Search

High-resolution remote sensing image segmentation has advanced significantly with 2-D convolutional neural networks and transformer-based models like SegFormer and Swin Transformer. Concurrently, the rapid development of 3-D convolution techniques has driven advancements in methods like PointNet and Kernel Point Convolution for 3-D LiDAR point cloud segmentation. Traditional fusion of aerial imagery and LiDAR data often relies on digital surface models or other features extracted from LiDAR point clouds, incorporating them as depth channels into image data. In this article, we propose a novel approach called Direct LiDAR-Aerial Fusion Network, which directly integrates multispectral images (RGB) and LiDAR point cloud data for semantic segmentation. Experiments on the modified GRSS18 dataset demonstrate that our method achieves an overall accuracy (OA) of 79.88%, outperforming conventional approaches. By fusing RGB and LiDAR features, our technique improves OA by 1.77% and mean Intersection over Union by 0.83%.

Single-image superresolution (SISR) of remote sensing images aims to improve image resolution through algorithmic means while restoring rich high-frequency detailed information. Previously, convolutional neural network (CNN) achieves impressive progress in SISR due to its strong local feature extraction capability. However, the CNN is difficult to model long-range dependencies, which limits the performance of SISR. Transformer has a greater advantage over the CNN in long-range dependence modeling. Moreover, remote sensing elements typically exhibit multiscale characteristics and maintain strong coupling relationships with the surrounding environment. Paying attention to multiscale local and global information can help further improve the performance of SISR. Existing methods encounter challenges in leveraging diverse feature sets within single architecture networks. In this article, we propose a multiscale CNN-Transformer feature fusion (MSCT) network for remote sensing SISR. MSCT is a hybrid structural network, which consists of the adaptive residual dense block (ARDB), the multiscale Transformer block (MSTB), and the local–global information enhancement block (LGEB). Among them, ARDB can extract abundant multiscale local features via dense connected convolutional layers and adaptive residual learning. MSTB generates multiscale tokens with multiple convolutional layers to obtain multiscale global information. LGEB further enhance the extraction of local–global information in spatial and frequency domain. Extensive experiments on multiple datasets show that MSCT achieves competitive results on RGB remote sensing imagery compared with other representative SISR methods. In addition, SR experiments on Sentinel-2 images show that MSCT has a certain generalization ability on multispectral images. Extended experiments also demonstrate that MSCT can effectively improve the performance of object detection.

Abstract Background Nicotinamide and tryptophan metabolism play important roles in regulating tumor synthesis metabolism and signal transduction functions. However, their comprehensive impact on the prognosis and the tumor immune microenvironment of glioma is still unclear. The purpose of this study was to investigate the association of nicotinamide and tryptophan metabolism with prognosis and immune status of gliomas and to develop relevant models for predicting prognosis and sensitivity to immunotherapy in gliomas. Methods Bulk and single-cell transcriptome data from TCGA, CGGA and GSE159416 were obtained for this study. Gliomas were classified based on nicotinamide and tryptophan metabolism, and PPI network associated with differentially expressed genes was established. The core genes were identified and the risk model was established by machine learning techniques, including univariate Cox regression and LASSO regression. Then the risk model was validated with data from the CGGA. Finally, the effects of genes in the risk model on the biological behavior of gliomas were verified by in vitro experiments. Results The high nicotinamide and tryptophan metabolism is associated with poor prognosis and high levels of immune cell infiltration in glioma. Seven of the core genes related to nicotinamide and tryptophan metabolism were used to construct a risk model, and the model has good predictive ability for prognosis, immune microenvironment, and response to immune checkpoint therapy of glioma. We also confirmed that high expression of TGFBI can lead to an increased level of migration, invasion, and EMT of glioma cells, and the aforementioned effect of TGFBI can be reduced by FAK inhibitor PF-573,228. Conclusions Our study evaluated the effects of nicotinamide and tryptophan metabolism on the prognosis and tumor immune microenvironment of glioma, which can help predict the prognosis and sensitivity to immunotherapy of glioma.

Wind erosion from farmland is a significant contributor to atmospheric particulate matter, particularly PM10 (atmospheric particulate matter with an aerodynamic diameter ≤ 10 μm), in regions with intensive agricultural activities such as the North China Plain (NCP). However, the specific impact of farmland dust emissions on regional air quality remains underexplored. This study integrated the Wind Erosion Prediction System (WEPS) model with the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem) to investigate the effect of agricultural dust emissions on PM10 concentrations in the NCP. Results indicated that wind erosion from agricultural fields in the NCP produced approximately 33.8 × 105 tons of PM10 annually. These emissions are predominantly concentrated during the winter months from October to next April, with the highest emissions occurring in Hebei, Henan, and Shandong provinces. Using scenario experiments with the WRF-Chem model, we further quantified the contribution of agricultural dust emissions to atmospheric PM10 concentrations. The findings revealed that farmland emissions contributed approximately 13% of atmospheric PM10 concentrations during winter months (January and December), underscoring the significant role of agricultural activities in regional air pollution. This study highlights the importance of including farmland wind erosion into chemical transport models to more accurately understand and mitigate the effects of agricultural activities on atmospheric pollution in agricultural regions worldwide.

Understanding the underlying mechanism driving ecosystem service relationships is crucial for developing successful urban planning and management policies. There is still a lack of understanding of the driving factors behind ecosystem service relationships, particularly in terms of long-term assessments of their spatial–temporal patterns and researches on the driving effects and thresholds of the driving factors. This study utilized various analytical methods including the InVEST 3.13.0 model, optimal parameter geographic detector, and bayesian belief network to assess ecosystem serviecs and explore their relationships. Moreover, the study identified the crucial driving factors and their effects to the spatiotemporal variation in ecosystem service relationships in the Wuhu city between 1990 and 2020.The results showed that: (1) The distribution of high-value areas for the three ecosystem services in Wuhu City has remained relatively stable over time. High-value areas for food production services are primarily located in traditional polder fields, flood mitigation services are concentrated in the plains in the north of the city, and habitat quality services are situated in the hills in the south. However, with the expansion of the city, there is a risk of further degradation of the three services. (2) Spatial-temporal changes in ecosystem service relationships were regular, and long-term assessments of ecosystem services and their relationships were important. (3) The biophysical factors exerted the most significant influence on the Spatial-temporal patterns of ecosystem service relationships. (4) The combined effect of two driving factors was greater than that of a single factor. (5)There was a threshold of drivers that promotes synergy of ecosystem services. (6) Multiple ecosystem services might exhibit synergy relationships within the threshold of the same driver. The findings from this study could provide urban managers with valuable insights into the ecosystem services relationships.

