检索结果-内蒙古大学图书馆

Mapping dominant plant communities in the degraded Zoige swamp using Sentinel-1/2 imagery and its implications for vegetation restoration

引用

Ecological Indicators 2025年 175卷

作者： Zhang, Guoying Zhao, Chuanpeng Jia, Mingming Zhang, Rong Jiang, Hou Wang, Zongming State Key Laboratory of Black Soils Conservation and Utilization Northeast Institute of Geography and Agroecology Chinese Academy of Sciences Changchun130102 China School of Chemistry and Environmental Engineering Changchun University of Science and Technology Changchun130022 China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China

Zoige swamp has experienced varying degrees of degradation due to human-driven drainage and global climate change. Through satellite remote sensing, existing studies have obtained data on the distribution and changes in area of degraded Zoige swamp;however, the detailed identification of constituent plant communities has not been conducted. In this study, we used Sentinel-1/2 imagery and digital elevation model (DEM) as the data sources to create median composite images for the fruiting and withering seasons of vegetation. Then, we applied the random forest (RF) algorithm to identify three plant communities dominated by Kobresia, Carex, and Blysmus in the degraded Zoige swamp. The generated map achieved an overall accuracy of 89.2%. Finally, we reconstructed the decision rules based on the trained RF model. The results showed that Carex could be identified through the image characteristics of the fruiting season, whereas the other two communities required dual-phase image features, wherein the identification of Kobresia was particularly challenging. This may be related to the differing water demands of vegetation communities: Kobresia is more drought-tolerant and often mixed with other plateau-based herbaceous plants. This study generated three dominant plant communities in the degraded Zoige swamp, providing new reference methods and data-based support to reveal the current degradation status and its restoration potential. © 2025 The Authors

关键词： Vegetation mapping

来源：评论

学校读者我要写书评

暂无评论

Perceptual Uncertainty-Aware Motion Planning for Autonomous Driving Based on Adaptive Heuristic Reinforcement Learning

引用

IEEE Transactions on Intelligent Transportation systems 2025年

作者： Hu, Chuan Du, Baiyu Wang, Zhidong Zhang, Qichao Zhang, Ronghui Gao, Hongbo Shanghai Jiao Tong University School of Mechanical Engineering Shanghai200240 China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Sun Yat-sen University Guangdong Provincial Key Laboratory of Intelligent Transport System School of Intelligent Systems Engineering Guangzhou510275 China University of Science and Technology of China School of Information Science and Technology Department of Automation Hefei230026 China

Autonomous driving has become an inevitable trend in automotive development. Reinforcement Learning (RL) is extensively used in autonomous vehicle motion planning, demonstrating good generalization but facing challenges of long training times and lack of consideration of uncertainty. To address these challenges, an Adaptive Heuristic Reinforcement Learning (AHRL) approach is proposed. First, this study improves upon the Dueling Double Deep Q Network (D3QN) algorithm by proposing the Adaptive Heuristic Dueling Double Deep Q Network (Adapt-HD3QN) algorithm. Specifically, heuristic functions from search-based planning algorithms are incorporated into the RL reward terms to guide heuristic learning and enhance learning efficiency. Additionally, considering the uncertainties in real-world driving environments, such as the movement of other traffic participants and building occlusions, a Mixed Artificial Potential Field (Mix-APF) is implemented to address static and dynamic obstacle avoidance. Furthermore, potential collisions between the autonomous vehicle and other vehicles in occluded areas are modeled as a zero-sum game, with a Dynamic Bayesian Network (DBN) used for prior modeling of potential vehicles, aiding in constructing the potential vehicle’s forward hidden set. Finally, a signal-free intersection scenario, a typical crash-prone road type, is constructed on CARLA, incorporating static obstacles and other traffic participants. Experimental results demonstrate that the proposed Adapt-HD3QN algorithm exhibits superior safety, training efficiency, and traffic efficiency in scenarios with road environment perception uncertainties caused by occlusion. © 2000-2011 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

