Search

The Tianshan Expressway plays a crucial role in China’s “Belt and Road” strategy, yet the extreme climate of the Tianshan Mountains poses significant traffic safety risks, hindering local economic development. Efficient detection of hazardous road surface conditions (RSCs) is vital to address these challenges. The complexity and variability of RSCs in the region, exacerbated by harsh weather, make traditional surveillance methods inadequate for real-time monitoring. To overcome these limitations, a vision-based artificial intelligence approach is urgently needed to ensure effective, real-time detection of dangerous RSCs in the Tianshan road network. This paper analyzes the primary structures and architectures of mainstream neural networks and explores their performance for RSC recognition through a comprehensive set of experiments, filling a research gap. Additionally, T-Net, specifically designed for the Tianshan Expressway engineering project, is built upon the optimal architecture identified in this study. Leveraging the split-transform-merge structure paradigm and asymmetric convolution, the model excels in capturing detailed information by learning features across multiple dimensions and perspectives. Furthermore, the integration of channel, spatial, and multi-head attention modules enhances the weighting of key features, making the T-Net particularly effective in recognizing the characteristics of snow-covered and icy road surfaces. All models presented in this paper were trained on a custom RSC dataset, compiled from various sources. Experimental results indicate that the T-Net outperforms fourteen once state-of-the-art (SOTA) models and three models specifically designed for RSC recognition, with 97.44% accuracy and 9.79% loss on the validation set.

Abstract Osteoarthritis (OA), a degenerative disease of the joints, has one of the highest disability rates worldwide. This study investigates the role of pyroptosis-related genes in osteoarthritis and their expression in different chondrocyte subtypes at the individual cell level. Using OA-related datasets for single-cell RNA sequencing and RNA-seq, the study identified PRDEGs and DEGs and conducted Cox regression analysis to identify independent prognostic factors for OA. CASP6, NOD1, and PYCARD were found to be prognostic factors. Combined Weighted Gene Correlation Network Analysis with PPI network, a total of 15 hub genes related to pyroptosis were involved in the notch and oxidative phosphorylation pathways, which could serve as biomarkers for the diagnosis and prognosis of OA patients. The study also explored the heterogeneity of chondrocytes between OA and normal samples, identifying 19 single-cell subpopulation marker genes that were significantly different among 7 chondrocyte cell clusters. AGT, CTSD, CYBC, and THYS1 were expressed differentially among different cell subpopulations, which were associated with cartilage development and metabolism. These findings provide valuable insights into the molecular mechanisms underlying OA and could facilitate the development of new therapeutic strategies for this debilitating disease.

Objective: To investigate the effect of depressive symptoms on osteoporotic bone metabolism and prognosis of joint replacement surgery in elderly male patients with femoral neck fractures. Method: 102 elderly male patients with femoral neck fractures hospitalized in the Beijing Hospital from January 2017 to January 2019 were included. The patients with femoral neck fractures were divided into the depression group and the control group. The observation indicators included: bone mineral density, serum alkaline phosphatase, serum calcium, serum phosphorus, 25-hydroxy-vitamin D, osteocalcin, Type I procollagen amino-terminal propeptide, serum β-isomer of C-terminal telopeptide of type I collagen, hip function scores, and pain visual analogue scale at pre- and post-operative examinations. Results: The BMD was significantly lower in the depressed group than in the control group [either for lumbar spine or hip, P

Abstract Background Tendon injuries are among the most common musculoskeletal disorders. Celecoxib possesses an effective anti-inflammatory activity in the tendon injury treatment. Lactoferrin has a great potential for the tendon regeneration. However, the efficacy of celecoxib combined with lactoferrin in the treatment of tendon injury has not been reported. In this study, we aimed to investigate the effect of celecoxib and lactoferrin on tendon injury and repair, and screen for the crucial genes associated with the tendon injury and repair. Methods The rat tendon injury models were established and divided into four groups: normal control group (n = 10), tendon injury model group (n = 10), celecoxib treatment group (n = 10), and celecoxib + lactoferrin treatment group (n = 10). Then, RNA sequencing was performed to identify differentially expressed lncRNAs (DElncRNAs), miRNAs (DEmiRNAs) and mRNAs (DEmRNAs) in celecoxib treatment group and celecoxib + lactoferrin treatment group. Next, autophagy/hypoxia/ferroptosis/pyroptosis-related DEmRNAs were further identified. Subsequently, functional enrichment, protein–protein interaction (PPI) network and transcriptional regulatory network construction for these genes were performed. Results The animal study demonstrated that combinational administration of celecoxib with lactoferrin rescued the harmful effects caused by celecoxib in the treatment of tendon injury. Compared to tendon injury model group, 945 DEmRNAs, 7 DEmiRNAs and 34 DElncRNAs were obtained in celecoxib treatment group, and 493 DEmRNAs, 8 DEmiRNAs and 21 DElncRNAs were obtained in celecoxib + lactoferrin treatment group, respectively. Subsequently, 376 celecoxib + lactoferrin treatment group-specific DEmRNAs were determined. Then, 25 DEmRNAs associated with autophagy/hypoxia/ferroptosis/pyroptosis were identified. Conclusions Several genes, such as, Ppp1r15a, Ddit4, Fos, Casp3, Tgfb3, Hspb1 and Hspa8, were identified to be associated with tendon injury and repair.

