Shuhe Zhao

High-resolution multispectral images are of great value in various fields. However, the physical limitations of satellite sensors hinder the simultaneous acquisition of high spatial resolution and high spectral resolution images. Deep learning has become a powerful tool for remote sensing image fusion, but its full potential has not been fully utilized. In order to maximize the quality of the high-resolution multispectral images generated by the improved model, this paper proposes a module called EBIFusion, which introduces an error backtracking mechanism to improve fusion performance. The module uses the intermediate results of the deep learning model to capture the information lost during the high-resolution image generation process, thereby guiding the optimization of model training. The experimental results on the GF-6 dataset show that the QNR index is increased by 2.22% after the introduction of the module. In addition, the spatial and spectral quality has been continuously improved on multiple datasets, including QuickBird and GF-2. The optimized models, such as PSGAN, PNN, GPPNN, and UCGAN, show stronger spatial details and spectral fidelity. The main contribution of this paper is to propose an error backtracking framework for recovering and compensating for the lost information in the process of remote sensing image fusion based on deep learning. Based on this, a lightweight and model-independent enhancement module EBIFusion is designed, which can be integrated into different deep learning fusion architectures. At the same time, the generalization ability of the module in multiple datasets and network paradigms is verified. In summary, the error backtracking module enhances the quality of the generated high-resolution multispectral images. In addition, it is not limited to specific models and data and can be used as the basis for a versatile and effective optimization component to improve the availability of high-resolution multispectral images.

Methane source-rate inversion from remote-sensing plume imagery is essential for emissions monitoring, but its accuracy is often limited by uncertainty in ancillary wind information. This study examines how physical knowledge can be integrated into a deep-learning inversion model when the available wind input is imperfect. Using a controlled large-eddy-simulation (LES) benchmark designed for EnMAP/PRISMA-style imaging-spectrometer methane quantification, we compare six models that span image-only regression, flexible wind conditioning, simplified hard integrated-mass-enhancement (IME) coupling, and soft physics-guided learning under clean inputs, deterministic wind bias, stochastic Gaussian wind noise, and source-rate-stratified tests. Under clean benchmark conditions, flexible wind conditioning provides the best scalar accuracy, with FiLM reaching a mean absolute percentage error (MAPE) of 6.19% and a root mean squared error (RMSE) of 1323.36, followed closely by Concat (MAPE 6.37%, RMSE 1325.69). The simplified hard-coupling model is sensitive to wind perturbations: DIN-hard rises from MAPE 8.44% under clean inputs to 31.39% and 26.89% under deterministic wind-bias multipliers α = 0.7 and α = 1.3, respectively, and becomes unstable under stronger Gaussian wind noise in the tested protocol. By contrast, DIN-soft-v2 remains competitive under clean conditions (MAPE 6.39%, RMSE 1360.94), follows smoother degradation under biased or noisy wind, and improves plume spatial diagnostics relative to DIN-soft (center-of-mass shift 3.92 versus 4.07 pixels; plume alignment degree 2.60 versus 2.72 degrees). The calibrated IME-style physical baseline reaches a clean MAPE 24.45%, indicating that the learning-based models substantially outperform this benchmark physical proxy. Within this LES-based benchmark and the tested wind-perturbation protocols, the results suggest that IME-inspired physical knowledge is more robustly incorporated as a calibratable soft prior than as the simplified hard log-additive forward coupling considered here; however, transfer to real satellite scenes still requires validation.

1. Natural gas is a clean and environmentally friendly energy source for sustainable development and widely used in industrial production and residential life as a fuel. At present, the world has e...