CTCNet: A CNN-Transformer Dual Branch Network for Sand Dune Image Segmentation

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Tianrui Wang, Zhaobin Zhang, Yaonan Guo, Xuejun Lanzhou University School of Information Science and Engineering Lanzhou730000 China Northwest Institute of Eco-Environment and Resources Chinese Academy of Sciences National Cryosphere Desert Data Center Lanzhou730000 China Institute of Tibetan Plateau Research Chinese Academy of Sciences State Key Laboratory of Tibetan Plateau Earth System Science National Tibetan Plateau Data Center Beijing100101 China

Dune images typically display intricate details and relatively uniform spectral characteristics, making them a unique challenge for image segmentation tasks. Due to the limitations of traditional convolution operations, the convolutional neural network (CNN)-based methods struggle to capture long-range dependencies. The Transformer-based methods have good performance in long-term dependency relationships, but it lacks modeling of local context. Based on the strengths of both approaches and the concept of a dual-branch architecture, in order to better achieve segmentation of sand dune images in desert areas, a dual-branch network combining CNN and Transformer (CTCNet) is proposed, and comparative experiments are conducted on a self-made Chinese desert sand dune morphology dataset and the Registan-Kharan desert sand dune morphology dataset. The CNN branch aims to capture local information and enhance feature extraction capabilities using convolutional attention block (CAB). The Transformer branch captures global information and employs an enhanced transformer block to improve the capture of remote dependencies and create more discriminative features. Afterward, the dual branch features are merged through a feature fusion module (FFM) to enhance the capture of finer details. Driven by its dual-branch structure and other design features, CTCNet has demonstrated exceptional capability in capturing dependencies and contextual information for sand dune image segmentation tasks. The experimental results demonstrate that CTCNet achieves an accuracy of 89.66% and a mean intersection over union (MIoU) of 82.29% on the Chinese desert sand dune morphology dataset. On the Registan-Kharan desert dune morphology dataset, it achieves an accuracy of 91.24% and a MIoU of 81.21%. Outperforming other models of similar complexity and size, achieving state-of-the-art results, and demonstrating the effectiveness and robustness of CTCNet. © 1980-2012 IEEE.

关键词： Jurassic

来源：评论

学校读者我要写书评

暂无评论

Calculating models of mass action concentrations for structural units or ion couples in RbCl-H_2O binary system and RbCl-RbNO_3-H_2O ternary system

引用

Transactions of Nonferrous Metals Society of China 2010年第6期20卷 1112-1120页

作者：郭汉杰杨学民赵伟洁 School of Metallurgical and Ecological Engineering University of Science and Technology Beijing State Key Laboratory of Multiphase Complex System Institute of Process Engineering Chinese Academy of Sciences

Thermodynamic models of calculating mass action concentrations for structural units or ion couples in RbCl-H2O binary and RbCl-RbNO3-H2O ternary strong electrolyte aqueous solutions were developed based on the ion and molecule coexistence theory at 298.15 K.A transformation coefficient is needed to compare the calculated mass action concentration and the reported activity because they are obtained at different standard states and concentration *** results show that the transformation coefficients between the calculated mass action concentrations and the reported activities of the same structural units or ion couples in RbCl-H2O binary and RbCl-RbNO3-H2O ternary strong electrolyte aqueous solutions change in a very narrow *** transformed mass action concentrations of structural units or ion couples in RbCl-H2O binary system are in good agreement with the reported activities. The transformed mass action concentrations of RbCl and RbNO3 in RbCl-RbNO3-H2O ternary solution are also in good agreement with the reported activities,aRbCl and 3RbNOa,with different total ionic strengths as 0.01,0.05,0.1,0.5,1.0,1.5,2.0,3.0 and 3.5 mol/kg,*** those results mean the developed thermodynamic model of strong electrolyte aqueous solutions can reflect structural characteristics of RbCl-H2O binary and RbCl-RbNO3-H2O ternary strong electrolyte aqueous solutions and the mass action concentration also strictly follows the mass action law.

