Search

The objective of the pansharpening task is to integrate multispectral (MS) images with low spatial resolution (LR) and to integrate panchromatic (PAN) images with high spatial resolution (HR) to generate HRMS images. Recently, deep learning-based pansharpening methods have been widely studied. However, traditional deep learning methods lack transparency while deep unrolling methods have limited performance when using one implicit prior for HRMS images. To address this issue, we incorporate one implicit prior with a semi-implicit prior and propose a double prior deep unrolling network (DPDU-Net) for pansharpening. Specifically, we first formulate the objective function based on observation models of PAN and LRMS images and two priors of an HRMS image. In addition to the implicit prior in the image domain, we enforce the sparsity of the HRMS image in a certain multi-scale implicit space; thereby, the feature map can obtain better sparse representation ability. We optimize the proposed objective function via alternating iteration. Then, the iterative process is unrolled into an elaborate network, with each iteration corresponding to a stage of the network. We conduct both reduced-resolution and full-resolution experiments on two satellite datasets. Both visual comparisons and metric-based evaluations consistently demonstrate the superiority of the proposed DPDU-Net. [ABSTRACT FROM AUTHOR]

The High Resolution Picture Transmission (HRPT) data of the National Oceanic and Atmospheric Administration (NOAA) series meteorological satellites had been received by the SeaSpace ground station located at the Ocean University of China (OUC). Based on the atmospheric radiative transfer model, we obtained the NOAA-15/16/17/18/19 Advanced Very High Resolution Radiometer (AVHRR) sea surface skin temperature (SSTskin) data using the Bayesian cloud detection method and the optimal estimation (OE) sea surface temperature (SST) retrieval algorithm. Compared with the NOAA/AVHRR multi-channel SST data, the AVHRR SSTskin data have higher data accuracy. We also compared the AVHRR SSTskin with the buoy SST with spatial and temporal windows of 0.01° and 30 min. The daytime biases ranged from −0.32 °C (NOAA-16) to 0.08 °C (NOAA-17) with standard deviations (SDs) ranging from 0.36 °C (NOAA-18/ NOAA-19) to 0.60 °C (NOAA-16), and the nighttime biases ranged from −0.26 °C (NOAA-16) to −0.02 °C (NOAA-17) with SDs ranging from 0.33 °C (NOAA-19) to 0.60 °C (NOAA-16). The accuracy of all five satellite data during daytime and nighttime was significantly improved. These results show that the AVHRR SSTskin of NOAA series satellites is good and consistent in different periods, and the SSTskin data products with high spatial resolution and accuracy can be used for mesoscale and submesoscale marine applications. [ABSTRACT FROM AUTHOR]

Accurate diameter at breast height (DBH) and tree height (H) information can be acquired through terrestrial laser scanning (TLS) and airborne LiDAR scanner (ALS) point cloud, respectively. To utilize these two features simultaneously but avoid the difficulties of point cloud fusion, such as technical complexity and time-consuming and laborious efforts, a feature-level point cloud fusion method (FFATTe) is proposed in this paper. Firstly, the TLS and ALS point cloud data in a plot are georeferenced by differential global navigation and positioning system (DGNSS) technology. Secondly, point cloud processing and feature extraction are performed for the georeferenced TLS and ALS to form feature datasets, respectively. Thirdly, the feature-level fusion of LiDAR data from different data sources is realized through spatial join according to the tree trunk location obtained from TLS and ALS, that is, the tally can be implemented at a plot. Finally, the individual tree parameters are optimized based on the tally results and fed into the binary volume model to estimate the total volume (TVS) in a large area (whole study area). The results show that the georeferenced ALS and TLS point cloud data using DGNSS RTK/PPK technology can achieve coarse registration (mean distance ≈ 40 cm), which meets the accuracy requirements for feature-level point cloud fusion. By feature-level fusion of the two point cloud data, the tally can be achieved quickly and accurately in the plot. The proposed FFATTe method achieves high accuracy (with error of 3.09%) due to its advantages of combining different LiDAR data from different sources in a simple way, and it has strong operability when acquiring TVS over large areas. [ABSTRACT FROM AUTHOR]