Gas flaring, a long-standing issue in the petrochemical industry as a business problem, has become the second leading cause of methane emissions. We proposed a gas flaring detection method using multi-source remote sensing data. The method combined Visible Infrared Imaging Radiometer Suite (VIIRS) Nightfire data and the Normalized Hotspot Index (NHI) algorithm. At first, the K-means algorithm is applied for spatial clustering of VIIRS Nightfire data. Then, the NHI algorithm was calculated using the Landsat-8 Operational Land Imager and Sentinel-2 Multi-spectral Instrument images. Finally, Xinjiang province in China was selected as the study area, and the gas flaring detection results were validated by the existing global gas flare datasets. The results show that the method presented in our study has high performance and provides more accurate information in detecting gas flares, with an accuracy of 72.73%. In addition, the geographic location of gas flaring sites correlates with oil and gas fields, primarily concentrated in the Tarim Basin in the southwest and Junggar and Turpan Basins in the north. Aksu accounted for the highest, representing 43.05% of the total. This method offers a reliable way to detect gas flares onshore and provides effective measurements for controlling methane emissions.

The common channel attention mechanism maps feature statistics to feature weights. However, the effectiveness of this mechanism may not be assured in remotely sensing images due to statistical differences across multiple bands. This paper proposes a novel channel attention mechanism based on feature information called the feature information entropy attention mechanism (FEM). The FEM constructs a relationship between features based on feature information entropy and then maps this relationship to their importance. The Vaihingen dataset and OpenEarthMap dataset are selected for experiments. The proposed method was compared with the squeeze-and-excitation mechanism (SEM), the convolutional block attention mechanism (CBAM), and the frequency channel attention mechanism (FCA). Compared with these three channel attention mechanisms, the mIoU of the FEM in the Vaihingen dataset is improved by 0.90%, 1.10%, and 0.40%, and in the OpenEarthMap dataset, it is improved by 2.30%, 2.20%, and 2.10%, respectively. The proposed channel attention mechanism in this paper shows better performance in remote sensing land use classification.

Agricultural drought assessment is based on soil moisture deficit during the plant-growing season. The available long-term in situ soil moisture data can be used to evaluate the drought indices’ performance. Drought indices have different sensitivities to various climates and vegetation cover types. Moreover, little research has been carried out on the sensitivity to soil moisture in specific soil layers. Comparing the performance of drought indices in different environments enables us to use and construct an effective drought index for drought delineation. We used soil moisture data from 2000 to 2021 to compare the performance of satellite image-derived drought indices (VCI, NLSWI, TCI, VHI, and NVSWI) in different climates, vegetation cover types, and soil layers over the Contiguous United States at monthly intervals and a 1000 m spatial resolution. The performances of drought indices based on vegetation status showed little differences in the different soil layers. In contrast, drought indices based on single-temperature conditions performed better in the 0–20 cm soil layer than in the deeper soil layer. The integrated index might not improve the correlation in all soil layers compared with single-condition indices under some environments. In general, while the optimal drought index might vary in different environments, the VHI performed most efficiently in most cases. This research has the potential to improve our understanding of drought monitoring in large regions with different climates, vegetation cover types, and soil layers.

Background: Mara River Basin is an ecologically fragile area in East Africa, with a pattern of alternating wet and dry seasons shaped by periodic precipitation. Considering the regional biological traits and climatic change, the vegetation's response to seasonal variation is complicated and frequently characterized by time lags. This study analyzed the variation of the Normalized Difference Vegetation Index (NDVI) and investigated its time lag to precipitation at the monthly scale. NDVI characteristic peaks were proposed from the perspective of seasonal mechanisms and were quantified to assess the lag effect. Results: The results showed that the Anomaly Vegetation Index could identify low precipitation in 2006, 2009, and 2017. The NDVI showed an increasing trend in 75% of areas of the basin, while showed a decreased significance in 3.5% of areas, mainly in savannas. As to the time lag, the 1-month lag effect dominated most months, and the spatiotemporal disparities were noticeable. Another method considering the alternations of wet and dry seasons found that the time lag was approximately 30 days. Based on the time distribution of NDVI characteristic peaks, the average time lag was 35.5 days and increased with the range of seasons. Conclusions: The findings confirmed an increasing trend of NDVI in most regions from 2001 to 2020, while the trends were most obvious in the downstream related to human activities. The results could reflect the time lag of NDVI response to precipitation, and the 1-month lag effect dominated in most months with spatial heterogeneity. Four NDVI characteristic peaks were found to be efficient indicators to assess the seasonal characteristics and had a great potential to quantify vegetation variation.

