Deep learning-based super-resolution (SR) methods have been widely used in natural images; however, their applications in satellite-derived sea surface temperature (SST) have not yet been fully discussed. Hence, it is necessary to analyze the validity of deep learning-based SR methods in SST reconstruction. In this study, an SR model, including multiscale feature extraction and multireceptive field mapping, was first proposed. Then, the proposed model and four other existing SR models were applied to SST reconstruction and analyzed. First, compared with the bicubic interpolation method, the SR models can improve the reconstruction accuracy. Compared with four other SR models, the proposed model can achieve the lowest mean squared error (MAE) in the East China Sea (ECS), in the northwest Pacific (NWP) and in the west Atlantic (WA), the second-lowest MAE in the southeast Pacific (SEP); the lowest root mean squared error (RMSE) in ECS and WA, the second-lowest RMSE in NWP and SEP. Additionally, ODRE model can acquire the highest or the second-highest peak single-to-noise ratio (PSNR) and structural similarity index (SSIM) in ECS, NWP and SEP. Moreover, the number of missing pixels and SST variety are two essential factors in the SR performance. The proposed multiscale feature extraction process can enhance the SR performance, especially for small regions and stable SST regions. Finally, while a deeper network can be helpful in achieving SR performance, the approach of simply adding more dilation convolutions may not enhance the reconstruction accuracy.

The Sichuan-Tibet grid connection project is a national key project implemented in accordance with the developmental needs of Tibet and the living requirements of 700 thousand local residents. It is the first grid project with special high voltage that passes through eastern margin of the Tibetan Plateau. The ground deformation due to widely distributed landslides and debris flow in this area is the major concern to the safety of the project. The multi-temporal interferometry technique is applied to retrieve the surface deformation information using high resolution X-band SAR imagery. The time series of surface deformation is obtained through the sequential high spatial and temporal resolution TerraSAR images (20 scenes of X-band TerraSAR SLC images acquired from 5 January 2014 to 12 December 2014). The results have been correlated with the permafrost activities and intensive precipitation. They show that the study area is prone to slow to moderate ground motion with the range of −30 to +30 mm/year. Seasonal movement is observed due to the freeze-thaw cycle effect and intensive precipitation weather condition. Typical region analysis suggests that the deformation rate tends to increase dramatically during the late spring and late autumn while slightly during the winter time. The correlations of surface deformations with these two main trigger factors were further discussed. The deformation curves of persistent scatterers in the study area showing the distinct seasonal characteristics coincide well with the effect of freeze-thaw cycle and intensive precipitation. The movement occurring at late spring is dominated by the freeze-thaw cycle which is a common phenomenon in such a high-elevated area as the Tibetan Plateau. Intensive precipitation plays more important role in triggering landsides in the summer season. The combining effect of both factors results in fast slope movement in May. The results also suggest that the movement often occur at the middle to toe part of the slope where the combining effect of freeze-thaw cycle and precipitation plays an important role. Therefore the majority of transmission towers are not threatened significantly by geological hazards since they are located on the higher elevation which is beyond the boundary of slope movement. The comparison between field observations and the persistent scatterers interferometry (PSI) results reveals good agreement in obvious deformation accumulations. High uncertainty still exists due to issue of SAR imagery quality and the persistent scatterers interferometry technique. Nevertheless, this study provides an insight into understanding the characteristics of ground movement trend in the complicated eastern Tibet area.

Landsat and MODIS data have been widely utilized in many remote sensing applications, however, the trade-off between the spatial resolution and temporal frequency has limited their capacities in monitoring detailed spatio-temporal dynamics. Spatio-temporal fusion methods based on a linear model that considers the differences between fine- and coarse-spatial-resolution images as linear can effectively solve this trade-off problem, yet the existing linear fusion methods either regard the coefficients of the linear model as constants or have adopted regression methods to calculate the coefficients, both of which may introduce some errors in the fusion process. In this paper, we proposed an enhanced linear spatio-temporal fusion method (ELSTFM) to improve the data fusion accuracy. In the ELSTFM, it is not necessary to calculate the slope of the linear model, and the intercept, which can be deemed as the residual caused by systematic biases, is calculated based on spectral unmixing theory. Additionally, spectrally similar pixels in a given fine-spatial-resolution pixel’s neighborhood and their corresponding weights were used in the proposed method to mitigate block effects. Landsat-7/ETM+ and 8-day composite MODIS reflectance data covering two study sites with heterogeneous and homogenous landscapes were selected to validate the proposed method. Compared to three other typical spatio-temporal fusion methods visually and quantitatively, the predicted images obtained from ELSTFM could acquire better results for the two selected study sites. Furthermore, the resampling methods used to resample MODIS to the same spatial resolution of Landsat could slightly, but did not significantly influence the fusion accuracy, and the distributions of slopes of different bands for the two study sites could all be deemed as normal distributions with a mean value close to 1. The performance of ELSTFM depends on the accuracy of residual calculation at fine-resolution and large landscape changes may influence the fusion accuracy.