Adding an attention module to the deep convolution semantic segmentation network has significantly enhanced the network performance. However, the existing channel attention module focusing on the channel dimension neglects the spatial relationship, causing location noise to transmit to the decoder. In addition, the spatial attention module exemplified by self-attention has a high training cost and challenges in execution efficiency, making it unsuitable to handle large-scale remote sensing data. We propose an efficient vector pooling attention (VPA) module for building the channel and spatial location relationship. The module can locate spatial information better by performing a unique vector average pooling in the vertical and horizontal dimensions of the feature maps. Furthermore, it can also learn the weights directly by using the adaptive local cross-channel interaction. Multiple weight learning ablation studies and comparison experiments with the classical attention modules were conducted by connecting the VPA module to a modified DeepLabV3 network using ResNet50 as the encoder. The results show that the mIoU of our network with the addition of an adaptive local cross-channel interaction VPA module increases by 3% compared to the standard network on the MO-CSSSD. The VPA-based semantic segmentation network can significantly improve precision efficiency compared with other conventional attention networks. Furthermore, the results on the WHU Building dataset present an improvement in IoU and F1-score by 1.69% and 0.97%, respectively. Our network raises the mIoU by 1.24% on the ISPRS Vaihingen dataset. The VPA module can also significantly improve the network's performance on small target segmentation. [ABSTRACT FROM AUTHOR]

Cloud properties are essential for the Clouds and the Earth's Radiant Energy System (CERES) Project, enabling accurate interpretation of measured broadband radiances, providing a means to understand global cloud-radiation interactions, and constituting an important climate record. Producing consistent cloud retrievals across multiple platforms is critical for generating a multidecadal cloud and radiation record. Techniques used by CERES for retrievals from measurements by the MODerate-Resolution Imaging Spectroradiometer (MODIS) on Terra and Aqua platforms are adapted for the application to radiances from the Visible Infrared Imaging Radiometer Suite (VIIRS) on the Suomi National Polar-orbiting Partnership to continue the CERES record beyond the MODIS era. The algorithm adjustments account for spectral and channel differences, use revised reflectance models, and set new thresholds for detecting thin cirrus clouds at night. Cloud amounts from VIIRS are less than their MODIS counterparts by 0.016 during the day and 0.026 at night, but trend consistently over the 2012–2020 period. The VIIRS mean liquid water cloud fraction differs by ~0.01 from the MODIS amount. The average cloud heights from VIIRS differ from the MODIS heights by less than 0.2 km, except the VIIRS daytime ice cloud heights, which are 0.4 km higher. The mean VIIRS nonpolar optical depths are 17% (1%) larger (smaller) than those from MODIS for liquid (ice) clouds. The VIIRS cloud hydrometeor sizes are generally smaller than their MODIS counterparts. Discrepancies between the MODIS and VIIRS properties stem from spectral and spatial resolution differences, new tests at night, calibration inconsistencies, and new reflectance models. Many of those differences will be addressed in future editions. [ABSTRACT FROM AUTHOR]

Despite the profound roles of surface deformation monitoring techniques in observing permafrost surface stability, predetermining the approximate location and time of possibly occurring severe permafrost degradation before applying these techniques is extremely necessary, but has received little attention. Taking the oil tank collapse accident in the Norilsk region as a case, we explored this concern by analyzing the permafrost deformation mechanisms and determining early surface deformation signals. Regarding this case, we firstly applied the Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) technique to obtain its permafrost surface deformation rate, then utilized a sine model to decompose its interannual deformation and seasonal deformation, and finally compared the relationship between the topographic slope and deformation rate. Based on experimental results, we reveal that when the annual average temperature continuously increases at a rate of 2 ° C/year for 2∼3 consecutive years, permafrost areas with relatively large topographic slopes (>15 ° ) are more prone to severe surface deformation during the summer thaw period. Therefore, this paper suggests that permafrost areas with large topographic slopes (>15 ° ) should be taken as the key surveillance areas, and that the appropriate monitoring time for employing surface deformation monitoring techniques should be the summer thawing period after a continuous increase in annual average temperature at a rate of 2 ° C/year for 2∼3 years. [ABSTRACT FROM AUTHOR]

Global Positioning System (GPS) has been confirmed to be a feasible tool to measure displacement of civil engineering structures. In this paper, we report on an analysis of annual deformations of a pumped-storage power station dam using historical GPS observations. Data spanning more than nine years are resolved using the GAMIT (GPS at MIT) software, and a GPS time-series method is employed to extract linear trends and annual cycle signals. It is evident that the monument located on the main dam has a linear trend, with rates of 1.0 mm/yr and 1.8 mm/yr in east and up directions, respectively. Annual cycles with amplitudes larger than 0.5 mm are shown in coordinate components at all monitoring stations. However, the annual amplitude can be 30–84% lower when a monitoring station whose monument materials and height are similar to other monitoring stations is chosen as the reference station. This suggests that differential thermal expansion of monuments could be 30% to 80% and even higher in baseline time series. A spurious offset style annual signal with 5 mm amplitude that is highly correlated with annual temperature variance is observed in the east–west direction of the monitoring station located at the east side of the reservoir. This suggests that upper ground layer movement correlated with temperature could be responsible for these annual cycles. Meanwhile, no periodic correlations are observed between the water level data and the baseline time series. [ABSTRACT FROM AUTHOR]