Aboveground biomass (AGB) serves as a crucial measure of ecosystem productivity and carbon storage in alpine grasslands, playing a pivotal role in understanding the dynamics of the carbon cycle and the impacts of climate change on the Qinghai–Xizang Plateau. This study utilized Google Earth Engine to amalgamate Landsat 8 and Sentinel-2 satellite imagery and applied the Random Forest algorithm to estimate the spatial distribution of AGB in the alpine grasslands of the Beiliu River Basin in the Qinghai–Xizang Plateau permafrost zone during the 2022 growing season. Additionally, the geodetector technique was employed to identify the primary drivers of AGB distribution. The results indicated that the random forest model, which incorporated the normalized vegetation index (NDVI), the enhanced vegetation index (EVI), the soil-adjusted vegetation index (SAVI), and the normalized burn ratio index (NBR2), demonstrated robust performance in regards to AGB estimation, achieving an average coefficient of determination (R2) of 0.76 and a root mean square error (RMSE) of 70 g/m2. The average AGB for alpine meadows was determined to be 285 g/m2, while for alpine steppes, it was 204 g/m2, both surpassing the regional averages in the Qinghai–Xizang Plateau. The spatial pattern of AGB was primarily driven by grassland type and soil moisture, with q-values of 0.63 and 0.52, and the active layer thickness (ALT) also played a important role in AGB change, with a q-value of 0.38, demonstrating that the influences of ALT should not be neglected in regards to grassland change.

In recent years, deep learning methods utilizing convolutional neural networks have been extensively employed in hyperspectral image classification (HSI) applications. Nevertheless, while a substantial number of stacked 3D convolutions can indeed achieve high classification accuracy, they also introduce a significant number of parameters to the model, resulting in inefficiency. Furthermore, such intricate models often exhibit limited classification accuracy when confronted with restricted sample data, i.e., small sample problems. Therefore, we propose a spectral–spatial double-branch network (SSDBN) with an attention mechanism for HSI classification. The SSDBN is designed with two independent branches to extract spectral and spatial features, respectively, incorporating multi-scale 2D convolution modules, long short-term memory (LSTM), and an attention mechanism. The flexible use of 2D convolution, instead of 3D convolution, significantly reduces the model’s parameter count, while the effective spectral–spatial double-branch feature extraction method allows SSDBN to perform exceptionally well in handling small sample problems. When tested on 5%, 0.5%, and 5% of the Indian Pines, Pavia University, and Kennedy Space Center datasets, SSDBN achieved classification accuracies of 97.56%, 96.85%, and 98.68%, respectively. Additionally, we conducted a comparison of training and testing times, with results demonstrating the remarkable efficiency of SSDBN.

Abstract Background Osteoporosis (OP) is a metabolic disease that involves microstructure destruction and fracture damage. The present study probed into the significance of miR-215-5p in OP progression. Methods Serum samples were collected from surgical patients and healthy controls. qRT-PCR analysis was utilized to determine the miR-215-5p level in clinical samples and human bone mesenchymal stem cells (hBMSCs) induced by β-glycerol phosphate. A dual luciferase reporter assay was exploited to examine the targeted relationship between miR-215-5p and XIAP. The mineralization and calcium deposition of hBMSCs were assessed by detection of ALP activity, Alizarin red staining, and osteoblast marker expression. Protein expression was determined by western blot analysis. Results MiR-215-5p was significantly reduced in patients with OP and increased in hBMSCs treated with β-glycerophosphate. Enhanced miR-215-5p level triggered augment in osteoblast markers (Alkaline phosphatase/ ALP, Osteocalcin/ OCN, and Runt-Related Transcription Factor 2/ Runx2), which was accompanied by the increase of ALP activity in hBMSCs and accumulation of Calcium. Functional experiments show that XIAP was a target of miR-215-5p and negatively modulated by miR-215-5p. XIAP expression levels were increased in OP samples, and decreased XIAP in β-glycerophosphate-treated hBMSCs inhibited its’ osteogenic differentiation. Functional loss and acquisition experiments depicted that miR-215-5p promoted the differentiation of hBMSCs by inhibiting the XIAP level, playing a protective role in the pathogenesis of OP. Conclusions β-glycerophosphate promoted the osteogenic differentiation of hBMSCs, increased miR-215-5p level, and decreased XIAP. miR-215-5p stimulated osteogenic differentiation of hBMSCs by targeting XIAP, shedding new insights for the detection and therapy of OP.

High spatial–temporal resolution surface net radiation (RN) data are of great significance to the study of climate, ecology, hydrology and cryosphere changes on the Tibetan Plateau (TP), but the verification of the surface net radiation products on the plateau is not sufficient. In this study, the China Meteorological Administration Global Land Surface Reanalysis Products (CRA/Land) and ECMWF Land Surface Reanalysis version 5 (ERA5-Land) RN data were validated using ground measurements at daily and monthly time scales, and the spatiotemporal patterns were also analyzed. The results indicate the following: (1) CRA/Land overestimated while ERA5-Land underestimated RN, but CRA/Land RN outperformed ERA5-Land in observations at the daily and monthly scale. (2) The CRA/Land RN data had a larger error in the central part and a smaller error in the northeast of the TP, while ERA5-Land showed the opposite. (3) The spatial patterns of RN revealed by CRA/Land and ERA5-Land data showed differences in most regions. The CRA/Land data showed that the RN of the TP had a downward trend during 2000 and 2020 with a slope of −0.112 W·m−2/a, while the ERA5-Land data indicated an upward trend with a change rate of 0.016 W·m−2/a. (4) Downwelling shortwave radiation (DSR), upwelling shortwave radiation (USR), downwelling longwave radiation (DLR) and upwelling longwave radiation (ULR) are the four components of RN, and the evaluation results indicate that the DSR, DLR and ULR recorded via CRA/Land and ERA5-Land are consistent with the observed data, but the consistency between the USR recorded via CRA/Land and ERA5-Land and the observed data is poor. (5) The inconsistency of the USR data is the main reason for the large differences in the spatiotemporal distribution of CRA/Land and ERA5-Land RN data across the TP.