关键词： mass action concentration activity ion and molecule coexistence theory RbCl-H2O RbCl-RbNO3-H2O structural unit ion couple

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal distribution of seasonal snow density in the Northern Hemisphere based on in situ observation

引用

Research in Cold and Arid Regions 2025年

作者： Che, Tao Dai, LiYun Li, Xin Key Laboratory of Cryospheric Science and Frozen Soil Engineering Heihe Remote Sensing Experimental Research Station Northwest Institute of Eco-Environment and Resources Chinese Academy of Sciences Lanzhou 730000 China State Key Laboratory of Tibetan Plateau Earth System Resources and Environment (TPESRE) Institute of Tibetan Plateau Research Chinese Academy of Sciences Beijing 100049 China

The snow density is a fundamental variable of the snow physical evolution processes, which can reflect the snowpack condition due to the thermal and gravitational compaction. Snow density is a bridge to transfer snow depth to snow water equivalent (SWE) for the snow water resources research. Therefore, it is important to understand the spatiotemporal distribution of snow density for the appropriate estimation of SWE. In this study, in situ snow densities from more than 6,000 stations in the Northern Hemisphere were used to analyze the spatial and temporal variations in snow density. The results displayed that snow density varied spatially and temporally in the Northern Hemisphere, with range of below 0.1 to over 0.4 g/cm³. The average snow densities in the mountainous regions of western North America, southeastern Canada, and Europe range from approximately 0.24 to 0.26 g/cm³, which is significantly greater than the values of 0.16–0.17 g/cm³ observed in Siberia, central Canada, the Great Plains of the United states, and China. The seasonal growth rates also present large spatial heterogeneity. The rates are over 0.024 g/cm³ per month in Southeastern Canada, the west mountain of North America and Europe, approximately 0.017 g/cm³ per month in Siberia, much larger than approximately 0.004 g/cm³ per month in other regions. Snow cover duration is a critical factor to determine the snow density. This study endorses the small snow density in China based on meteorological station observations, which results from that the meteorological stations are dominantly distributed in plain areas with relative short snow cover duration and shallow snow. © 2025 Northwest institute of Eco-Environment and Resources, CAS

关键词： Northern Hemisphere Snow cover duration Snow density Snow depth

来源：评论

学校读者我要写书评

暂无评论

TTOP model simulation of long-term (1981–2100) permafrost dynamics of the Tibetan Plateau

引用

Geoderma 2025年 457卷

作者： Zhao, Yufeng Yao, Yingying Jin, Huijun Li, Xin Cao, Bin Ran, Youhua Kuang, Xingxing Zheng, Chunmiao Institute of Global Environmental Change Xi'an Jiaotong University Xi'an710049 China School of Ecology China-Russia Joint Laboratory of Cold Regions Engineering and Environment Permafrost Institute Northeast Forestry University Harbin 150040 China State Key Laboratory of Frozen Soils Engineering Northwest Institute of Eco-Environment and Resources Chinese Academy of Sciences Lanzhou730000 China State Key Laboratory of Tibetan Plateau Earth System Environment and Resources National Tibetan Plateau Data Center Institute of Tibetan Plateau Research Chinese Academy of Sciences Beijing 100101 China Heihe Remote Sensing Experimental Research Station State Key Laboratory of Cryospheric Science and Frozen Soil Engineering Northwest Institute of Eco-Environment and Resources Chinese Academy of Sciences Lanzhou 730000 China School of Environmental Science and Engineering Southern University of Science and Technology Shenzhen518055 China Eastern Institute for Advanced Study Eastern Institute of Technology Ningbo315200 China