Cultivated land resources are crucial to food security and economic development. Exploring the spatiotemporal pattern of cultivated land non-agriculturalization and its drivers is a prerequisite for cultivated land conservation. This paper used GlobeLand30 data to reveal the spatial and temporal pattern, the shift of the gravity center and the drivers of cultivated land non-agriculturalization by employing spatial analysis, gravity center model and the geographical detector model. The results show a dramatic increase in the non-agriculturalization of cultivated land in the period of 2010–2020 compared to 2000–2010. Spatially, the cultivated land non-agriculturalization mainly occurred in areas with high urbanization levels, such as eastern Sichuan Province and western Chongqing Municipality, while the cultivated land non-agriculturalization in other areas was small-scale and spatially scattered. Furthermore, the speed of cultivated land non-agriculturalization showed spatial unevenness, and the gravity center of cultivated land non-agriculturalization shifted towards the northeast at a distance of 123.21 km. The cultivated land non-agriculturalization was affected by GDP per capita, population density, GDP per unit of land and total retail sales of social consumer goods. The key drivers for the cultivated land non-agriculturalization in the study area were the continuous expansion of urban space and the large-scale cultivation of economic fruit trees. The government should promote small-scale machinery suitable for agricultural cultivation in the mountainous and hilly areas of Southwest China, and appropriately develop economic fruit groves and livestock farming to reduce the phenomenon of cultivated land non-foodization. [ABSTRACT FROM AUTHOR]

Wide-scale automatic monitoring based on the Normalized Difference Water Index (NDWI) and Mask Region-based Convolutional Neural Network (Mask R-CNN) with remote sensing images is of great significance for the management of aquaculture areas. However, different spatial resolutions brought different cost and model performance. To find more suitable image spatial resolutions for automatic monitoring offshore aquaculture areas, seven different resolution remote sensing images in the Sandu'ao area of China, from 2 m, 4 m, to 50 m, were compared. Results showed that the remote sensing images with a resolution of 15 m and above can achieve the corresponding recognition effect when no financial issues were considered, with the F1 score of over 0.75. By establishing a cost-effectiveness evaluation formula that comprehensively considers image price and recognition effect, the best image resolution in different scenes can be found, thus providing the most appropriate data scheme for the automatic monitoring of offshore aquaculture areas. [ABSTRACT FROM AUTHOR]

Sea surface temperature (SST) has important practical value in ocean related fields. Numerical prediction is a common method for forecasting SST at present. However, the forecast results produced by the numerical forecast models often deviate from the actual observation data, so it is necessary to correct the bias of the numerical forecast products. In this paper, an SST correction approach based on the Convolutional Long Short-Term Memory (ConvLSTM) network with multiple attention mechanisms is proposed, which considers the spatio-temporal relations in SST data. The proposed model is appropriate for correcting SST numerical forecast products by using satellite remote sensing data. The approach is tested in the region of the South China Sea and reduces the root mean squared error (RMSE) to 0.35 °C. Experimental results reveal that the proposed approach is significantly better than existing models, including traditional statistical methods, machine learning based methods, and deep learning methods. [ABSTRACT FROM AUTHOR]

Severe meteorological drought is generally considered to lead to crop damage and loss. In this study, we created a new standard value by averaging the values distributed in the middle 30–70% instead of the traditional mean value, and we proposed a new index calculation method named Normalized Indices (NI) for meteorological drought monitoring after normalized processing. The TRMM-derived precipitation data, GLDAS-derived soil moisture data, and MODIS-derived vegetation condition data from 2003 to 2019 were used, and we compared the NI with commonly used Condition Indices (CI) and Anomalies Percentage (AP). Taking the mid-to-lower reaches of the Yangtze River (MLRYR) as an example, the drought monitoring results for paddy rice and winter wheat showed that (1) NI can monitor well the relative changes in real precipitation/soil moisture/vegetation conditions in both arid and humid regions, while meteorological drought was overestimated with CI and AP, and (2) due to the monitoring results of NI, the well-known drought event that occurred in the MLRYR from August to October 2019 had a much less severe impact on vegetation than expected. In contrast, precipitation deficiency induced an increase in sunshine and adequate heat resources, which improved crop growth in 78.8% of the area. This study discusses some restrictions of CI and AP and suggests that the new NI index calculation provides better meteorological drought monitoring in the MLRYR, thus offering a new approach for future drought monitoring studies. [ABSTRACT FROM AUTHOR]