Desertification seriously hinders economic development and ecological security, which has led to increased research on desertification monitoring and control. Remote sensing technology is widely used in desert research due to its large detection range and ability to obtain target feature information without touching objects. In order to better monitor and control desertification, the research methods on desert mobility and dune morphology in mobile deserts were reviewed. Among them, an important index to distinguish mobile and nonmobile deserts is desert vegetation coverage. The research progress of desert vegetation coverage based on visual interpretation, the nonlinear spectral model, normalized vegetation index (NDVI) fitting and plant community classification was reviewed. The loss of vegetation in the transitional zone of the desert is a contributing factor to desertification. The new technologies and applications of desert area monitoring, the remote sensing ecological index, and desert feature information extraction were introduced and analyzed. To combat desertification more accurately and effectively, the classification methods of moving dunes based on deep learning were also reviewed. It can be concluded that desertification monitoring methods are gradually becoming more accurate and adaptive, but they remain insufficient and less mature. Therefore, exploring how to apply desertification control technology more scientifically and rationally is an extremely valuable area for research.

Since 2007, Ulva prolifera disasters have occurred every year in the South Yellow Sea of China, the largest green tide disaster in the world. The inter-annual differences make monitoring and early warning for such disasters difficult. This study used remote sensing data (2015–2019) to determine its spatio-temporal variations in all life cycles. The results showed a lay effect between the NDVI-mean and the coverage area of U. prolifera. The spatio-temporal distribution of U. prolifera showed stages and regional differences. From late April to early May, U. prolifera first emerged near the Subei Shoal. After development in the middle of the Yellow Sea, U. prolifera broke out in the eastern sea area of Shandong and Jiangsu, declined in the Shandong sea area, and disappeared near Qingdao. The cycle lasted for approximately 90 days. The sea surface temperature was the necessary condition for the disaster, and the sea wind field was the main driving force for its horizontal drift. This study overcomes the poor timing and continuity of remote sensing data in the monitoring of U. prolifera. It provides a theoretical reference for forecasting the outbreak period of U. prolifera and can aid policy-makers to avert such disasters in advance. HIGHLIGHTS There is a significant hysteresis effect between NDVIM and the U. prolifera coverage area.; U. prolifera disasters at different growth stages are geographically regional.; Sea surface temperature and sea wind field are the main influencing factors of U. prolifera disaster.; NDVIM can provide a scientific theoretical reference for predicting the future outbreak period of U. prolifera.;

Abstract Background The non-invasive quantitative evaluation of left ventricle (LV) function plays a critical role in clinical cardiology. This study proposes a novel ultrasonic biomechanics method by integrating both LV vortex and wall motion to fully assess and understand the LV structure and function. The purpose of this study was to validate the ultrasonic biomechanics method as a quantifiable approach to evaluate LV function. Methods Firstly, B-mode ultrasound images were acquired and processed, which were utilized to implement parameters for quantifying the LV vortex and wall motion respectively. Next, the parameters were compared in polyvinyl alcohol cryogen (PVA) phantoms with different degree of stiffness corresponding to different freezing and thawing cycles in vitro. Finally, the parameters were computed in vivo during one cardiac cycle to assess the LV function in normal and abnormal subjects in vivo. Results In vitro study, the velocity field of PVA phantom differed with stiffness (varied elasticity modulus). The peak of strain for wall motion decreases with the increase of elasticity modulus, and periodically changed values. Statistical analysis for parameters of vortex dynamics (energy dissipation index, DI; kinetic energy fluctuations, KEF; relative strength, RS; and vorticity, W) based on different elasticity (E) of phantom depicted the good viability of this algorithm. In vivo study, the results confirmed that subjects with LV dysfunction had lower vorticity and strain (S) compared to the normal group. Conclusion Ultrasonic biomechanics method can obtain the vortex and wall motion of left ventricle. The method may have potential clinical value in evaluation of LV dysfunction.

Fatty acid synthase (FASN) is highly expressed in multiple types of human cancers and is recognized as one of the therapeutic targets for treating cancer metastasis. α-Mangostin is a natural xanthone extracted from mangosteen fruit, and possesses various biological activities. In our previous studies, α-mangostin was found to inhibit FASN activity. The present study was designed to reveal the effects of α-mangostin on osteosarcoma and to reveal whether the mechanism of α-mangostin in anticancer activity is related to FASN inhibition. Cytotoxicity was assessed in osteosarcoma MG63, 143B and U2OS cells. Cell viability was detected by an MTT assay. The protein expression levels were detected by western blotting. Flow cytometry, Annexin V/propidium iodide dual staining and Hoechst 33258 staining were performed to assess the apoptotic effects. Wound healing and Transwell assays were used to detect the inhibitory effect of α-mangostin on osteosarcoma cells invasion and migration. We found that α-mangostin blocked FASN expression, inhibited osteosarcoma cell proliferation, invasion and migration in a dose-dependent manner. In addition, α-mangostin regulated endoplasmic reticulum transmembrane receptors and signal protein expression in osteosarcoma cells. These findings suggested that α-mangostin suppresses osteosarcoma cell proliferation and metastasis by inhibiting FASN expression, which provides a basis as a potential target for osteosarcoma treatment.