The Tibetan Plateau (TP) covers the largest regions under low- and mid-latitude permafrost. The evolution of permafrost has significantly affected the hydrology, biogeochemistry, and infrastructure of Asia. However, model reconstructions of long-term permafrost evolution with high accuracy and reliability are insufficient. Here, spatial changes in mean annual ground temperature at the depth where the annual amplitude is zero (MAGT) on the TP since 1981 were modeled and validated based on temperature records from 155 boreholes, and future changes were predicted under scenarios from the Climate Model Intercomparison Project 6 (CMIP6). The results indicated that the MAGT on the TP was approximately 1.5 °C (2010 – 2018), and the corresponding permafrost extent on the TP is estimated to be approximately 1.03 × 106 km2, which is projected to decrease to 0.77 × 106, 0.50 × 106, 0.30 × 106, and 0.17 × 106 km2 under the scenarios of shared socioeconomic pathway (SSP)126, SSP245, SSP370, and SSP585, respectively, by 2100. As predicted in the SSP585 scenario, permafrost is predicted to largely disappear from many basins of major Asian rivers, such as the Yarlung Zangpo-Brahmaputra, Nu-Salween, and Lancang-Mekong Rivers, between 2041 and 2060, followed by the Yellow and Yangtze Rivers between 2061 and 2080. Moreover, the original stable permafrost in the West Kunlun Mountains will change to transitional and unstable conditions. Our study offers comprehensive datasets of year-to-year ground temperatures and permafrost extent maps for the TP, which can serve as a fundamental resource for further investigations on the hydrogeology, engineering geology, ecology, and geochemistry of the TP. © 2025 The Author(s)

关键词： Permafrost

来源：评论

学校读者我要写书评

暂无评论

Research on flame classification and recognition based on object detection and similarity fusion

引用

The Journal of China Universities of Posts and Telecommunications 2021年第5期28卷 59-67页

作者： He Xin Zhou Junhua Liao Zhonghua Zhai Xiang Sun Siyuan School of Electronic Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation CenterBeijing 100854China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System EngineeringBeijing 100854China

The color, shape, and other appearance characteristics of the flame emitted by different flame engines are different. In order to make a preliminary judgment on the category of the device to which it belongs through studying exterior characteristics of the flame, this paper uses the flame of matches, lighters, and candles to simulate different types of flames. It is hoped that the flames can be located and classified by detecting the characteristics of flames using the object detection algorithm. First, different types of fire are collected for the dataset of experiments. The mmDetection toolbox is then used to build several different object detection frameworks, in which the dataset can be trained and tested. The object detection model suitable for this kind of problem is obtained through the evaluation index analysis. The model is ResNet50-based faster-region-convolutional neural network(Faster R-CNN), whose mean average-precision(mAP) is 93.6%. Besides, after clipping the detected flames through object detection, a similarity fusion algorithm is used to aggregate and classify the three types of flames. Finally, the color components are analyzed to obtain the red, green, blue(RGB) color histograms of the three flames.

关键词： flame classification object detection similarity fusion

来源：评论

学校读者我要写书评

暂无评论

Negative capacitance tunneling field-effect transistor for logic electronics and photodetection devices

引用

Applied Materials Today 2025年 44卷

作者： Yan, Haoran Wu, Shuaiqin Chen, Yan Xiao, Yongguang Xiong, Ke Zhao, Qianru Tang, Minghua Jiao, Hanxue Lin, Tie Shen, Hong Meng, Xiangjian Wang, Xudong Chu, Junhao Wang, Jianlu School of Materials Science and Engineering Xiangtan University Hunan Xiangtan411105 China State Key Laboratory of Infrared Physics Shanghai Institute of Technical Physics Chinese Academy of Sciences No.500 Yutian Road Shanghai 200083 China Shanghai Frontiers Science Research Base of Intelligent Optoelectronics and Perception Institute of Optoelectronics Fudan University Shanghai 200433 China University of Chinese Academy of Sciences No. 19 A Yuquan Road Beijing 100049 China State Key Laboratory of Integrated Chips and Systems Frontier Institute of Chip and System Fudan University Shanghai 200433 China