Primary tinnitus is a disabling disease with an unknown pathogenesis and a high incidence rate in China. Its diagnosis and treatment are complex and difficult to control. Although many treatments are available for primary tinnitus, their efficacy is often unsatisfactory. This paper proposes a new diagnosis and treatment method using knowledge graphs, and an intelligent assistant decision system is developed. To support diagnosis, a knowledge graph is created as a decision support tool using traditional Chinese medicine (TCM). Based on the knowledge graph, a model for the syndrome differentiation of tinnitus in TCM is built. At tinnitus treatment, an intelligent recommandation model for pentatonic music using knowledge graph based heterogeneous label propagation is then used to provide patients with personalized treatment plans. According to evaluation results, the proposed method achieves an accuracy of 87.1 % in tinnitus diagnosis. Compared with the control group, the recommended pentatonic music had a more obvious effect, and the efficacy of the five types of tinnitus was increased by 33.34 %, 33.33 %, 20 %, 26.67 %, 33.34 %, respectively. The system developed in this paper will help clinicians improve the diagnosis and treatment of tinnitus while reducing unnecessary medical expenses and offering significant social and economic benefits.

Objective The goal of the present research was to evaluate the effectiveness of physical exercise intervention in enhancing psychological well-being and decreasing symptoms of depression among college students, adopting a systematic review and meta-analysis. Methodology The study was performed by searching four databases (PubMed, Embase, Web of Science, and the Cochrane Library) to determine randomized controlled trials (RCTs) exploring the impacts of physical exercise therapies among college students with symptoms of depression. The sequential execution of a meta-analyses, subgroup analyses, and publication bias analyses was accomplished utilizing the software package RevMan version 5.3. Results There were eight articles included. This research demonstrated a significant impact (d = −0.75, P < 0.05), indicating that physical exercise has a substantial impact on decreasing or mitigating depression. The subgroup analyses revealed that interventions involving physical exercise workouts lasting 12 weeks or longer (d = −0.93, P < 0.05), with physical exercise sessions lasting between 30 and 60 min (d = −0.77, P < 0.05), and with physical exercise performed minimum of three times a week (d = −0.90, P < 0.05) were the most effective in reducing symptoms of depression. Conclusion Physical exercise interventions have a beneficial impact on reducing depression among college students. The optimal mode was discovered to be college students participating in each session for a duration of 30 to 60 min, at least three times per week, and for more than 12 weeks. College students are encouraged to cultivate a consistent and long-term physical exercise routine to sustain their physical and mental health.

BackgroundThe gut microbiota (GM) has been implicated in neurological disorders, but the relationship with hydrocephalus, especially the underlying mechanistic pathways, is unclear. Using Mendelian randomization (MR), we aim to discover the mediating role of inflammatory factors in the relationship between GM and hydrocephalus.MethodsAfter removing confounders, univariable and multivariable MR analyses were performed using summary statistics to assess the causal relationships between GM, inflammatory factors (IL-17A and IL-27), and types of hydrocephalus. Meta-analyses were used to reconcile the differences in MR results between different hydrocephalus sources. Finally, mediator MR analyses were applied to determine the mediating effect of inflammatory factors. Various sensitivity analysis methods were employed to ensure the reliability and stability of the results.ResultsAfter correction for P-values, Firmicutes (phylum) (OR, 0.34; 95%CI, 0.17–0.69; P = 2.71E-03, PFDR = 2.44E-02) significantly reduced the risk of obstructive hydrocephalus. The remaining 18 different taxa of GM had potential causal relationships for different types of hydrocephalus. In addition, Firmicutes (phylum) decreased the risk of obstructive hydrocephalus by increasing levels of IL-17A (mediating effect = 21.01%), while Eubacterium ruminantium group (genus) increased the risk of normal-pressure hydrocephalus by decreasing levels of IL-27 (mediating effect = 7.48%).ConclusionWe reveal the connection between GM, inflammatory factors (IL-17A and IL-27), and hydrocephalus, which lays the foundation for unraveling the mechanism between GM and hydrocephalus.

BackgroundTinnitus diagnosis poses a challenge in otolaryngology owing to an extremely complex pathogenesis, lack of effective objectification methods, and factor-affected diagnosis. There is currently a lack of explainable auxiliary diagnostic tools for tinnitus in clinical practice. ObjectiveThis study aims to develop a diagnostic model using an explainable artificial intelligence (AI) method to address the issue of low accuracy in tinnitus diagnosis. MethodsIn this study, a knowledge graph–based tinnitus diagnostic method was developed by combining clinical medical knowledge with electronic medical records. Electronic medical record data from 1267 patients were integrated with traditional Chinese clinical medical knowledge to construct a tinnitus knowledge graph. Subsequently, weights were introduced, which measured patient similarity in the knowledge graph based on mutual information values. Finally, a collaborative neighbor algorithm was proposed, which scored patient similarity to obtain the recommended diagnosis. We conducted 2 group experiments and 1 case derivation to explore the effectiveness of our models and compared the models with state-of-the-art graph algorithms and other explainable machine learning models. ResultsThe experimental results indicate that the method achieved 99.4% accuracy, 98.5% sensitivity, 99.6% specificity, 98.7% precision, 98.6% F1-score, and 99% area under the receiver operating characteristic curve for the inference of 5 tinnitus subtypes among 253 test patients. Additionally, it demonstrated good interpretability. The topological structure of knowledge graphs provides transparency that can explain the reasons for the similarity between patients. ConclusionsThis method provides doctors with a reliable and explainable diagnostic tool that is expected to improve tinnitus diagnosis accuracy.

The emergence of semisupervised object detection (SSOD) techniques has greatly enhanced object detection performance. SSOD leverages a limited amount of labeled data along with a large quantity of unlabeled data. However, there exists a problem of sample inconsistency in remote sensing images, which manifests in two ways. First, remote sensing images are diverse and complex. Conventional random initialization methods for labeled data are insufficient for training teacher networks to generate high-quality pseudolabels. Finally, remote sensing images typically exhibit a long-tailed distribution, where some categories have a significant number of instances, while others have very few. This distribution poses significant challenges during model training. In this article, we propose the utilization of SSOD networks for remote sensing images characterized by a long-tailed distribution. To address the issue of sample inconsistency between labeled and unlabeled data, we employ a labeled data iterative selection strategy based on the active learning approach. We iteratively filter out high-value samples through the designed selection criteria. The selected samples are labeled and used as data for supervised training. This method filters out valuable labeled data, thereby improving the quality of pseudolabels. Inspired by transfer learning, we decouple the model training into the training of the backbone and the detector. We tackle the problem of sample inconsistency in long-tail distribution data by training the detector using balanced data across categories. Our approach exhibits an approximate 1% improvement over the current state-of-the-art models on both the DOTAv1.0 and DIOR datasets.