The “4.20” Lushan earthquake in Sichuan province, China has induced a large amount of geological hazards and produced abundant loose materials which are prone to post-earthquake rainfall-triggered landslides. A detailed landslide inventory was acquired through post-earthquake emergent field investigation and high resolution remote sensing interpretation. The rainfall analysis was conducted using historical rainfall records during the period from 1951 to 2010. Results indicate that the average annual rainfall distribution is heterogeneous and the largest average annual rainfall occurs in Yucheng district. The Stability Index MAPping (SINMAP) model was adopted to assess and analyze the post-earthquake slope stability under different rainfall scenarios (light rainfall, moderate rainfall, heavy rainfall, and rainstorm). The model parameters were calibrated to reflect the significant influence of strong earthquakes on geological settings. The slope stability maps triggered by different rainfall scenarios were produced at a regional scale. The effect of different rainfall conditions on the slope stability is discussed. The expanding trend of the unstable area was quantitatively assessed with the different critical rainfall intensity. They provide a new insight into the spatial distribution and characteristics of post-earthquake rainfall-triggered landslides in the Lushan seismic area. An increase of rainfall intensity results in a significant increase of unstable area. The heterogeneous distribution of slope instability is strongly correlated with the distribution of earthquake intensity in spite of different rainfall conditions. The results suggest that the both seismic intensity and rainfall are two crucial factors for post-earthquake slope stability. This study provides important references for landslide prevention and mitigation in the Lushan area after earthquake.

Oceanic dissolved oxygen (DO) is crucial for oceanic material cycles and marine biological activities. However, obtaining subsurface DO values directly from satellite observations is limited due to the restricted observed depth. Therefore, it is essential to develop a connection between surface oceanic parameters and subsurface DO values. Machine learning (ML) methods can effectively grasp the complex relationship between input attributes and target variables, making them a valuable approach for estimating subsurface DO values based on surface oceanic parameters. In this study, the potential of ML methods for subsurface DO retrieval is analyzed. Among the selected ML methods, namely support vector regression (SVR), random forest (RF) regression, and extreme gradient boosting (XGBoosting) regression, the RF method generally demonstrates superior performance. As the depth increases, the accuracy of DO estimates tends to initially decrease, then gradually improve, with the poorest performance occurring at the depth of 600 dbar. The range of determination coefficients (R²) and root mean square error (RMSE) values based on the test dataset at different depths lies between 0.53 and 47.59 μmol/kg to 0.99 and 4.01 μmol/kg. In addition, compared to sea surface salinity (SSS) and sea surface chlorophyll-a (SCHL), sea surface temperature (SST) plays a more significant role in DO retrieval. Finally, compared to the pelagic interactions scheme for carbon and ecosystem studies (PISCES) model, the RF method achieves higher retrieval accuracies at depths above 700 dbar. In the deep ocean, the primary differences in DO values obtained from the RF method and the PISCES model-based method are noticeable in the vicinity of the equatorial region.

Meso- and fine-scale sea surface temperature (SST) is an essential parameter in oceanographic research. Remote sensing is an efficient way to acquire global SST. However, single infrared-based and microwave-based satellite-derived SST cannot obtain complete coverage and high-resolution SST simultaneously. Deep learning super-resolution (SR) techniques have exhibited the ability to enhance spatial resolution, offering the potential to reconstruct the details of SST fields. Current SR research focuses mainly on improving the structure of the SR model instead of training dataset selection. Different from generating the low-resolution images by downscaling the corresponding high-resolution images, the high- and low-resolution SST are derived from different sensors. Hence, the structure similarity of training patches may affect the SR model training and, consequently, the SST reconstruction. In this study, we first discuss the influence of training dataset selection on SST SR performance, showing that the training dataset determined by the structure similarity index (SSIM) of 0.6 can result in higher reconstruction accuracy and better image quality. In addition, in the practical stage, the spatial similarity between the low-resolution input and the objective high-resolution output is a key factor for SST SR. Moreover, the training dataset obtained from the actual AMSR2 and MODIS SST images is more suitable for SST SR because of the skin and sub-skin temperature difference. Finally, the SST reconstruction accuracies obtained from different SR models are relatively consistent, yet the differences in reconstructed image quality are rather significant.