Accurate knowledge of urban forest patterns contributes to well-managed urbanization, but accurate urban tree canopy mapping is still a challenging task because of the complexity of the urban structure. In this paper, a new method that combines double-branch U-NET with multi-temporal satellite images containing phenological information is introduced to accurately map urban tree canopies. Based on the constructed GF-2 image dataset, we developed a double-branch U-NET based on the feature fusion strategy using multi-temporal images to obtain an accuracy improvement with an IOU (intersection over union) of 2.3% and an F1-Score of 1.3% at the pixel level compared to the U-NET using mono-temporal images which performs best in existing studies for urban tree canopy mapping. We also found that the double-branch U-NET based on the feature fusion strategy has better accuracy than the early fusion strategy and decision fusion strategy in processing multi-temporal images for urban tree canopy mapping. We compared the impact of image combinations of different seasons on the urban tree canopy mapping task and found that the combination of summer and autumn images had the highest accuracy in the study area. Our research not only provides a high-precision urban tree canopy mapping method but also provides a direction to improve the accuracy both from the model structure and data potential when using deep learning for urban tree canopy mapping. Full article

Quantification of hydrologic model prediction uncertainty for various flow quantiles is of great importance for water resource planning and management. Thus, this study is designed to assess the effect of subbasin spatial scale on the hydrological model prediction uncertainty for different flow quantiles. The Soil Water Assessment Tool (SWAT), a geographic information system (GIS) interfaced hydrological model, was used in this study. Here, the spatial variations within the sub-basins of the Omo Gibe River basin in Ethiopia’s Abelti, Wabi, and Gecha watersheds from 1989 to 2020 were examined. The results revealed that (1) for the Abelti, Wabi, and Gecha watersheds, SWAT was able to reproduce the observed hydrograph with more than 85%, 82%, and 73% accuracy in terms of the Nash-Sutcliffe efficiency coefficient (NSE), respectively; (2) the variation in the spatial size of the subbasin had no effect on the overall flow simulations. However, the reproduction of the flow quantiles was considerably influenced by the subbasin spatial scales; (3) the coarser subbasin spatial scale resulted in the coverage of most of the observations. However, the finer subbasin spatial scale provided the best simulation closer to the observed stream flow pattern; (4) the SWAT model performed much better in recreating moist, high, and very-high flows than it did in replicating dry, low, and very-low flows in the studied watersheds; (5) a smaller subbasin spatial scale (towards to distributed model) may better replicate low flows, while a larger subbasin spatial scale (towards to lumped model) enhances high flow replication precision. Thus, it is crucial to investigate the subbasin spatial scale to reproduce the peak and low flows; (6) in this study, the best subbasin spatial scales for peak and low flows were found to be 79–98% and 29–42%, respectively. Hence, it is worthwhile to investigate the proper subbasin spatial scales in reproducing various flow quantiles toward sustainable management of floods and drought. Full article

The uncertainty from the under-estimation and over-estimation of forest aboveground biomass (AGB) is an urgent problem in optical remote sensing estimation. In order to more accurately estimate the AGB of Pinus densata forests in Shangri-La City, we mainly discuss three non-parametric models—the artificial neural network (ANN), random forests (RFs), and the quantile regression neural network (QRNN) based on 146 sample plots and Sentinel-2 images in Shangri-La City, China. Moreover, we selected the corresponding optical quartile models with the lowest mean error at each AGB segment to combine as the best QRNN (QRNNb). The results showed that: (1) for the whole biomass segment, the QRNNb has the best fitting performance compared with the ANN and RFs, the ANN has the lowest R² (0.602) and the highest RMSE (48.180 Mg/ha), and the difference between the QRNNb and RFs is not apparent. (2) For the different biomass segments, the QRNNb has a better performance. Especially when AGB is lower than 40 Mg/ha, the QRNNb has the highest R² of 0.961 and the lowest RMSE of 1.733 (Mg/ha). Meanwhile, when AGB is larger than 160 Mg/ha, the QRNNb has the highest R² of 0.867 and the lowest RMSE of 18.203 Mg/ha. This indicates that the QRNNb is more robust and can improve the over-estimation and under-estimation in AGB estimation. This means that the QRNNb combined with the optimal quantile model of each biomass segment provides a method with more potential for reducing the uncertainties in AGB estimation using optical remote sensing images. Full article