In recent years, there has been significant research focus on topological states in two-dimensional materials, particularly those exhibiting intrinsic magnetic orderings. In this study, we employ theoretical calculations to uncover the remarkable band topology of monolayer V2Cl3Br3. This two-dimensional compound not only possesses a half-metallic ferromagnetic ground state but also demonstrates exceptional thermodynamic and mechanical stabilities. Notably, we observe clean band crossings with complete spin polarization, which manifest as phase transitions between Weyl semimetal states and quantum anomalous Hall states under different magnetization directions. Both of these topological phases exhibit pronounced edge states. Furthermore, utilizing Monte Carlo simulations with the Heisenberg model, we estimate a high Curie temperature of up to 79.2 K, indicating its potential for spintronic development. Additionally, we analyze the mechanical properties of the material, emphasizing its isotropic mechanical behavior, which offers advantageous features for practical applications. These findings establish the foundation for further exploration of practical applications involving two-dimensional ferromagnetic topological states. Importantly, the identified material candidate can be readily incorporated into experimental preparation, thus accelerating progress in topological quantum applications and the development of half-metallic spintronic devices.

Abstract In this study, we simulated the spatial and temporal processes of a particulate matter (PM) pollution episode from December 10–29, 2019, in Zhengzhou, the provincial capital of Henan, China, which has a large population and severe PM pollution. As winter is the high incidence period of particulate pollution, winter statistical data were selected from the pollutant observation stations in the study area. During this period, the highest concentrations of PM2.5 (atmospheric PM with a diameter of less than 2.5 µm) and PM10 (atmospheric PM with a diameter of less than 10 µm) peaked at 283 μg m-3 and 316 μg m-3, respectively. The contribution rates of local and surrounding regional emissions within Henan (emissions from the regions to the south, northwest, and northeast of Zhengzhou) to PM concentrations in Zhengzhou were quantitatively analyzed based on the regional Weather Research and Forecasting model coupled with Chemistry (WRF/Chem). Model evaluation showed that the WRF/Chem can accurately simulate the spatial and temporal variations in the PM concentrations in Zhengzhou. We found that the anthropogenic emissions south of Zhengzhou were the main causes of high PM concentrations during the studied episode, with contribution rates of 14.39% and 16.34% to PM2.5 and PM10, respectively. The contributions of anthropogenic emissions from Zhengzhou to the PM2.5 and PM10 concentrations in Zhengzhou were 7.94% and 7.29%, respectively. The contributions of anthropogenic emissions from the area northeast of Zhengzhou to the PM2.5 and PM10 concentrations in Zhengzhou were 7.42% and 7.18%, respectively. These two areas had similar contributions to PM pollution in Zhengzhou. The area northeast of Zhengzhou had the lowest contributions to the PM2.5 and PM10 concentrations in Zhengzhou (5.96% and 5.40%, respectively).

Red raspberry (Rubus idaeus L.), which is an important nutritional source for human health, belongs to fruit crops of the Rosaceae family. Here, we used Pacific Biosciences single-molecule real-time (SMRT) sequencing and high-throughput chromosome conformation capture (Hi-C) sequencing technologies to assemble genomes and reported a high-quality Rubus idaeus L. (DNS-1) genome with 321.29 Mb assembled into seven chromosomes. The LAI score of the DNS-1 genome assembly was 21.32, belonging to gold quality. Approximately 52.3% of the assembly sequences were annotated as repetitive sequences, and 24.15% were composed of long terminal repeat elements. A total of 29,814 protein-coding genes and 2474 pseudogenes were predicted in DNS-1. We characterized the complete genomes of DNS-1 and compared them to those of seven other species. We found that 652 gene families were unique to DNS-1 and they were shaped from an ancestor. There were 1000 and 5193 gene families that expanded and contracted in the DNS-1 genome. The Rubus idaeus L. genome can be used to understand the structure and evolution of Rosaceae genomes and can be developed to identify genes controlling important traits and improve breeding work.

The phase space, as coded by kinematic parameters and chemical abundances, is crucial for understanding the formation of the Galactic disk. Using red giant stars from the Galactic thin disk with [Fe/H] > − 0.8 and low- α ratios identified in LAMOST-Gaia, we detect numerous ridges and undulations in the R – V _ϕ diagram coded by median V _R . Strikingly, the slope of these features changes from −22 km s ^−1 kpc ^−1 to −8 km s ^−1 kpc ^−1 at R ∼ 11.5 kpc. Accordingly, the R _g – V _ϕ plane, also coded by median V _R , reveals wave-like structures that propagate outwards in the inner disk but reverse direction and move inwards beyond R _g = 11.5 kpc. The most prominent feature is the G1 group, distinguished by its wider spread and negative median V _R at R _g ∼ 15 kpc, contrasting with the narrower G0 group that exhibits positive median V _R at R _g < 11.5 kpc. Furthermore, the [C/N] versus [Fe/H] relationship for the G1 group mirrors the opposite trend compared to the G0 group. Since [C/N] serves as a proxy for age, this contrasting behavior suggests an inverse age–metallicity relation for the G1 group. Comparison with the Sagittarius dwarf galaxy reveals that the G1 group possesses distinct [Mg/Fe] and [Al/Fe] ratios, yet its [C/N] versus [Fe/H] pattern is similar to that of the Sgr dwarf galaxy. Based on these observations, we proposed that the inward-moving and asymmetric velocity wave G1 might be linked to the minor merge of the Sagittarius galaxy.

Topological states in two-dimensional materials have garnered significant research attention in recent years, particularly those with intrinsic magnetic orderings, which hold great potential for spintronic applications. Through theoretical calculations, we unveil the superior band topology of monolayer vanadium trihalides, with a specific focus on V2Cl6. These two-dimensional compounds exhibit a half-metallic ferromagnetic ground state, showcasing excellent thermodynamic and mechanical stabilities. Remarkably, clean band crossings with complete spin polarization manifest as phase transitions between Weyl semimetal states and quantum anomalous Hall states under different magnetization directions, and both topological phases yield prominent edge states. Furthermore, Monte Carlo simulations estimate a high Curie temperature of up to 381.3 K, suggesting the potential for spintronic development above room temperature. Taking a step forward, we construct two heterojunctions utilizing selected substrates, MoS2 and h-BN. These substrates not only facilitate a suitable lattice integration but also have a negligible impact on the half-metallicity and band topology. These findings lay the groundwork for exploring practical applications of two-dimensional ferromagnetic topological states. Importantly, the presented material candidates have the potential to accelerate the development of room temperature applications and integrate spintronic devices.