As an image-segmentation method based on graph theory, GrabCut has attracted more and more researchers to pay attention to this new method because of its advantages of simple operation and excellent segmentation. In order to clarify the research status of GrabCut, we begin with the original GrabCut model, review the improved algorithms that are new or important based on GrabCut in recent years, and classify them in terms of pre-processing based on superpixel, saliency map, energy function modification, non-interactive improvement and some other improved algorithms. The application status of GrabCut in various fields is also reviewed. We also experiment with some classical improved algorithms, including GrabCut, LazySnapping, OneCut, Saliency Cuts, DenseCut and Deep GrabCut, and objectively analyze the experimental results using five evaluation indicators to verify the performance of GrabCut. Finally, some existing problems are pointed out and we also propose some future work.

With the rapid development of new energy technologies and aiming at the proposal of the “DOUBLE CARBON” goal, the proportion of wind energy and other new sustainable energy power solutions in the power industry continues to increase and occupy a more critical position. However, the instability of wind power output brings serious challenges to safe and stable power grid operations. Therefore, accurate ultra-short-term wind power prediction is of great significance in stabilizing power system operations. This paper presents an ACNN-BiGRU wind power ultra-short-term prediction model based on the Attention mechanism, the fusion of convolutional neural network (CNN), and bidirectional gated recurrent unit (BiGRU). The model takes a single wind turbine as the prediction unit and uses the real-time meteorological data in the wind farm, the historical power data of the wind turbine, and the real-time operation data for parallel training. Then, it extracts the key features of the input data through CNN and uses the BiGRU network to conduct bidirectional modeling learning on the dynamic changes of the features proposed by CNN. In addition, the Attention mechanism is introduced to give different weights to BiGRU implicit states through mapping, weighting, and learning parameter matrix to complete the ultra-short-term wind power prediction. Finally, the actual observation data of a wind farm in Northwest China is used to verify the feasibility and effectiveness of the proposed model. The model provides new ideas and methods for ultra-short-term high-precision prediction for wind power.

Abstract Spin‐up is essential to provide initial conditions for land surface models (LSM) when they cannot be given reliably as in the application to regional permafrost change studies. In this study, the impacts of spin‐up strategy including total spin‐up length and cycling scheme on modeling of permafrost dynamics on the Qinghai‐Tibet Plateau (QTP) were evaluated through two groups of experiments using a modified Noah LSM. The first group aims to test different total spin‐up lengths and the second group for different cycling schemes. The results show that the presence of permafrost prolongs the convergence of the model. Vertically, the slowest convergence is observed at the permafrost table. The insufficiency of total spin‐up length is prone to underestimate permafrost area and overestimate the degradation rate. Different cycling schemes considerably affect the resulting initial thermal fields and result in degradation rates with a difference of 3.37 × 103 km2/a on the QTP, which exceeds the difference (2.92 × 103 km2/a) in the degradation rates reported in existing studies. The multi‐year cycling scheme is generally preferred, but overlong cycle length should be avoided to prevent the introduction of climate change trends in the spin‐up period. We recommend a spin‐up strategy of a 500‐year cycling with the first 5‐ to 10‐year of forcing for modeling permafrost on the QTP with the Noah LSM. Our findings highlight the importance of the spin‐up strategy, which is usually neglected in present LSM‐based permafrost modeling studies.

Generating an unbiased inventory of mass movements is challenging, particularly in a large region such as China. However, due to the enormous threat to human life and property caused by the increasing number of mass movements, it is imperative to develop a reliable nationwide mass movement susceptibility model to identify mass movement-prone regions and formulate appropriate disaster prevention strategies. In recent years, the mixed-effects models have shown their unique advantages in dealing with the biased mass movement inventory, yet there are no relevant studies to compare different mixed-effects models. This research compared three mixed-effects models to explore the most plausible and robust susceptibility mapping model, considering the inherently heterogeneously complete mass movement information. Based on a preliminary data analysis, eight critical factors influencing mass movements were selected as basis predictors: the slope, aspect, profile curvature, plan curvature, road density, river density, soil moisture, and lithology. Two additional factors, namely, the land use and geological environment division, representing the inventory bias were selected as random intercepts. Subsequently, three mixed-effects models—Statistical-based generalized linear mixed-effects model (GLMM), generalized additive mixed-effects model (GAMM), and machine learning-based tree-boosted mixed-effects model (TBMM)—were adopted. These models were used to evaluate the susceptibility of three distinct types of mass movements (i.e., 28,814 debris flows, 54,586 rockfalls and 108,432 landslides), respectively. The results were compared both from quantitative and qualitative perspectives. The results showed that TBMM performed best in all three cases with AUROCs (Area Under the Receiver Operating Characteristic curve) of cross-validation, spatial cross-validation, and predictions on simulated highly biased inventory, all exceeding 0.8. In addition, the spatial prediction patterns of TBMM were more in line with the natural geomorphological underlying process, indicating that TBMM can better reduce the impact of inventory bias than GLMM and GAMM. Finally, factor contribution analysis showed the key role of topographic factors in predicting the occurrence of mass movements, followed by road density and soil moisture. This study contributes to assessing China’s overall mass movement susceptibility situation and assisting policymakers in master planning for risk mitigation. Further, it demonstrates the tremendous potential of TBMM for mass movement susceptibility assessment, despite inherent biases in the inventory.

