Land surface temperature (LST) is a crucial parameter driving water and heat exchange at the surface-atmosphere interface. Satellite-derived LST require rigorous validation to ensure its reliability in Earth system modeling and climate change research. To address validation accuracy degradation caused by cloud contamination artifacts and satellite-ground spatiotemporal mismatch errors, conventional mean- and median-based outlier detection methods were commonly used in the validation of satellite-derived LST products using in situ measurements. However, both methods are based solely on the degree of deviation within statistical data itself, without considering the uncertainties associated with satellite-derived and ground-based LST. This limitation could result in biased identification of outliers in satellite-derived LST validation. In this study, an uncertainty-based method was proposed to detect outliers in the validation of MODIS-derived LST using in situ measurements. This method quantifies total LST uncertainty budgets to flag anomalous data points by integrating uncertainties from both satellite retrievals and ground observations. Validation results across SURFRAD sites demonstrate the method’s efficacy when compared with those without outlier detection. Daytime implementation achieves significant root mean squared error (RMSE) reductions, notably at the BND site with a 3.1 K improvement, while nighttime applications yield marginal enhancements (< 0.4 K), reflecting diminished thermal contrast and uncertainty components during nighttime. The uncertainty-based method consistently outperforms conventional mean- and median-based methods during daytime, with RMSE improvements ranging from 0.2 K at DRA to 2.6 K at BND. Site-specific variations highlight the method’s sensitivity to surface heterogeneity and vegetation dynamics. All methods exhibit comparable performance at night (ΔRMSE < 0.15 K).

As a vital resource for the Earth’s ecological environment, effective extraction of surface water has a profound impact on human livelihoods and socio-economic development. Currently, water indices based on satellite imagery are widely used for surface water extraction. However, their accuracy remains significantly limited in complex scenarios—such as urban areas with high- and low-reflectivity buildings and shadow interference, sediment-laden or eutrophic water bodies, and intricate water–land transition zones. These limitations typically manifest in the failure to detect smaller water bodies, unclear water edges, and the presence of surrounding noise. To address these challenges, this study introduces a novel and practical water-body index—the Harmonized Landsat-Sentinel Water Index (HLSWI)—based on the Harmonized Landsat and Sentinel-2 dataset. HLSWI integrates the complementary spectral characteristics of the Landsat OLI and Sentinel-2 MSI sensors and optimizes classification thresholds via the ISO-Data clustering algorithm. HLSWI’s effectiveness is assessed through comparisons with seven commonly adopted water indices across 14 study areas worldwide and three representative complex scenarios, covering various surface types, including wetlands, arid zones, and urban aquatic environments. Experimental findings indicate that HLSWI outperforms the other seven water indices, reducing total water extraction errors by an average of 1.18% to 5.55% and improving overall accuracy and the Kappa coefficient by 1.42%–3.63% and 0.02–0.05, respectively. Therefore, HLSWI serves as a simple yet effective tool for surface water detection using optical remote sensing imagery and provides essential technical support for water extraction in complex environments.

Land surface temperature (LST) simulated by land surface model (LSM) can maintain spatial integrity and high temporal resolution. However, the relatively low spatial resolution limits the practical applications of LSM-simulated LST. Traditional downscaling methods often require lots of auxiliary data and suffer from significant loss of spatial details under large scale differences. To this end, we propose a super-resolution (SR) downscaling method based on multi-source reference using a multi-attention multi-residual network (MAMRN). The Moderate Resolution Imaging Spectroradiometer (MODIS) LST was used as the reference to improve the spatial resolution of LSM-simulated China Land Data Assimilation System (CLDAS) LST. Six regions with different land cover types covered the Chinese mainland were selected to test the MAMRN’s performance, and a traditional bilinear interpolation method and three deep learning-based SR methods were used for comparison. Comparative experiments demonstrate that MAMRN achieves improved performance, both visually and quantitatively in all six regions. Specifically, the average Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR) and Learned Perceptual Image Patch Similarity (LPIPS) are 2.06 K, 16.76, and 0.54, respectively. The quantitative evaluation scores surpass those of the comparison methods. The transfer experiments and ablation studies also indicate MAMRN’s superiority and effectiveness. Validation by in-situ LST shows that MAMRN can accurately retrieve LST under both clear-sky and cloudy-sky conditions, with the overall accuracy of clear-sky slightly superior to that of cloudy-sky. In a word, MAMRN can enhance the spatial resolution of CLDAS LST (about 6.25 km) to MODIS (1 km) scale while preserving clear spatial details. This capability is beneficial for generating spatially integrity LST with high spatiotemporal resolution, and contributes to the study of global climate change. Our code can be available at https://github.com/AHU-RS/MAMRN.