Abstract Objective This study aimed to understand the demographics, clinical characteristics, and psychoacoustic status of subjective tinnitus patients to explore the factors associated with acute and chronic tinnitus in the general hospitals of Shanghai. Methods A cross‐sectional study was conducted to investigate the clinical characteristics and psychoacoustic status of subjective tinnitus patients with history greater than 1 month. Data were collected during January 2021 and January 2022 from eight general hospitals in five districts of Shanghai, China. All patients accepted questionnaires and acoustic examination, then SPSS 22.0 and GraphPad Prism 8.0.2 were applied for data analysis. Results Among the 359 tinnitus patients, 126 cases were diagnosed with acute tinnitus, 58 cases were subacute tinnitus, and 175 cases were chronic tinnitus. Patients with acute and chronic tinnitus differed in terms of side of tinnitus, hearing loss, frequency of tinnitus, severity of tinnitus, anxiety, depression, and sleep status. Different characteristics were included in the multivariate ordinal logistic regression analysis. Persistent tinnitus (OR = 2.00, p = .008), high frequency hearing loss (OR = 4.77, p

A lightweight image recognition model, L-GhostNet based on improved GhostNet, is proposed to address the problems of extensive computation and high storage cost of deep convolutional neural networks. The model incorporated learning group convolution and improved CA into GhostNet to reduce the calculation and number of parameters and improve the flexibility of the network. At the same time, the pruning ratio in the learning group convolution is increased to control the end time of pruning in the whole process; the improved CA uses a fully connected layer to replace the convolutional layer, which can make the connection between the two dimensions tighter and increase the flexibility of the model. Experiments on datasets in various fields, such as grape leaf recognition, gesture recognition, face recognition, rice recognition, and CIFAR-10, show that L-GhostNet has slightly improved accuracy, reduced computation by more than 44%, decreased the number of parameters by more than 33%, and improved FPS by 26% on all datasets compared to GhostNet. Compared with other commonly used lightweight network models, MobileNets and ShuffleNets, it has the best overall performance with the lowest FLOPs, highest accuracy, and fewer parameters on all datasets at the same level of FLOPs.

Weakly supervised object detection (WSOD) is an increasingly important task in remote sensing images. However, mainstream WSOD methods often rely on low-quality proposals due to the complex backgrounds of remote sensing images. Moreover, applying strong data augmentations directly in WSOD methods can introduce significant noise, which can hinder training procedures that rely only on image-level ground truth labels. To address these issues, we propose a dynamic informative proposal-based iterative WSOD training procedure. Specifically, we implement an informative proposal reconstruction (IPR) method to generate more informative proposals dynamically. We also use a proposal-based contrastive learning (PBCL) technique to steadily improve the quality of generated proposals. In addition, we employ a pseudolabel learning-based multistage (PLMS) training procedure to progressively improve the quality of new informative proposals while alleviating the noise catastrophe caused by strong data augmentations. Extensive experiments demonstrate the effectiveness of our proposed method in generating higher quality proposals and enhancing model generalization. Our method achieves state-of-the-art results in optical remote sensing images (DIOR), Northwestern Polytechnical University (NWPU) VHR-10.v2, and HRSC2016 datasets.

Abstract The utility of noncontrast computed tomography markers in the prognosis of spontaneous intracerebral hemorrhage has been studied. This study aimed to investigate the predictive value of the computed tomography (CT) irregularity shape for poor functional outcomes in patients with spontaneous intracerebral hemorrhage. We retrospectively reviewed all 782 patients with intracranial hemorrhage in our stroke emergency center from January 2018 to September 2019. Laboratory examination and CT examination were performed within 24 h of admission. After three months, the patient's functional outcome was assessed using the modified Rankin Scale. Multinomial logistic regression analyses were applied to identify independent predictors of functional outcome in patients with intracerebral hemorrhage. Out of the 627 patients included in this study, those with irregular shapes on CT imaging had a higher proportion of poor outcomes and mortality 90 days after discharge (P

The twin-spool rotor-bearing system plays a crucial role in the aero-engine. The potential manufacturing defect, assembly error, and abnormal working loads in the rotor-bearing system can induce multiple rotor failures, such as bolt looseness and rub impact. However, the prediction of the fault rotor dynamic behavior for the aero-engine remains a difficult frontier in numerical modeling. We present a dynamic model of the twin-spool rotor-bearing system, the failure model of bearing seat loosening, and the failure model of rub impact by using second-type Lagrangian equations, finite element theory, and the Timoshenko beam theory. In particular, to improve the accuracy of the numerical model, the rotating speed control equation and the actual aero-engine parameter are taken into account. An analysis is conducted on the impact of critical failure parameters, such as looseness stiffness and rub impact initial gap, on the vibration behaviors of the essential components of the twin-spool rotor system and on the entire engine. Additionally, this paper examines the twin-spool rotor-bearing system affected by looseness–rub coupled failures. The obtained conclusions can serve as a theoretical foundation for optimizing the structure and diagnosing faults in the aero-engine rotor system.

With developments in deep learning, semantic segmentation of remote sensing images has made great progress. Currently, mainstream methods are based on convolutional neural networks (CNNs) or vision transformers. However, these methods are not very effective in extracting features from remote sensing images, which are usually of high resolution with plenty of detail. Operations including downsampling will cause the loss of such features. To address this problem, we propose a novel module called Hierarchical Wavelet Feature Enhancement (WFE). The WFE module involves three sequential steps: (1) performing multi-scale decomposition of an input image based on the discrete wavelet transform; (2) enhancing the high-frequency sub-bands of the input image; and (3) feeding them back to the corresponding layers of the network. Our module can be easily integrated into various existing CNNs and transformers, and does not require additional pre-training. We conducted experiments on the ISPRS Potsdam and ISPRS Vaihingen datasets, with results showing that our method improves the benchmarks of CNNs and transformers while performing little additional computation.