The remote sensing inversion of the water quality parameters of a complex river network in the absence of historical ground data is a difficult problem in the field of remote sensing. In this paper, a sub-regional inversion method for typical water quality parameters is presented for a complex river network using Gaofen-1 satellite data. Qidong’s rivers were selected as the survey region, and different band combination models and datasets on different river sub-regions were used to perform the remote sensing inversion, which realized the inversion of the permanganate index (CODMn), ammonia nitrogen (NH3-N), total phosphorus (TP), and total nitrogen (TN) in the rivers. The results show that all the coefficients of determination (R^2) of the inversion models are larger than 0.5, indicating an increase of about 0.4 when compared with the inversion method of the whole region, indicating good relevance. Water quality data and satellite data collected at different times were used for validation, which showed good results. On the basis of the water quality inversion, the key polluted areas were extracted in combination with on-site surveys to find the pollution source in order to verify the results of the inversion. The sub-region inversion method proposed in this paper can be used for the remote sensing inversion of the water quality parameters of complex river networks in the absence of historical ground data.

Satellite-based soil moisture products are suitable for large-scale regional monitoring due to the accessibility. Five soil moisture products including SMAP, ESA CCI, and AMSR2 (ascending, descending, and average) were selected in the continental United States (US) from 2016 to 2021. To evaluate the performance of the products and assess their applicability, ISMN (International Soil Moisture Network) data were used as the in situ measurement. PBIAS (Percentage of BIAS), R (Pearson correlation coefficient), RMSE (Root Mean Square Error), ubRMSE (unbiased RMSE), MAE (Mean Absolute Error), and MBE (Mean Bias Error) were selected for evaluation. The performance of five products over six observation networks and various land cover types was compared, and the differences were analyzed at monthly, seasonal, and annual scales. The results show that SMAP had the smallest deviation with the ISMN data because PBIAS was around −0.13, and MBE was around −0.02 m³/m³. ESA CCI performed the best in almost all aspects; its R reached around 0.7, and RMSE was only around 0.07 m³/m³ at the three time scales. The performance of the AMSR2 products varied greatly across the time scales, and increasing errors and deviations showed from 2016 to 2020. The PBO_H2O and USCRN networks could reflect soil moisture characteristics in the continental US, while iRON performed poorly. The evaluation of the networks was closely related to spatial distributions. All products performed better over grasslands and shrublands with R, which was greater than 0.52, and ubRMSE was around 0.1 m³/m³, while products performed worse over forests, where PBIAS was less than −0.62, and RMSE was greater than 0.2 m³/m³, except for ESA CCI. From the boxplot, SMAP was close to the ISMN data with differences less than 0.004 m³/m³ between the median and lower quartiles.

The Mara River Basin of Africa has a world-famous ecosystem with vast vegetation, which is home to many wild animals. However, the basin is experiencing vegetation degradation and bad climate change, which has caused conflicts between people and wild animals, especially in dry seasons. This paper studied the vegetation greenness (VG), vegetation greenness trends (VGT), and their responses to climate change in dry seasons in the Mara River Basin, Africa. Firstly, based on Google Earth Engine (GEE) platform and Sentinel-2 images, the vegetation distribution map of the Mara River Basin was drawn. Then dry seasons MODIS NDVI data (January to February and June to September) were used to analyze the VGT. Finally, a random forest regression algorithm was used to evaluate the response of VG and VGT to temperature and precipitation derived from ERA5 from 2000 to 2019 at a resolution of 250 m. The results showed that the VGT was fluctuating in dry seasons, and the spatial differentiation was obvious. The greenness increasing trends both upstream and downstream were significantly larger than that of in the midstream. The responses of VG to precipitation were almost twice larger than temperature, and the responses of VGT to temperature were about 1.5 times larger than precipitation. The climate change trend of rising temperature and falling precipitation will lead to the degradation of vegetation and the reduction of crop production. There will be a vegetation degradation crisis in dry seasons in the Mara River Basin in the future. Identifying the spatiotemporal changes of VGT in dry seasons will be helpful to understand the response of VG and VGT to climate change and could also provide technical support to cope with climate-change-related issues for the basin.