Abstract Background Body posture is a fundamental indicator for assessing health and quality of life, especially for elderly people. Deciphering the changes in body posture occurring with age is a current topic in the field of geriatrics. The aims of this study were to assess the parameters of standing body posture in the global sagittal plane and to determine the dynamics of changes in standing body posture occurring with age and differences between men and women. Methods The measurements were performed on 226 individuals between the ages of 20 to 89 with a new photogrammetry, via which we assessed five postural angles - neck, thorax, waist, hip and knee. The data were analyzed with t-test, one-way ANOVA, linear regression model and generalized additive model. Results Among these segments studied here, neck changed most, while the middle segments of the body, waist and hip, were relative stable. Significant differences between men and women were found with respect to the angles of neck, thorax and hip. Three of the five postural angles were significantly influenced with aging, including increasing cervical lordosis, thoracic kyphosis and knee flexion, starting from no older than around 50 yrs. showed by fitting curve derived with generalized additive model. These changes were more marked among women. Besides, this study highlights the effects of age and gender on the complex interrelation between adjacent body segments in standing. Conclusions The presented results showed changes in the parameters describing body posture throughout consecutive ages and emphasized that for an individualized functional analysis, it is essential to consider age-and gender-specific changes in the neck, thorax and knee. This paper presents useful externally generalizable information not only for clinical purposes but also to inform further research on larger numbers of subjects.

The widely distributed “Step-type” landslides in the Three Gorges Reservoir (TGR) area have caused serious casualties and heavy economic losses. The prediction research of landslide displacement will be beneficial to the establishment of local geological hazard early warning systems for the realization of scientific disaster prevention and mitigation. However, the number of observed data like landslide displacement, rainfall, and reservoir water level in this area is very small, which results in difficulties for the training of advanced deep learning model to obtain more accurate prediction results. To solve the above problems, a Two-stage Combined Deep Learning Dynamic Prediction Model (TC-DLDPM) for predicting the typical “Step-type” landslides in the TGR area under the condition of small samples is proposed. The establishment process of this method is as follows: (1) the Dynamic Time warping (DTW) method is used to enhance the small samples of cumulative displacement data obtained by the Global Positioning System (GPS); (2) A Difference Decomposition Method (DDM) based on sequence difference is proposed, which decomposes the cumulative displacement into trend displacement and periodic displacement, and then the cubic polynomial fitting method is used to predict the trend displacement; (3) the periodic displacement component is predicted by the proposed TC-DLDPM model combined with external environmental factors such as rainfall and reservoir water level. The TC-DLDPM model combines the advantages of Convolutional Neural Network (CNN), Attention mechanism, and Long Short-term Memory network (LSTM) to carry out two-stage learning and parameter transfer, which can effectively realize the construction of a deep learning model for high-precision under the condition of small samples. A variety of advanced prediction models are compared with the TC-DLDPM model, and it is verified that the proposed method can accurately predict landslide displacement, especially in the case of drastic changes in external factors. The TC-DLDPM model can capture the spatio-temporal characteristics and dynamic evolution characteristics of landslide displacement, reduce the complexity of the model, and the number of model training calculations. Therefore, it provides a better solution and exploration idea for the prediction of landslide displacement under the condition of small samples.

The application of remote sensing technology in grassland monitoring and management has been ongoing for decades. Compared with traditional ground measurements, remote sensing technology has the overall advantage of convenience, efficiency, and cost effectiveness, especially over large areas. This paper provides a comprehensive review of the latest remote sensing estimation methods for some critical grassland parameters, including above-ground biomass, primary productivity, fractional vegetation cover, and leaf area index. Then, the applications of remote sensing monitoring are also reviewed from the perspective of their use of these parameters and other remote sensing data. In detail, grassland degradation and grassland use monitoring are evaluated. In addition, disaster monitoring and carbon cycle monitoring are also included. Overall, most studies have used empirical models and statistical regression models, while the number of machine learning approaches has an increasing trend. In addition, some specialized methods, such as the light use efficiency approaches for primary productivity and the mixed pixel decomposition methods for vegetation coverage, have been widely used and improved. However, all the above methods have certain limitations. For future work, it is recommended that most applications should adopt the advanced estimation methods rather than simple statistical regression models. In particular, the potential of deep learning in processing high-dimensional data and fitting non-linear relationships should be further explored. Meanwhile, it is also important to explore the potential of some new vegetation indices based on the spectral characteristics of the specific grassland under study. Finally, the fusion of multi-source images should also be considered to address the deficiencies in information and resolution of remote sensing images acquired by a single sensor or satellite.