The ecological redline defines areas where industrialization and urbanization development should be prohibited. Its purpose is to establish the most stringent environmental protection system to meet the urgent needs of ecological function guarantee and environmental safety. Nowadays, deep learning methods have been widely used in change detection tasks based on remote sensing images, which can just be applied to the monitoring of the ecological redline. Considering the convolution-based neural networks’ lack of utilization of global information, we choose a transformer to devise a Siamese network for change detection. We also use a transformer to design a pyramid pooling module to help the network maintain more features. Moreover, we construct a self-supervised network based on a contrastive method to obtain a pre-trained model, especially for remote sensing images, aiming to achieve better results. As for study areas and data sources, we chose Hebei Province, where the environmental problem is quite nervous, and used its GF-1 satellite images to do our research. Through ablation experiments and contrast experiments, our method is proven to have significant advantages in terms of accuracy and efficiency. We also predict large-scale areas and calculate the intersection recall rate, which confirms that our method has practical values. Full article

Landslides are geological disasters that can cause great damage to natural and social environments. Landslide hazard assessments are crucial for disaster prevention and mitigation. Conventional regional landslide hazard assessment results are static and do not take into account the dynamic changes in landslides; thus, areas with landslides that have been treated and stabilized are often still identified as high-risk areas. Therefore, a new hazard assessment method is proposed in this paper that combines the deformation rate results obtained by interferometric synthetic aperture radar (InSAR) with the results of conventional hazard assessments to obtain the hazard assessment level while considering the deformation factor of the study area, with Zhouqu, Gansu Province, selected as the case study. First, to obtain the latest landslide inventory map of Zhouqu, the hazard assessment results of the study area were obtained based on a neural network and statistical analysis, and an innovative combination of the deformation rate results of the steepest slope direction from the ascending and descending data were obtained by InSAR technology. Finally, the hazard assessment level considering the deformation factor of Zhouqu was obtained. The method proposed in this paper allows for a near-term hazard assessment of the study area, which in turn enables dynamic regional landslide hazard assessments and improves the efficiency of authorities when conducting high-risk-area identification and management. Full article

Marine heatwaves (MHWs) are persistent, discrete, extreme high-temperature events in the ocean, which can destructively affect marine ecosystems. Using satellite remote sensing data and reanalysis data from 1982 to 2021, we find that six indices characterizing the MHWs are in a remarkable increasing trend in the Japan/East Sea (JES), which shows that the most severe MHW events take place in the East Korean Bay (EKB) in the summer of 2021. Based on this finding, the present study focuses on the characteristics and mechanisms of the MHWs in the EKB and its adjacent areas from June to August 2021. The analysis reveals that the total days and mean intensity of MHWs that occur in the EKB are 1.84 and 1.47 times more than those averaged in the JES, respectively. It is shown that mechanisms for the occurrences of the MHWs in the summer of 2021 are caused by the atmospheric high-pressure system moving to the EKB area. Other reasons also decrease the water cooling: the net positive lateral heat fluxes across open boundaries, and the weak sea surface wind over the EKB area. Other possible reasons which cause the summer MHW events in 2021 need the oceanic numerical models to further investigate the issue. Full article

The vegetation of the post-mining areas is subject to constant and significant changes. Reclamation works, carried out after the cessation of mineral extraction, contribute to the intensive development of new plant species. However, secondary deformations, occurring even many years after the end of exploitation, may cause the degradation of the vegetation cover. It is, therefore, an important issue to identify changes in flora conditions and to determine whether and to what extent past mining has a negative impact on the plant cover state. The objectives of this research have been as follows: (1) analysis of the flora condition in the post-mining area in the 1989–2019 period, (2) identification of sites with significant changes in vegetation state, and (3) modeling of the relationship between the identified changes in vegetation and former mining activities. The research was carried out in the area of the former opencast and underground lignite mine “Friendship of Nations—Babina Shaft,” which is located in the present-day Geopark (Western Poland), using Landsat TM/ETM+/OLI derived vegetation indices (NDVI, NDII, MTVI2) and GIS-based spatial regression. The results indicate a general improvement in flora condition, especially in the vicinity of post-mining waste heaps and former opencast excavations, with the exception of the northwestern part of the former mining field where the values of all of the analyzed vegetation indices have decreased. Also, four zones of statistically significant changes in the flora condition were identified. Finally, the developed GWR models demonstrate that former mining activities had a significant influence on changes in the plant cover state of the analyzed region. Full article