Low-power consumption field-effect transistors leveraging quantum mechanical tunneling and negative capacitance effects hold significant potential in electronic and optoelectronic fields. However, challenges such as the low on-current of tunnel field-effect transistors and current hysteresis in negative capacitance field-effect transistors hinder their applications. One approach to addressing these drawbacks is to combine the advantages of both mechanisms to develope negative capacitance tunnel field-effect transistor devices. In this research, we report a ReS2/BP negative capacitance tunnel field-effect transistor based on high-k ferroelectric material zirconium-doped hafnium oxide for electronics and optoelectronic devices. The device achieved subthreshold swing on/Ioff ratio of 106 with a low electrical hysteresis. An inverter integrated by a BP p-type field-effect transistor and a ReS2/BP n-type negative capacitance tunnel field-effect transistor was further demonstrated. Furthermore, the device demonstrated high performance optoelectronic properties. Benefiting from the tunneling process inherent in the type-III junction, the device achieved a response time of 8 µs;and the responsivity of device reached 41 A/W. These results provide a promising method for developing low-power consumption and high-performance electronics and optoelectronics. © 2025

关键词： Ferroelectric materials

来源：评论

学校读者我要写书评

暂无评论

Vehicle identification and battery voltage prediction using the long short-term memory neural networks for unknown real-world charging pile data oriented to vehicle-pile interaction

引用

Journal of Energy Storage 2025年 126卷

作者： Hong, Jichao Ma, Shikun Li, Kerui Liang, Fengwei Zhang, Baoqiang Qiu, Yulong Chen, Yuan School of Mechanical Engineering University of Science and Technology Beijing Beijing100083 China Shunde Innovation School University of Science and Technology Beijing Foshan528399 China Power Battery & System Research Center Dalian Institute of Chemical Physics Chinese Academy of Sciences Dalian116023 China State Key Laboratory of Catalysis Dalian Institute of Chemical Physics Chinese Academy of Sciences Dalian116023 China Co. Ltd Tianjin300300 China School of Artificial Intelligence Anhui University Hefei230000 China

Current research on battery voltage prediction is mainly based on data from electric vehicles, but considering that many vehicles may experience voltage anomalies during the charging process, it is equally essential for charging piles to have the ability to predict the voltage of electric vehicles. However, the charging piles do not have access to the vehicle identification numbers, which directly makes research based on pure charging pile data very limited and challenging. To address this issue, this paper proposes a vehicle identification-driven Long Short-Term Memory (LSTM) network model, which aims to achieve accurate multi-step forward prediction of the battery pack voltage for unknown electric vehicles by analyzing the real-world vehicle data collected from the charging pile. This study first groups the charging data by vehicle identification and then utilizes the LSTM model to predict the voltage of the grouped data. The experimental results demonstrate that the LSTM model can effectively predict the voltage of the grouped data, with a mean relative error of 0.225 %. This is the first time the LSTM model was applied to charging pile data for battery voltage prediction, providing a reference for subsequent safety warnings. © 2025 Elsevier Ltd

关键词： Battery Pack

来源：评论

学校读者我要写书评

暂无评论

Synergistic Mechanism Design and Market Modelling of Demand Response Center, Trading Center and Dispatching Center for New Power systems

Synergistic Mechanism Design and Market Modelling of Demand ...

引用

Smart Grid and Artificial Intelligence (SGAI), International Conference on

作者： Baoming Ma Haili Wang Liyong Hou Jiawei Zhu Bowen Han Fanqi Meng Peng Wang Yihong Ding Inner Mongolia Power Exchange Center Co. Ltd Inner Mongolia China College of Electrical and Electronic Engineering Electric Power University Beijing China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing China National Institute of Energy Development Strategy Electric Power University North China Beijing China

ISBN: (数字)9798331518806

ISBN: (纸本)9798331518813

The continuation of the traditional trading center and dispatch center power market operation under the new power system may be difficult to adapt to the regulatory needs of multiple types of flexibility resources participating in the market. This study combines the development of China's electric power market with the actual power operation and management departments, considers the regulation characteristics of large amount of flexibility resources, and innovatively proposes a “three-center” collaborative operation mechanism of demand response center-trading center-dispatch center, which provides a more convenient management platform for market-based demand response under the vigorous development of new energy.

关键词： Energy consumption Power supplies Mechanism design Power system stability Electricity supply industry Demand response Regulation Dispatching Stability analysis Smart grids

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：