Small target detection from the infrared remote sensing image is a challenge task. In this article, a novel local adaptive threshold algorithm combined with heterogeneity and compactness filters is proposed to detect the small target from the infrared remote sensing images. First, the infrared image is filtered by a heterogeneity filter to enhance the target saliency. Then, the enhanced image is filtered by a compactness filter to generate a target candidate region map. Finally, for each pixel in the target candidate region, a local adaptive threshold is calculated from the enhanced image to determine whether it is a target pixel or not, and thus, the targets are extracted out. The designed heterogeneity filter and compactness filter can effectively suppress the background clutter, enhance the target, and generate target candidate regions. The proposed adaptive thresholding is a local threshold method, which is calculated in a small local window and can effectively reduce the false alarm and missing alarm. Qualitative and quantitative experiments are conducted on synthetic images and real images. The experiment results show that, with good target enhancement and background suppression, and high detection accuracy, the proposed method outperforms other state-of-the-art methods.

To better understand the possible role of projected land use and cover change (LUCC) in future regional climate projections, we explored the regional climate change response from land use/cover change under different climate scenarios. To do so, we propose a research framework based on different SSP-RCPs to simulate and explore the impacts of future land use/cover changes on the future climate of Zhengzhou City, China, using the Weather Research and Forecasting (WRF) model with land use/cover and meteorological data under different SSP-RCP scenarios based on CMIP6. Two scenarios, SSP2-4.5 and SSP5-8.5, were compared and analyzed by simulating changes in future climate factors of temperature at 2 m height above ground(T2) and precipitation. The results show that T2 is higher for all 4 months by the year 2060 compared to that in the year 2030. Furthermore, a comparison of the abovementioned years showed that the mean temperatures of January and July were higher than those of SSP2-4.5 under the SSP5-8.5 scenario in both years, but in 2030, the mean T2 of April and October were lower than those of SSP2-4.5 under the SSP5-8.5 scenario. In terms of precipitation, both scenarios have no significant precipitation in July in 2030 and 2060, but there is an unusual increase in January and October.

Pyroelectric thermal–electrical cycles enable a class of solid-state heat engines that convert waste heat to electrical energy. This article numerically investigates thermal-to-electrical energy conversion in a PbZr0.52Ti0.48O3 (PZT) pyroelectric layer near room temperature and optimizes operating parameters to maximize the electrical energy output. A general thermodynamic cycle is modeled after the prototypical pyroelectric Ericsson cycle—implemented based on the Ginzburg–Landau–Devonshire theory—with variable operating temperature range, and heating/cooling and charging/discharging time intervals. We used a Pareto optimization approach to simultaneously maximize electrical energy density and power density for different PZT sample and cycle parameters. The evaluated Pareto optimal fronts showcase the possibility of achieving multiple optimal solutions and highlight the trade-off between output energy density and power density in pyroelectric energy conversion. Specifically, we demonstrate that a 4× enhancement in power density is achievable with a less than 10% reduction in energy density for the same sample and operating conditions primarily by optimizing heat transfer. The multi-objective optimization approach and results presented in this study could provide a framework to facilitate the design and operation of pyroelectric cycles for waste heat energy harvesting systems.

With the development of ship detection in optical remote sensing images, it is convenient to obtain accurate detection results and ship images. Owing to the superior performance of convolutional neural networks (CNNs), one way to acquire the category of ship is to train a classifier using numerous ship images. However, the classification performance of CNN may degrade in the case of a small number of training samples. To solve this problem, we propose a metric-based few-shot method to generate novel concept (class) representation using nearest neighbor prototype. Different from image-to-image measure in common few-shot methods, we use an image-to-feature measure. We map small number of samples to the feature space through CNN, and generate prototypes by computing nearest neighbor value on each dimension of the feature separately. Our method is validated on patch-level ship image dataset, a reproduced ship classification dataset based on HRSC2016. The experimental results demonstrate the accuracy and robustness of our method for ship classification with a small amount of labeled data.

Multispectral remote sensing images are often degraded by clouds, resulting in the reduced efficiency and accuracy of image interpretation. Thin cloud removal is one of the most important and significant tasks for optical multispectral images. In this article, we propose a novel thin cloud removal method for multispectral images, which is a combination of traditional methods and deep learning methods. First, we adopt U-Net to estimate the reference thin cloud thickness map of the cloudy image. Then, a convolutional neural network named Slope-Net is designed to estimate the thickness coefficient of each band relative to the reference thin cloud thickness map to obtain the thin cloud thickness maps of different bands. Finally, the recovered clear image can be obtained by subtracting the thin cloud thickness maps from the cloudy image according to the traditional thin cloud imaging model. To train U-Net and Slope-Net, a wavelength-dependent thin cloud simulation method is presented to generate a labeled dataset composed of synthetic cloudy images, corresponding clear images, reference thin cloud thickness maps, and thickness coefficients. Qualitative and quantitative comparison experiments are conducted on both synthetic cloudy images and real cloudy images from the Landsat 8 Operational Land Imager. The results indicate that the proposed method can effectively remove thin clouds in multispectral images with various land cover types and maintain good color fidelity.

Background: Augmented assembly guidance aims to help users complete assembly operations more efficiently and quickly through augmented reality technology, breaking the limitations of traditional assembly guidance technology which is single in content and boring in way. Object registration is one of the key technologies in augmented assembly guidance process, which can affect the location and direction of virtual assembly guidance information in real assembly environment. Methods: This paper presents an object registration method based on RGB-D camera, which combines Lucas-Kanade (LK) optical flow algorithm and Iterative Closet Point (ICP) algorithm. An augmented assembly guidance system for complex products through this method is built. Meanwhile, in order to compare the effectiveness of the proposed method, we also implemented object registration based on an open source augmented reality SDK Vuforia. Results: An engine model and a complex weapon cabin equipment are taken as an case to verify this work. The result shows that the registration method proposed in this paper is more accurate and stable compared with that based on Vuforia and the augmented assembly guidance system through this method greatly improves the user's time compared with the traditional assembly. Conclusions: Therefore, we can conclude that the object registration method mentioned in this paper can be well applied in the augmented assembly guidance system, which can do enhance the efficiency of assembly considerably.