Due to the large quantity of noise and complex spatial background of the remote sensing images, how to improve the accuracy of semantic segmentation has become a hot topic. Lake water body extraction is crucial for disaster detection, resource utilization, and carbon cycle, etc. The the area of lakes on the Tibetan Plateau has been constantly changing due to the movement of the Earth’s crust. Most of the convolutional neural networks used for remote sensing images are based on single-layer features for pixel classification while ignoring the correlation of such features in different layers. In this paper, the two-branch encoder is presented, which is a multiscale structure that combines the features of ResNet-34 with a feature pyramid network. Secondly, adaptive weights are distributed to global information using the hybrid-scale attention block. Finally, PixelShuffle is used to recover the feature maps’ resolution, and the densely connected block is used to refine the boundary of the lake water body. Likewise, we transfer the best weights which are saved on the Google dataset to the Landsat-8 dataset to ensure that our proposed method is robust. We validate the superiority of Hybrid-scale Attention Network (HA-Net) on two given datasets, which were created by us using Google and Landsat-8 remote sensing images. (1) On the Google dataset, HA-Net achieves the best performance of all five evaluation metrics with a Mean Intersection over Union (MIoU) of 97.38%, which improves by 1.04% compared with DeepLab V3+, and reduces the training time by about 100 s per epoch. Moreover, the overall accuracy (OA), Recall, True Water Rate (TWR), and False Water Rate (FWR) of HA-Net are 98.88%, 98.03%, 98.24%, and 1.76% respectively. (2) On the Landsat-8 dataset, HA-Net achieves the best overall accuracy and the True Water Rate (TWR) improvement of 2.93% compared to Pre_PSPNet, which proves to be more robust than other advanced models.

Accurate simulation of snow cover process is of great significance to the study of climate change and the water cycle. In our study, the China Meteorological Forcing Dataset (CMFD) and ERA-Interim were used as driving data to simulate the dynamic changes in snow depth and snow water equivalent (SWE) in the Irtysh River Basin from 2000 to 2018 using the Noah-MP land surface model, and the simulation results were compared with the gridded dataset of snow depth at Chinese meteorological stations (GDSD), the long-term series of daily snow depth dataset in China (LSD), and China’s daily snow depth and snow water equivalent products (CSS). Before the simulation, we compared the combinations of four parameterizations schemes of Noah-MP model at the Kuwei site. The results show that the rainfall and snowfall (SNF) scheme mainly affects the snow accumulation process, while the surface layer drag coefficient (SFC), snow/soil temperature time (STC), and snow surface albedo (ALB) schemes mainly affect the melting process. The effect of STC on the simulation results was much higher than the other three schemes; when STC uses a fully implicit scheme, the error of simulated snow depth and snow water equivalent is much greater than that of a semi-implicit scheme. At the basin scale, the accuracy of snow depth modeled by using CMFD and ERA-Interim is higher than LSD and CSS snow depth based on microwave remote sensing. In years with high snow cover, LSD and CSS snow depth data are seriously underestimated. According to the results of model simulation, it is concluded that the snow depth and snow water equivalent in the north of the basin are higher than those in the south. The average snow depth, snow water equivalent, snow days, and the start time of snow accumulation (STSA) in the basin did not change significantly during the study period, but the end time of snow melting was significantly advanced.

Land degradation and development (LDD) has become an urgent global issue. Quick and accurate monitoring of LDD dynamics is key to the sustainability of land resources. By integrating normalized difference vegetation index (NDVI) and net primary productivity (NPP) based on the Euclidean distance method, a LDD index (LDDI) was introduced to detect LDD processes, and to explore its quantitative relationship with climate change and human activity in China from 1985 to 2015. Overall, China has experienced significant land development, about 45% of China’s mainland, during the study period. Climate change (temperature and precipitation) played limited roles in the affected LDD, while human activity was the dominant driving force. Specifically, LDD caused by human activity accounted for about 58% of the total, while LDD caused by climate change only accounted for 0.34% of the total area. Results from the present study can provide insight into LDD processes and their driving factors and promote land sustainability in China and around the world.

Xinjiang is located in an arid and semi-arid climate region in China, but Xinjiang Ili river valley is more humid, with higher precipitation intensity and precipitation, which is closely related to the role of the Tianshan Mountains. In this paper, through the NCRP 1° × 1° reanalysis data and the conventional observation data of the Ili River Valley in Xinjiang, the terrain sensitivity experiment conducted by the WRF model is used to analyze the short-term extreme precipitation event of the Ili River Valley from 18–19 of May 2017, to reveal the influence of Tianshan Mountains on the extreme precipitation event of the Ili River Valley. The results show that: (1) The reduction or removal of the terrain will cause a wide range of wind field changes, weaken the vertical upward movement of the windward slope, and the accumulation of water vapor before the windward slope will also be reduced; a large-scale change of the terrain will also affect the direction of water vapor transportation. These effects together lead to a decrease or increase in regional precipitation. (2) “Fuzzy” (smooth) terrain will affect the precipitation simulated by changing the local vertical movement and water vapor transport, which shows that the WRF model’s accurate description of the terrain structure characteristics of mountainous areas is beneficial to accurately simulate the precipitation process on the windward slope area.

Cloud computing satisfies the requirement for large volumes of storage and computing resources to simulate land surface models (LSMs). Thus, the Science Cloud of the Chinese Academy of Sciences, which is based on a data cloud and high performance computing cloud, was adopted to support the simulation of LSMs. In this paper, we take advantage of the software and hardware resources of the Science Cloud to establish a prototype system for LSM applications. First, pre-processing and post-processing are crucial components of LSMs, so we specifically designed a freely available integrated software package called “PPLSMS”(for the pre- and post-processing of LSMs) with different scripting languages and data sets, which can be built on the cloud computing platform. Second, we developed a dedicated Web portal for LSMs based on the cloud computing platform with the representational state transfer application programming interface, which allows the operation of functions, such as parameter and data selection, model configuration, as well as customization of the output, statistics and visualization via a Web browser. Finally, some basic steps were presented to operate the Web portal for LSM applications. The system integrated data sets and approaches may serve as a practical means to facilitate the simulation of LSMs.