Obtaining accurate and timely crop area information is crucial for crop yield estimates and food security. Because most existing crop mapping models based on remote sensing data have poor generalizability, they cannot be rapidly deployed for crop identification tasks in different regions. Based on a priori knowledge of phenology, we designed an off-center Bayesian deep learning remote sensing crop classification method that can highlight phenological features, combined with an attention mechanism and residual connectivity. In this paper, we first optimize the input image and input features based on a phenology analysis. Then, a convolutional neural network (CNN), recurrent neural network (RNN), and random forest classifier (RFC) were built based on farm data in northeastern Inner Mongolia and applied to perform comparisons with the method proposed here. Then, classification tests were performed on soybean, maize, and rice from four measurement areas in northeastern China to verify the accuracy of the above methods. To further explore the reliability of the method proposed in this paper, an uncertainty analysis was conducted by Bayesian deep learning to analyze the model’s learning process and model structure for interpretability. Finally, statistical data collected in Suibin County, Heilongjiang Province, over many years, and Shandong Province in 2020 were used as reference data to verify the applicability of the methods. The experimental results show that the classification accuracy of the three crops reached 90.73% overall and the average F1 and IOU were 89.57% and 81.48%, respectively. Furthermore, the proposed method can be directly applied to crop area estimations in different years in other regions based on its good correlation with official statistics. Full article

Yangjiang coastal waters provide vital spawning grounds, feeding grounds, and nursery areas for many commercial fish species. It is important to understand the spatial distribution of fish for the management, development, and protection of fishery resources. In this study, an acoustic survey was conducted from 29 July to 5 June 2021. Meanwhile, remote sensing data were collected, including sea surface temperature (SST), chlorophyll concentration (Chla), sea surface salinity (SSS), and sea surface temperature anomaly (SSTA). The spatial distribution of density and biomass of fish was analyzed based on acoustic survey data using the geostatistical method. Combining with remote sensing data, we explored the relation between fish density and the environment based on the GAMs model. The results showed that fish are mainly small individuals. The horizontal distri-bution of fish density had a characteristic of high nearshore and low offshore. In the vertical direc-tion, fish are mainly distributed in surface-middle layers in shallow waters (<10 m) and in middle-bottom layers in deeper waters (>10 m), respectively. The deviance explained in the optimal GAM model was 59.2%. SST, Chla, SSS, and longitude were significant factors influencing fish density distribu-tion with a contribution of 35.3%, 11.8%, 6.5%, and 5.6%, respectively. This study can pro-vide a scientific foundation and data support for rational developing and protecting fishery re-sources in Yangjiang coastal waters. Full article

Recent research has shown the advantages of incorporating multisource geospatial data into the classification of urban functional zones (UFZs), particularly remote sensing and social sensing data. However, the effects of combining datasets of varying quality have not been thoroughly analyzed. In addition, human mobility patterns from social sensing data, which capture signals of human activities, are often represented by origin-destination pairs, thus ignoring spatial relationships between UFZs embedded in mobility trajectories. To address the aforementioned issues, this study proposed a graph-based UFZ classification framework that fuses semantic features from high spatial resolution (HSR) remote sensing images, points of interest, and GPS trajectory data. The framework involves three main steps: (1) High-level scene information in HSR remote sensing imageries was extracted through deep neural networks, and multisource semantic embeddings were constructed based on physical features and social sensing features from multiple geospatial data sources; (2) UFZ mobility graph was constructed by spatially joining trajectory information with UFZs to construct topological connections between functional parcel segments; and (3) UFZ segments and multisource semantic features were transformed into nodes and embeddings in the mobility graphs, and subsequently graph-based models were adopted to identify UFZs. The proposed framework was tested on Zhuhai and Singapore datasets. Results indicated that it outperformed traditional classification methods with an overall accuracy of 76.7% and 84.5% for Zhuhai and Singapore datasets, respectively. The proposed framework contributes to literature in heterogeneous data fusion and is generalizable to other UFZ classification scenarios where human mobility patterns play a role. Full article

Dynamic detection of forest change is the fundamental method of monitoring forest resources and an essential means of preserving the accuracy and timeliness of forest land resource data. This study focuses on a deep learning-based method for dynamic forest change detection using Sentinel-2 satellite data, especially within mountainous areas. First, the performance of various deep learning models (U-Net++, U-Net, LinkNet, DeepLabV3+, and STANet) and various loss functions (CrossEntropyLoss(CELoss), DiceLoss, FocalLoss, and their combinations) are compared on a self-made dataset. Next, the best model and loss function is used to predict the annual forest change in Hunan Province from 2017 to 2021, and the detection results are evaluated in 12 sample areas. Finally, forest changes are detected in Sentinel-2 images for each quarter of 2017–2021. In addition, a dynamic detection map of forest change in Hunan Province from 2017 to 2021 is drawn. The results reveal that the U-Net++ model and the CELoss performed the best on the self-made dataset, with a Precision of 0.795, a Recall of 0.748, and an F1-score of 0.771. The results of annual and quarterly forest change detection were consistent with the changes in the Sentinel-2 images with accurate boundaries. This result demonstrates the high practicality and generalizability of the method used in this paper. This paper achieves a rapid and accurate extraction of multi-temporal Sentinel-2 image forest change areas based on the U-Net++ model, which can be used as a benchmark for future large territorial areas monitoring and management of forest resources. Full article