Single image super-resolution (SISR) is to reconstruct a high-resolution (HR) image from a corresponding low-resolution (LR) input. It is an effective way to solve the problem that infrared remote sensing images are usually suffering low resolution due to hardware limitations. Most previous learning-based SISR methods just use synthetic HR-LR image pairs (obtained by bicubic kernels) to learn the mapping from LR images to HR images. However, the underlying degradation in the real world is often different from the synthetic method, i.e., the real LR images are obtained through a more complex degradation kernel, which leads to the adaptation problem and poor SR performance. To handle this problem, we propose a novel closed-loop framework that can not only make full use of the learning ability of the channel attention module but also introduce the information of real images as much as possible through a closed-loop structure. Our network includes two independent generative networks for down-sampling and super-resolution, respectively, and they are connected to each other to get more information from real images. We make a comprehensive analysis of the training data, resolution level and imaging spectrum to validate the performance of our network for infrared remote sensing image super-resolution. Experiments on real infrared remote sensing images show that our method achieves superior performance in various training strategies of supervised learning, weakly supervised learning and unsupervised learning. Especially, our peak signal-to-noise ratio (PSNR) is 0.9 dB better than the second-best unsupervised super-resolution model on PROBA-V dataset.

Abstract Premature infants who require surgery for retinopathy of prematurity often exhibit bronchopulmonary dysplasia. Reactive airway is a clinical manifestation of bronchopulmonary dysplasia. We describe premature infant twins who had difficulty with positive pressure ventilation during anesthesia. Both cases occurred during induction of anesthesia for binocular anterior chamber puncture and vitreous cavity injection. The most likely cause in each case was airway malacia. We recommend that endotracheal intubation is performed in infant patients with low body weight; the possibility of airway malacia occurrence should be considered, especially for infants with comorbid bronchopulmonary dysplasia.

Dust emitted from arid and semi-arid areas of China is a main contributor to the global atmospheric aerosols. However, the long-term spatial and temporal variations in dust concentrations in China is still unknown. Here, we simulated the spatial and temporal variations in spring dust concentrations in China from 2000 to 2020 using the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem). The results showed that the configured WRF-Chem model in this study reproduced the spatial patterns and temporal variations of dust aerosols. The annual mean spring dust concentration at the country level was 26.95 g kg−1-dry air and showed a slightly increasing trend in China during 2000–2020. There were clear spatial differences and inter-annual variations in dust concentrations. The dust concentration generally decreased from the dust source regions of the northwest to the southeast regions of China. Obvious increasing and decreasing trends in spring dust concentrations were identified in the regions of northern Xinjiang and Gansu and in the regions of southern Xinjiang and western Inner Mongolia, respectively. In May, the dust concentration showed an increasing trend in most regions of northwestern China. This provided the basic information for insight into the long-term spatial and temporal variations in spring dust concentrations in China.

Relative pose estimation of a satellite is an essential task for aerospace missions, such as on-orbit servicing and close proximity formation flying. However, the changeable situation makes precise relative pose estimation difficult. This paper introduces a deep-learning-based satellite relative pose estimation method for monocular optical images. The method is geared towards uncooperative target satellites with known 3D models. This paper proposes a novel convolutional neural network combined with 3D prior knowledge expressed by the 3D model in the form of the point cloud. The method utilizes point cloud convolution to extract features from the point cloud. To make the result more precise, a loss function that is more suitable for satellite pose estimation tasks is designed. For training and testing the proposed method, large amounts of data are required. This paper constructs a satellite pose estimation dataset BUAA-SID-POSE 1.0 by simulation. The proposed method is applied to the dataset and shows desirable performance on the pose estimation task. The proposed technique can be used to accomplish monocular vision-based relative pose estimation tasks in space-borne applications.

Estimation of spacecraft pose is essential for many space missions, such as formation flying, rendezvous, docking, repair, and space debris removal. We propose a learning-based method with uncertainty prediction to estimate the pose of a spacecraft from a monocular image. We first used a spacecraft detection network (SDN) to crop out the rectangular area in the original image where only spacecraft exist. A keypoint detection network (KDN) was then used to detect 11 pre-selected keypoints with obvious features from the cropped image and predict uncertainty. We propose a keypoints selection strategy to automatically select keypoints with higher detection accuracy from all detected keypoints. These selective keypoints were used to estimate the 6D pose of the spacecraft with the EPnP algorithm. We evaluated our method on the SPEED dataset. The experiments showed that our method outperforms heatmap-based and regression-based methods, and our effective uncertainty prediction can increase the final precision of the pose estimation.

As the main driving force of global climate change, land use and land cover change (LUCC) can affect the surface energy balance and the interaction between the surface and atmosphere. This effect will cause further surface temperature changes. The Yellow River Basin is an important ecological security barrier in China. Therefore, exploring the impact of its LUCC on temperature changes can provide certain help for future land-use planning in the Yellow River Basin. Here, we conducted two numerical simulation experiments (Case2015 and Case1995) by using the weather research and forecasting (WRF) model to quantify the effect of LUCC in the Yellow River Basin on the summer 2 m air temperature (T2 m). The results showed that LUCC led to an overall warming trend in T2 m in the Yellow River Basin. Urban expansion caused T2 m to rise by approximately 0.3 °C to 0.6 °C. A warming effect was also identified in the areas where farmland and bare areas were converted to grassland, with T2 m increasing by around 0.4 °C.

Monitoring and identification of ships in remote sensing images is of great significance for port management, marine traffic, marine security, etc. However, due to small size and complex background, ship detection in remote sensing images is still a challenging task. Currently, deep-learning-based detection models need a lot of data and manual annotation, while training data containing ships in remote sensing images may be in limited quantities. To solve this problem, in this paper, we propose a few-shot multi-class ship detection algorithm with attention feature map and multi-relation detector (AFMR) for remote sensing images. We use the basic framework of You Only Look Once (YOLO), and use the attention feature map module to enhance the features of the target. In addition, the multi-relation head module is also used to optimize the detection head of YOLO. Extensive experiments on publicly available HRSC2016 dataset and self-constructed REMEX-FSSD dataset validate that our method achieves a good detection performance.

The large-scale structure systems in engineering are complex, high dimensional, and variety of physical mechanism couplings; it will be difficult to analyze the dynamic behaviors of complex systems quickly and optimize system parameters. Model order reduction (MOR) is an efficient way to address those problems and widely applied in the engineering areas. This paper focuses on the model order reduction of high-dimensional complex systems and reviews basic theories, well-posedness, and limitations of common methods of the model order reduction using the following methods: center manifold, Lyapunov–Schmidt (L-S), Galerkin, modal synthesis, and proper orthogonal decomposition (POD) methods. The POD is a powerful and effective model order reduction method, which aims at obtaining the most important components of a high-dimensional complex system by using a few proper orthogonal modes, and it is widely studied and applied by a large number of researchers in the past few decades. In this paper, the POD method is introduced in detail and the main characteristics and the existing problems of this method are also discussed. POD is classified into two categories in terms of the sampling and the parameter robustness, and the research progresses in the recent years are presented to the domestic researchers for the study and application. Finally, the outlooks of model order reduction of high-dimensional complex systems are provided for future work.

