppe are more sensitive to precipitation. The central river valley dominated by herbaceous swamp is more sensitive to temperature-vegetation dryness index. This study underscores that the sensitivity of vegetation cover to climate change is spatially differentiated at the regional scale.