Lake water body extraction from remote sensing images is a key technique for spatial geographic analysis. It plays an important role in the prevention of natural disasters, resource utilization, and water quality monitoring. Inspired by the recent years of research in computer vision on fully convolutional neural networks (FCN), an end-to-end trainable model named the multi-scale lake water extraction network (MSLWENet) is proposed. We use ResNet-101 with depthwise separable convolution as an encoder to obtain the high-level feature information of the input image and design a multi-scale densely connected module to expand the receptive field of feature points by different dilation rates without increasing the computation. In the decoder, the residual convolution is used to abstract the features and fuse the features at different levels, which can obtain the final lake water body extraction map. Through visual interpretation of the experimental results and the calculation of the evaluation indicators, we can see that our model extracts the water bodies of small lakes well and solves the problem of large intra-class variance and small inter-class variance in the lakes’ water bodies. The overall accuracy of our model is up to 98.53% based on the evaluation indicators. Experimental results demonstrate that the MSLWENet, which benefits from the convolutional neural network, is an excellent lake water body extraction network.

Land surface temperature (LST) is a critical state variable of land surface energy equilibrium and a key indicator of environmental change such as climate change, urban heat island, and freezing-thawing hazard. The high spatial and temporal resolution datasets are urgently needed for a variety of environmental change studies, especially in remote areas with few LST observation stations. MODIS and Landsat satellites have complementary characteristics in terms of spatial and temporal resolution for LST retrieval. To make full use of their respective advantages, this paper developed a pixel-based multi-spatial resolution adaptive fusion modeling framework (called pMSRAFM). As an instance of this framework, the data fusion model for joint retrieval of LST from Landsat-8 and MODIS data was implemented to generate the synthetic LST with Landsat-like spatial resolution and MODIS temporal information. The performance of pMSRAFM was tested and validated in the Heihe River Basin located in China. The results of six experiments showed that the fused LST was high similarity to the direct Landsat-derived LST with structural similarity index (SSIM) of 0.83 and the index of agreement (d) of 0.84. The range of SSIM was 0.65–0.88, the root mean square error (RMSE) yielded a range of 1.6–3.4 °C, and the averaged bias was 0.6 °C. Furthermore, the temporal information of MODIS LST was retained and optimized in the synthetic LST. The RMSE ranged from 0.7 °C to 1.5 °C with an average value of 1.1 °C. When compared with in situ LST observations, the mean absolute error and bias were reduced after fusion with the mean absolute bias of 1.3 °C. The validation results that fused LST possesses the spatial pattern of Landsat-derived LSTs and inherits most of the temporal properties of MODIS LSTs at the same time, so it can provide more accurate and credible information. Consequently, pMSRAFM can be served as a promising and practical fusion framework to prepare a high-quality LST spatiotemporal dataset for various applications in environment studies.

Plants are ubiquitous in human life. Recognizing an unknown plant by its leaf image quickly is a very interesting and challenging research. With the development of image processing and pattern recognition, plant recognition based on image processing has become possible. Bag of features (BOF) is one of the most powerful models for classification, which has been used for many projects and studies. Dual-output pulse-coupled neural network (DPCNN) has shown a good ability for texture features in image processing such as image segmentation. In this paper, a method based on BOF and DPCNN (BOF_DP) is proposed for leaf classification. BOF_DP achieved satisfactory results in many leaf image datasets. As it is hard to get a satisfactory effect on the large dataset by a single feature, a method (BOF_SC) improved from bag of contour fragments is used for shape feature extraction. BOF_DP and LDA (linear discriminant analysis) algorithms are, respectively, employed for textual feature extraction and reducing the feature dimensionality. Finally, both features are used for classification by a linear support vector machine (SVM), and the proposed method obtained higher accuracy on several typical leaf datasets than existing methods.

Soil temperature (ST) plays a key role in the processes and functions of almost all ecosystems, and is also an essential parameter for various applications such as agricultural production, geothermal development, and their utilization. Although numerous machine learning models have been used in the prediction of ST, and good results have been obtained, most of the current studies have focused on daily or monthly ST predictions, while hourly ST predictions are scarce. This paper presents a novel scheme for forecasting the hourly ST using weather forecast data. The method considers the hourly ST prediction to be the superposition of two parts, namely, the daily average ST prediction and the ST amplitude (the difference between the hourly ST and the daily average ST) prediction. According to the results of correlation analysis, we selected nine meteorological parameters and combined two temporal parameters as the input vectors for predicting the daily average ST. For the task of predicting the ST amplitude, seven meteorological parameters and one temporal parameter were selected as the inputs. Two submodels were constructed using a deep bidirectional long short-term memory network (BiLSTM). For the task of hourly ST prediction at five different soil depths at 30 sites, which are located in 5 common climates in the United States, the results showed the method proposed in this paper performs best at all depths for 30 stations (100% of all) for the root mean square error (RMSE), 27 stations (90% of all) for the mean absolute error (MAE), and 30 stations (100% of all) for the coefficient of determination (R2), respectively. Moreover, the method adopted in this study displays a stronger ST prediction ability than the traditional methods under all climate types involved in the experiment, the hourly ST produced by it can be used as a driving parameter for high-resolution biogeochemical models, land surface models and hydrological models and can provide ideas for an analysis of other time series data.