We report the presence of a Weyl fermion in VI3 monolayer. The material shows a sandwich-like hexagonal structure and stable phonon spectrum. It has a half-metal band structure, where only the bands in one spin channel cross the Fermi level. There are three pairs of Weyl points slightly below the Fermi level in spin-up channel. The Weyl points show a clean band structure and are characterized by clear Fermi arcs edge state. The effects of spin-orbit coupling, electron correlation, and lattice strain on the electronic band structure were investigated. We find that the half-metallicity and Weyl points are robust against these perturbations. Our work suggests VI3 monolayer is an excellent Weyl half-metal.

Extracting accurate star centroids in the observed star images is one of the key problems for image navigation of the geosynchronous interferometric infrared sounder (GIIRS) of Fengyun-4A Satellite (FY-4A), the first scientific experimental satellite of the new generation of Chinese geostationary meteorological satellite Fengyun-4 series. Compared with star sensors which are widely used for star observation, it is challenging to detect the 2×2 star spot from the focused star images of GIIRS and calculate the star centroid in high precision. In this paper, we propose a star detection and centroiding method based on trajectory search and trajectory fitting. Since the launch of FY-4A in December 2016, our centroiding method has been tested in-orbit for over two years. The extensive experiments show that the star centroiding error of our method is less than 0.3 pixels, which makes an important contribution to image navigation of FY-4A.

Star observation can be used for the image navigation of certain instruments aboard the three-axis stabilized geostationary satellites. How to extract the accurate star centroids in the observed star images is one of the key problems. In this paper, a high precision star centroid detection method is proposed for the advanced geosynchronous radiation imager (AGRI) of Fengyun-4A (FY-4A), the first experimental satellite of the new generation of Chinese geostationary meteorological satellites FY-4 series. Different from star sensors which are deliberately defocused with relatively large star spot, AGRI is focused for the purpose of earth observation, making it challenging to extract accurate star centroids. To solve the problem, we take the advantage of continuous observing and improve the precision of star centroiding by trajectory fitting and energy response curve fitting. Extensive experiments have been performed on simulated star images and the actual observation data of AGRI aboard FY-4A over ten months in-orbit tests. Experimental results show that the proposed method can accurately extract star centroids with the error less than 0.3 pixels, laying a solid foundation for image navigation of FY-4A.

An invariable order reduction model cannot be obtained by the adaptive proper orthogonal decomposition (POD) method in parametric domain, there exists uniqueness of the model with different conditions. In this paper, the transient POD method based on the minimum error of bifurcation parameter is proposed and the order reduction conditions in the parametric domain are provided. The order reduction model equivalence of optimal sampling length is discussed. The POD method was applied for order reduction of a high-dimensional rotor system supported by sliding bearings in a certain speed range. The effects of speed, initial conditions, sampling length, and mode number on parametric domain order reduction are discussed. The existence of sampling length was verified, and two- and three-degrees-of-freedom (DOF) invariable order reduction models were obtained by proper orthogonal modes (POM) on the basis of optimal sampling length.

Fine-grained visual categorization (FGVC) is an important and challenging problem due to large intra-class differences and small inter-class differences caused by deformation, illumination, angles, etc. Although major advances have been achieved in natural images in the past few years due to the release of popular datasets such as the CUB-200-2011, Stanford Cars and Aircraft datasets, fine-grained ship classification in remote sensing images has been rarely studied because of relative scarcity of publicly available datasets. In this paper, we investigate a large amount of remote sensing image data of sea ships and determine most common 42 categories for fine-grained visual categorization. Based our previous DSCR dataset, a dataset for ship classification in remote sensing images, we collect more remote sensing images containing warships and civilian ships of various scales from Google Earth and other popular remote sensing image datasets including DOTA, HRSC2016, NWPU VHR-10, We call our dataset FGSCR-42, meaning a dataset for Fine-Grained Ship Classification in Remote sensing images with 42 categories. The whole dataset of FGSCR-42 contains 9320 images of most common types of ships. We evaluate popular object classification algorithms and fine-grained visual categorization algorithms to build a benchmark. Our FGSCR-42 dataset is publicly available at our webpages.

The transient proper orthogonal decomposition (TPOD) method is applied for order reduction in the rotor-bearing system with the coupling faults in this paper. A 24 degrees of freedom (DOFs) rotor model supported by a pair of sliding bearings with both crack and rub-impact faults is established by the discrete modeling method. The complexity of dynamic behaviors of the rotor system with the coupling faults is discussed via the comparison of the rotor system with the single fault (crack or rub-impact). The proper orthogonal mode (POM) energy method is proposed to confirm the DOF number of the reduced model. The TPOD method is used in the coupling faults system to obtain the optimal order reduction model based on the POM energy. The efficiency of the order reduction method is verified by comparing the bifurcation behaviors between the original and the reduced system. The TPOD method provides the optimal order reduction model to study the non-linear dynamic characteristics of the complex rotor system with the coupling faults.

The working condition of power network can significantly influence urban development. Among all the power facilities, electric pylon has an important effect on the normal operation of electricity supply. Therefore, the work status of electric pylons requires continuous and real-time monitoring. Considering the low efficiency of manual detection, we propose to utilize deep learning methods for electric pylon detection in high-resolution remote sensing images in this paper. To verify the effectiveness of electric pylon detection methods based on deep learning, we tested and compared the comprehensive performance of 10 state-of-the-art deep-learning-based detectors with different characteristics. Extensive experiments were carried out on a self-made dataset containing 1500 images. Moreover, 50 relatively complicated images were selected from the dataset to test and evaluate the adaptability to actual complex situations and resolution variations. Experimental results show the feasibility of applying deep learning methods to electric pylon detection. The comparative analysis can provide reference for the selection of specific deep learning model in actual electric pylon detection task.