All-weather Land Surface Temperature (LST) derived from passive microwave (PMW) sensors has significant implications for characterization on the physical processes of surface energy and water balance at local through global scales. However, the PMW sensors (e.g., the AMSR-E) suffer from swath gaps, cannot provide completely spatial-gapless observations. The existing Multi-temporal Feature Connection-CNN (MTFC-CNN) method caused obvious traces of ‘gaps’ when the sample number is small or features are not rich. This paper proposes a Sample Optimized-MTFC (SO-MTFC) seamless reconstruction method based on analyzing the periodicity and complementarity of AMSR-E swath gaps. Sample optimization includes two aspects: sample enhancement and single-cycle mask strategy. Taking China’s landmass as the study area, experimental results show that the original AMSR-E LSTs and the reconstructed AMSR-E LSTs are basically connected seamlessly. Validation against with the MODIS LSTs show that the daytime (nighttime) RMSEs of the original and the reconstructed AMSR-E LSTs are 3.87 K (2.57 K) and 4.76 K (2.96 K), respectively; while the corresponding daytime (nighttime) R2are 0.88 (0.94) and 0.73 (0.90), respectively. Validation against with the six in-situ LSTs show that the RMSEs and R2of reconstructed AMSR-E LSTs against in-situ LSTs are almost consistent with those of the original AMSR-E LST. The ablation study proves the effectiveness of the sample optimization. These findings indicated the SO-MTFC achieved a good reconstruction effect. Compared with the MTFC-CNN, the SO-MTFC got higher scores in visually and quantitatively. The SO-MTFC can potentially be implemented with other satellite PMW sensors to produce completely spatial-seamless PMW LST records on a global scale.

Super-resolution mapping (SRM) is an effective way to alleviate the mixed pixel problem of remotely sensed imagery, by transforming the coarse-resolution fraction image originated from spectral unmixing into a fine-resolution land-cover map. Deep learning has been widely used in SRM since it has a powerful ability to represent the complex heterogeneous spatial distribution patterns of land-cover patches. However, the accuracy of existing deep learning-based SRM models is compromised by the fact that the fraction images used in SRM always contain errors. In this paper, we propose an end-to-end convolutional neural network (CNN)-based fraction error eliminating SRM (DeepNESRM) method to overcome the negative effect of fraction errors in SRM. In DeepNESRM, to better learn the complex nonlinear relationship between the actual coarse-resolution fraction image and the fine-resolution land-cover map by the CNN, a practical error simulation method that considers the characteristics of fraction errors is introduced to produce training samples. In addition, a multi-level feature fusion CNN is adopted to eliminate fraction errors and simultaneously implement SRM. Experiments using Sentinel-2 and Landsat 8 images were conducted to test the performance of the proposed method. Two conventional SRM methods, namely the pixel swapping method and the spatial dependence and L2 norm combined SRM (L2_SRM) method, and also a stacked very deep CNN based SRM (VDSRM) method, were used as the comparison methods. The results show that DeepNESRM can deal with fraction errors and preserve the spatial detail information, and achieve higher average overall accuracies than the other methods.

Oil spill accidents can cause severe ecological disasters; hence, the timely and effective detection of oil spills on the marine surface is of great significance. Synthetic aperture radar (SAR) is very suitable for large-scale oil spill monitoring. As a more advanced form of SAR, polarimetric SAR (PolSAR) can provide more scattering information of land objects, which can help to improve the accuracy of oil spill detection. However, the current studies of oil spill detection by SAR data have mainly focused on using SAR intensity or amplitude information, and the phase information and other polarimetric information have not been fully utilized. To solve this problem, using Sentinel-1 dual-polarimetric images as the data source, this article presents an intelligent oil spill detection architecture based on a deep convolutional neural network (DCNN), in which both the amplitude information and phase information are utilized. Furthermore, to improve the feature discrimination capability, the Cloude polarimetric decomposition parameters are also integrated into the proposed model. The results show that the improved DeepLabv3+ model, which takes ResNet-101 as the backbone network and group normalization (GN) as the normalization layer, can achieve superior performance than those traditional methods. Moreover, the model is better able to capture the fine details of oil spill instances and can achieve fine-scale segmentation.