We propose a fast document image thresholding method (FADIT) and evaluations of the two classic methods for demonstrating the effectiveness of FADIT. We put forward two assumptions: (1) the probability of the occurrence of grayscale text and background is ideally two constants, and (2) a pixel with a low grayscale has a high probability of being classified as text and a pixel with a high grayscale has a high probability of being classified as background. With the two assumptions, a new criterion function is applied to document image thresholding in the Bayesian framework. The effectiveness of the method has been borne of a quantitative metric as well as qualitative comparisons with the state-of-the-art methods.

To solve the messy problem of data types and form a unified data-processing solution, data in the Heihe River Basin were first classified into five types to integrate them and achieve unified management of data and metadata, preventing the loss of metadata, in the data model of eScience framework. Considering many of the challenges that exist in the construction of the online spatial-temporal data integration and interoperability eScience platform, we used the open data interfaces and standards such as the Common DataModel (CDM) interface, common scientific data modelling (i.e., NetCDF, GRIB, and HDF), and Open Geospatial Consortium (OGC) standards. Through the eScience platform, we also provided online data processing tools by collecting free tools (e.g., NetCDF tool, quality control tool). This eScience platform enables researchers to make full use of scientific research information and results and facilitates collaboration, especially between the GIS community and other members of the earth science community, with the purpose of establishing an online platform of uniform spatial data from the Heihe River Basin via common scientific data modelling.

Most previous studies of the Qinghai-Tibet engineering corridor (QTEC) have focused on the impacts of climate change on thaw-induced slope failures, whereas few have considered freeze-induced slope failures. Terrestrial laser scanning was used in combination with global navigation satellite systems to monitor three-dimensional surface changes between 2014 and 2015 on the slope of permafrost in the QTEC, which experienced two thawing periods and a freezing period. Soil temperature and moisture sensors were also deployed at 11 depths to reveal the hydrological–thermal dynamics of the active layer. We analyzed scanned surface changes in the slope based on comparisons of multi-temporal point cloud data to determine how the hydrological–thermal process affected active layer deformation during freeze–thaw cycles, thereby comprehensively quantifying the surface deformation. During the two thawing periods, the major structure of the slope exhibited subsidence trends, whereas the major structure of the slope had an uplift trend in the freezing period. The seasonal subsidence trend was caused by thaw settlement and the seasonal uplift trend was probably due to frost heaving. This occurred mainly because the active layer and the upper permafrost underwent a phase transition due to heat transfer. The ground movements occurred approximately in the soil temperature conduction direction between the top of the soil and the permafrost table. The elevation deformation range was mainly −0.20 m to 0.20 m. Surface volume increases with heaving after freezing could have compensated for the loss of thawing twice and still led to the upward swelling of the slope. Thus, this type of slope in permafrost is dominated by frost heave. Deformation characteristics of the slope will support enhanced decision making regarding the implementation of remote sensing and hydrological–thermal measurement technologies to monitor changes in the slopes in permafrost adjacent to engineering corridors, thereby improving the understanding and assessment of hazards.

Merging satellite and rain gauge data by combining accurate quantitative rainfall from stations with spatial continuous information from remote sensing observations provides a practical method of estimating rainfall. However, generating high spatiotemporal rainfall fields for catchment-distributed hydrological modeling is a problem when only a sparse rain gauge network and coarse spatial resolution of satellite data are available. The objective of the study is to present a satellite and rain gauge data-merging framework adapting for coarse resolution and data-sparse designs. In the framework, a statistical spatial downscaling method based on the relationships among precipitation, topographical features, and weather conditions was used to downscale the 0.25° daily rainfall field derived from the Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis (TMPA) precipitation product version 7. The nonparametric merging technique of double kernel smoothing, adapting for data-sparse design, was combined with the global optimization method of shuffled complex evolution, to merge the downscaled TRMM and gauged rainfall with minimum cross-validation error. An indicator field representing the presence and absence of rainfall was generated using the indicator kriging technique and applied to the previously merged result to consider the spatial intermittency of daily rainfall. The framework was applied to estimate daily precipitation at a 1 km resolution in the Qinghai Lake Basin, a data-scarce area in the northeast of the Qinghai-Tibet Plateau. The final estimates not only captured the spatial pattern of daily and annual precipitation with a relatively small estimation error, but also performed very well in stream flow simulation when applied to force the geomorphology-based hydrological model (GBHM). The proposed framework thus appears feasible for rainfall estimation at high spatiotemporal resolution in data-scarce areas.

The autumn migration routes of bar-headed geese captured before the 2008 breeding season at Qinghai Lake, China, were documented using satellite tracking data. To assess how the migration strategies of bar-headed geese are influenced by environmental conditions, the relationship between migratory routes, temperatures, and vegetation coverage at stopovers sites estimated with the Normalized Difference Vegetation Index (NDVI) were analyzed. Our results showed that there were four typical migration routes in autumn with variation in timing among individuals in start and end times and in total migration and stopover duration. The observed variation may be related to habitat type and other environmental conditions along the routes. On average, these birds traveled about 1300 to 1500 km, refueled at three to six stopover sites and migrated for 73 to 83 days. The majority of the habitat types at stopover sites were lake, marsh, and shoal wetlands, with use of some mountainous regions, and farmland areas.