Grasshoppers can greatly interfere with agriculture and husbandry, and they will breed and grow rapidly in suitable habitats. Therefore, it is necessary to extract the distribution of the grasshopper potential habitat (GPH), analyze the spatial-temporal characteristics of the GPH, and detect the different effects of key environmental factors in the meadow and typical steppe. To achieve the goal, this study took the two steppe types of Xilingol (the Inner Mongolia Autonomous Region of China) as the research object and coupled them with the MaxEnt and multisource remote sensing data to establish a model. First, the environmental factors, including meteorological, vegetation, topographic, and soil factors, that affect the developmental stages of grasshoppers were obtained. Secondly, the GPH associated with meadow and typical steppes from 2018 to 2022 were extracted based on the MaxEnt model. Then, the spatial-temporal characteristics of the GPHs were analyzed. Finally, the effects of the habitat factors in two steppe types were explored. The results demonstrated that the most suitable and moderately suitable areas were distributed mainly in the southern part of the meadow steppe and the eastern and southern parts of the typical steppe. Additionally, most areas in the town of Gaorihan, Honggeergaole, Jirengaole, as well as the border of Wulanhalage and Haoretugaole became more suitable for grasshoppers from 2018 to 2022. This paper also found that the soil temperature in the egg stage, the vegetation type, the soil type, and the precipitation amount in the nymph stage were significant factors both in the meadow and typical steppes. The slope and precipitation in the egg stage played more important roles in the typical steppe, whereas the aspect had a greater contribution to the meadow steppe. These findings can provide a methodical guide for grasshopper control and management and for further ensuring the security of agriculture and husbandry. Full article

As an important factor determining the competitiveness of raw cotton, cotton fiber quality has received more and more attention. The results of traditional detection methods are accurate, but the sampling cost is high and has a hysteresis, which makes it difficult to measure cotton fiber quality parameters in real time and at a large scale. The purpose of this study is to use time-series UAV (Unmanned Aerial Vehicle) multispectral and RGB remote sensing images combined with machine learning to model four main quality indicators of cotton fibers. A deep learning algorithm is used to identify and extract cotton boll pixels in remote sensing images and improve the accuracy of quantitative extraction of spectral features. In order to simplify the input parameters of the model, the stepwise sensitivity analysis method is used to eliminate redundant variables and obtain the optimal input feature set. The results of this study show that the R² of the prediction model established by a neural network is improved by 29.67% compared with the model established by linear regression. When the spectral index is calculated after removing the soil pixels used for prediction, R² is improved by 4.01% compared with the ordinary method. The prediction model can well predict the average length, uniformity index, and micronaire value of the upper half. R² is 0.8250, 0.8014, and 0.7722, respectively. This study provides a method to predict the cotton fiber quality in a large area without manual sampling, which provides a new idea for variety breeding and commercial decision-making in the cotton industry. Full article

Hot giant exoplanets are very exotic objects with no equivalent in the Solar System that allow us to study the behavior of atmospheres under extreme conditions. Their thermal and chemical day–night dichotomies associated with extreme wind dynamics make them intrinsically 3D objects. Thus, the common 1D assumption, relevant to study colder atmospheres, reaches its limits in order to be able to explain hot and ultra-hot atmospheres and their evolution in a consistent way. In this review, we highlight the importance of these 3D considerations and how they impact transit, eclipse and phase curve observations. We also analyze how the models must adapt in order to remain self-consistent, consistent with the observations and sufficiently accurate to avoid bias or errors. We particularly insist on the synergy between models and observations in order to be able to carry out atmospheric characterizations with data from the new generation of instruments that are currently in operation or will be in the near future. Full article

The GRACE follow-on satellites carry the very first interspacecraft Laser Ranging Interferometer (LRI). After more than four years in orbit, the LRI outperforms the sensitivity of the conventional Microwave Instrument (MWI). However, in the current data processing scheme, the LRI product still needs the MWI data to determine the unknown absolute laser frequency, representing the “ruler” for converting the raw phase measurements into a physical displacement in meters. In this paper, we derive formulas for precisely performing that conversion from the phase measurement into a range, accounting for a varying carrier frequency. Furthermore, the dominant errors due to knowledge uncertainty of the carrier frequency as well as uncorrected time biases are derived. In the second part, we address the dependency of the LRI on the MWI in the currently employed cross-calibration scheme and present three different models for the LRI laser frequency, two of which are largely independent of the MWI. Furthermore, we analyze the contribution of thermal variations on the scale factor estimates and the LRI-MWI residuals. A linear model called Thermal Coupling (TC) is derived, which significantly reduces the differences between LRI and MWI to a level where the MWI observations limit the comparison. Full article