Due to the tradeoff between spatial and temporal resolutions commonly encountered in remote sensing, no single satellite sensor can provide fine spatial resolution land surface temperature (LST) products with frequent coverage. This situation greatly limits applications that require LST data with fine spatiotemporal resolution. Here, a deep learning-based spatiotemporal temperature fusion network (STTFN) method for the generation of fine spatiotemporal resolution LST products is proposed. In STTFN, a multiscale fusion convolutional neural network is employed to build the complex nonlinear relationship between input and output LSTs. Thus, unlike other LST spatiotemporal fusion approaches, STTFN is able to form the potentially complicated relationships through the use of training data without manually designed mathematical rules making it is more flexible and intelligent than other methods. In addition, two target fine spatial resolution LST images are predicted and then integrated by a spatiotemporal-consistency (STC)-weighting function to take advantage of STC of LST data. A set of analyses using two real LST data sets obtained from Landsat and moderate resolution imaging spectroradiometer (MODIS) were undertaken to evaluate the ability of STTFN to generate fine spatiotemporal resolution LST products. The results show that, compared with three classic fusion methods [the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM), the spatiotemporal integrated temperature fusion model (STITFM), and the two-stream convolutional neural network for spatiotemporal image fusion (StfNet)], the proposed network produced the most accurate outputs [average root mean square error (RMSE)0.971].

Traditionally, clean reference images are needed to train the networks when applying the deep learning techniques to tackle image denoising tasks. However, this idea is impracticable for the task of synthetic aperture radar (SAR) image despeckling, since no real-world speckle-free SAR data exist. To address this issue, this article presents a noisy reference-based SAR deep learning filter, by using complementary images of the same area at different times as the training references. In the proposed method, to better exploit the information of the images, parameter-sharing convolutional neural networks are employed. Furthermore, to mitigate the training errors caused by the land-cover changes between different times, the similarity of each pixel pair between the different images is utilized to optimize the training process. The outstanding despeckling performance of the proposed method was confirmed by the experiments conducted on several multitemporal data sets, when compared with some of the state-of-the-art SAR despeckling techniques. In addition, the proposed method shows a pleasing generalization ability on single-temporal data sets, even though the networks are trained using finite input-reference image pairs at a different imaging area.

Despeckling is a fundamental preprocessing step for applications using polarimetric synthetic aperture radar data in most cases. In this paper, a guided filter with nonlinear weight kernels and adaptive filtering windows is presented for PolSAR image despeckling, in which the guidance image is constructed by a weighted average using the statistical traits of the speckled image. The output result is then estimated by another weighted average, with the aid of the fully polarimetric information from both the guidance image and the speckled image. In the experimental part, the filtering results obtained with both simulated and real PolSAR images reveal the positive performance of the proposed method in both reducing speckle and retaining details, when compared with some of the state-of-the-art algorithms. Furthermore, the relatively low computational complexity is another strength of the proposed method.

The tradeoff in remote sensing instruments that balances the spatial resolution and temporal frequency limits our capacity to monitor spatial and temporal dynamics effectively. The spatiotemporal data fusion technique is considered as a cost-effective way to obtain remote sensing data with both high spatial resolution and high temporal frequency, by blending observations from multiple sensors with different advantages or characteristics. In this paper, we develop the spatial and temporal nonlocal filter-based fusion model (STNLFFM) to enhance the prediction capacity and accuracy, especially for complex changed landscapes. The STNLFFM method provides a new transformation relationship between the fine-resolution reflectance images acquired from the same sensor at different dates with the help of coarse-resolution reflectance data, and makes full use of the high degree of spatiotemporal redundancy in the remote sensing image sequence to produce the final prediction. The proposed method was tested over both the Coleambally Irrigation Area study site and the Lower Gwydir Catchment study site. The results show that the proposed method can provide a more accurate and robust prediction, especially for heterogeneous landscapes and temporally dynamic areas.

Lake are sensitive to both climate change and human activities, and therefore serves as an excellent indicator of environmental changes. Based on series Landsat images, this paper provides a first picture of the annual variations in area of nine plateau lakes in Yunnan province, China using the Modified Normalized Difference Water Index (MNDWI) and Object-based image analysis (OBIA) method. A spatiotemporal analysis had carried out for these lakes. The results showed that water area annual variations of nine plateau lakes are inferenced by both climate change and human activities in different degrees. For Qilu and Yilong Lakes, the human activities paly more important role.

The Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature (LST) product can offer accurate LST with high temporal and spatial resolution, but the quality is often degraded by cloud. To improve the usability of the MODIS LST, this letter proposes a reconstruction method based on multitemporal data. First, a multitemporal classification is employed to distinguish the different land surface types. The invalid LST values can then be predicted using a robust regression with the multitemporal information from the other LSTs. Finally, postprocessing is proposed to eliminate outliers. Simulated and actual experiments show that the method can accurately reconstruct the missing values.