In this paper, we address the problem of vision-based satellite recognition and pose estimation, which is to recognize the satellite from multiviews and estimate the relative poses using imaging sensors. We propose a vision-based method to solve these two problems using Gaussian process regression (GPR). Assuming that the regression function mapping from the image (or feature) of the target satellite to its category or pose follows a Gaussian process (GP) properly parameterized by a mean function and a covariance function, the predictive equations can be easily obtained by a maximum-likelihood approach when training data are given. These explicit formulations can not only offer the category or estimated pose by the mean value of the predicted output but also give its uncertainty by the variance which makes the predicted result convincing and applicable in practice. Besides, we also introduce a manifold constraint to the output of the GPR model to improve its performance for satellite pose estimation. Extensive experiments are performed on two simulated image datasets containing satellite images of 1D and 2D pose variations, as well as different noises and lighting conditions. Experimental results validate the effectiveness and robustness of our approach.

In the case of space-based space surveillance (SBSS), images of the target space objects captured by space-based imaging sensors usually suffer from low spatial resolution due to the extremely long distance between the target and the imaging sensor. Image super-resolution is an effective data processing operation to get informative high resolution images. In this paper, we comparably study four recent popular models for single image super-resolution based on convolutional neural networks (CNNs) with the purpose of space applications. We specially fine-tune the super-resolution models designed for natural images using simulated images of space objects, and test the performance of different CNN-based models in different conditions that are mainly considered for SBSS. Experimental results show the advantages and drawbacks of these models, which could be helpful for the choice of proper CNN-based super-resolution method to deal with image data of space objects.

The frequent hazy weather with air pollution in North China has aroused wide attention in the past few years. One of the most important pollution resource is the anthropogenic emission by fossil-fuel power plants. To relieve the pollution and assist urban environment monitoring, it is necessary to continuously monitor the working status of power plants. Satellite or airborne remote sensing provides high quality data for such tasks. In this paper, we design a power plant monitoring framework based on deep learning to automatically detect the power plants and determine their working status in high resolution remote sensing images (RSIs). To this end, we collected a dataset named BUAA-FFPP60 containing RSIs of over 60 fossil-fuel power plants in the Beijing-Tianjin-Hebei region in North China, which covers about 123 km 2 of an urban area. We compared eight state-of-the-art deep learning models and comprehensively analyzed their performance on accuracy, speed, and hardware cost. Experimental results illustrate that our deep learning based framework can effectively detect the fossil-fuel power plants and determine their working status with mean average precision up to 0.8273, showing good potential for urban environment monitoring.

The structural stability and magnetic properties of the cubic and tetragonal phases of Mn3Z (Z = Ga, In, Tl, Ge, Sn, Pb) Heusler alloys are studied by using first-principles calculations. It is found that with the increasing of the atomic radius of Z atom, the more stable phase varies from the cubic to the tetragonal structure. With increasing tetragonal distortion, the magnetic moments of Mn (A/C and B) atoms change in a regular way, which can be traced back to the change of the relative distance and the covalent hybridization between the atoms.

Micro-nano satellites have provided a large amount of remote sensing images for many earth observation applications. However, the hysteresis of satellite-ground mutual communication of massive remote sensing images and the low efficiency of traditional information processing flow have become the bottlenecks for the further development of micro-nano satellites. To solve this problem, this paper proposes an on-board ship detection scheme based on deep learning and Commercial Off-The-Shelf (COTS) component, which can be used to achieve near real-time on-board processing by micro-nano satellite computing platform. The on-board ship detection algorithm based on deep learning consists of a feature extraction network, Region Proposal Network (RPN) with square anchors, Global Average Pooling (GAP), and Bigger-Left Non-Maximum Suppression (BL-NMS). With the help of high performance COTS components, the proposed scheme can extract target patches and valuable information from remote sensing images quickly and accurately. A ground demonstration and verification system is built to verify the feasibility and effectiveness of our scheme. Our method achieves the performance with 95.9% recall and 80.5% precision in our dataset. Experimental results show that the scheme has a good application prospect in micro-nano satellites with limited power and computing resources.

No-reference (NR) image quality assessment (IQA) objectively measures the image quality consistently with subjective evaluations by using only the distorted image. In this paper, we focus on the problem of NR IQA for blurred images and propose a new no-reference structural similarity (NSSIM) metric based on re-blur theory and structural similarity index (SSIM). We extract blurriness features and define image blurriness by grayscale distribution. NSSIM scores an image quality by calculating image luminance, contrast, structure and blurriness. The proposed NSSIM metric can evaluate image quality immediately without prior training or learning. Experimental results on four popular datasets show that the proposed metric outperforms SSIM and well-matched to state-of-the-art NR IQA models. Furthermore, we apply NSSIM with known IQA approaches to blurred image restoration and demonstrate that NSSIM is statistically superior to peak signal-to-noise ratio (PSNR), SSIM and consistent with the state-of-the-art NR IQA models.

Automatic component detection of spacecraft can assist in on-orbit operation and space situational awareness. Spacecraft are generally composed of solar panels and cuboidal or cylindrical modules. These components can be simply represented by geometric primitives like plane, cuboid and cylinder. Based on this prior, we propose a robust automatic detection scheme to automatically detect such basic components of spacecraft in three-dimensional (3D) point clouds. In the proposed scheme, cylinders are first detected in the iteration of the energy-based geometric model fitting and cylinder parameter estimation. Then, planes are detected by Hough transform and further described as bounded patches with their minimum bounding rectangles. Finally, the cuboids are detected with pair-wise geometry relations from the detected patches. After successive detection of cylinders, planar patches and cuboids, a mid-level geometry representation of the spacecraft can be delivered. We tested the proposed component detection scheme on spacecraft 3D point clouds synthesized by computer-aided design (CAD) models and those recovered by image-based reconstruction, respectively. Experimental results illustrate that the proposed scheme can detect the basic geometric components effectively and has fine robustness against noise and point distribution density.

This paper addresses the problem of contextual hyperspectral image (HSI) classification. A novel conditional random fields (CRFs) model, known as higher order support vector random fields (HSVRFs), is proposed for HSI classification. By incorporating higher order potentials into a support vector random fields with a Mahalanobis distance boundary constraint (SVRFMC) model, the HSVRFs model not only takes advantage of the support vector machine (SVM) classifier and the Mahalanobis distance boundary constraint, but can also capture higher level contextual information to depict complicated details in HSI. The higher order potentials are defined on image segments, which are created by a fast unsupervised over-segmentation algorithm. The higher order potentials consider the spectral vectors of each of the segment’s constituting pixels coherently, and weight these pixels with the output probability of the support vector machine (SVM) classifier in our framework. Therefore, the higher order potentials can model higher-level contextual information, which is useful for the description of challenging complex structures and boundaries in HSI. Experimental results on two publicly available HSI datasets show that the HSVRFs model outperforms traditional and state-of-the art methods in HSI classification, especially for datasets containing complicated details.