Late frost damage is one of the main meteorological disasters that affect the growth of wine grapes in spring, causing a decline in wine grapes quality and a reduction in yield in Northwest China. At present, remote sensing technology has been widely used in the field of crop meteorological disasters monitoring and loss assessments, but little research has been carried out on late frost damage in wine grapes. To monitor the impact of late frost in wine grapes accurately and quickly, in this research, we selected the Ningxia planting area as the study area. A practical framework of late frost damage on wine grapes by integrating visible, near-infrared, and thermal infrared satellite data is proposed. This framework includes: (1) Wine grape planting area extraction using Gaofen-1 (GF-1), Landsat-8, and Sentinel-2 based on optimal feature selection and Random Forest (RF) algorithm; (2) retrieval of the land surface temperature (LST) using Landsat-8 thermal infrared data; (3) data fusion using Landsat-8 LST and MODIS LST for a high spatiotemporal resolution of LST with the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM); (4) the estimation of daily minimum air temperature (Tmin) using downscaled LST and meteorological station data; (5) monitoring and evaluation of the degree of late frost damage in wine grapes in April 2020 by combining satellite-derived data and late frost indicators. The results show that the total area of wine grapes extracted in Ningxia was about 39,837 ha. The overall accuracy was 90.47%, the producer's accuracy was 91.09%, and the user's accuracy was 90.22%. The root mean square (RMSE) and the coefficient of determination (R2) of the Tmin estimation model were 1.67 ℃ and 0.91, respectively. About 41.12% of the vineyards suffered severe late frost damage, and the total affected area was about 16,381 ha during April 20–25, 2020. This suggests the satellite data can accurately monitor late frost damage in wine grapes by mapping the wine grape area and estimating Tmin. The results can help farmers to take remedial measures to reduce late frost damage in wine grapes, and provide an objective evaluation of late frost damage insurance claims for wine grapes. With the increasing weather extremes, this study has an important reference value for standardized global wine grape management and food security planning. [ABSTRACT FROM AUTHOR]

As a key canopy structure parameter, the estimation method of the Leaf Area Index (LAI) has always attracted attention. To explore a potential method to estimate forest LAI from 3D point cloud at low cost, we took photos from different angles of the drone and set five schemes (O (0°), T15 (15°), T30 (30°), OT15 (0° and 15°) and OT30 (0° and 30°)), which were used to reconstruct 3D point cloud of forest canopy based on photogrammetry. Subsequently, the LAI values and the leaf area distribution in the vertical direction derived from five schemes were calculated based on the voxelized model. Our results show that the serious lack of leaf area in the middle and lower layers determines that the LAI estimate of O is inaccurate. For oblique photogrammetry, schemes with 30° photos always provided better LAI estimates than schemes with 15° photos (T30 better than T15, OT30 better than OT15), mainly reflected in the lower part of the canopy, which is particularly obvious in low-LAI areas. The overall structure of the single-tilt angle scheme (T15, T30) was relatively complete, but the rough point cloud details could not reflect the actual situation of LAI well. Multi-angle schemes (OT15, OT30) provided excellent leaf area estimation (OT15: R2 = 0.8225, RMSE = 0.3334 m2/m2; OT30: R2 = 0.9119, RMSE = 0.1790 m2/m2). OT30 provided the best LAI estimation accuracy at a sub-voxel size of 0.09 m and the best checkpoint accuracy (OT30: RMSE [H] = 0.2917 m, RMSE [V] = 0.1797 m). The results highlight that coupling oblique photography and nadiral photography can be an effective solution to estimate forest LAI. [ABSTRACT FROM AUTHOR]

When extracting land-use information from remote sensing imagery using image segmentation, obtaining fine edges for extracted objects is a key problem that is yet to be solved. In this study, we developed a new weight feature value convolutional neural network (WFCNN) to perform fine remote sensing image segmentation and extract improved land-use information from remote sensing imagery. The WFCNN includes one encoder and one classifier. The encoder obtains a set of spectral features and five levels of semantic features. It uses the linear fusion method to hierarchically fuse the semantic features, employs an adjustment layer to optimize every level of fused features to ensure the stability of the pixel features, and combines the fused semantic and spectral features to form a feature graph. The classifier then uses a Softmax model to perform pixel-by-pixel classification. The WFCNN was trained using a stochastic gradient descent algorithm; the former and two variants were subject to experimental testing based on Gaofen 6 images and aerial images that compared them with the commonly used SegNet, U-NET, and RefineNet models. The accuracy, precision, recall, and F1-Score of the WFCNN were higher than those of the other models, indicating certain advantages in pixel-by-pixel segmentation. The results clearly show that the WFCNN can improve the accuracy and automation level of large-scale land-use mapping and the extraction of other information using remote sensing imagery. [ABSTRACT FROM AUTHOR]