论文与情报流

聚合权威论文、预印本与机构内容源,支持按主题、来源与关键词筛选,面向实验室持续开展科研跟踪与资料沉淀。

筛选器
当前来源
当前展示 24 条,共 7420
论文列表
首页/论文
论文
GIScience & Remote Sensing
PublisherJournal
Tool
中国净生态系统生产力的空间异质性及其对气候的非线性响应
Spatial heterogeneity and nonlinear climatic responses of net ecosystem productivity across China
Xichen Mi Qing Yu Tianci Yao Binxiao Liu Jingzhao Lu a School of Civil Engineering and Geomatics, Shandong University of Technology, Zibo, Chinab Guangzhou Institute of Geography, Guangdong Academy of Sciences, Guangzhou, Chinac State Key Laboratory of Space-Ground Integrated Information Technology, Beijing Institute of Satellite Information Engineering, Beijing, Chinad Department of Science and Engineering, Hebei Agricultural University, Baoding, China
2026/04/28
论文
GIScience & Remote Sensing
PublisherJournal
基于无偏时空融合方法的异质地表田间尺度日蒸散发制图
Mapping field-scale daily evapotranspiration using unbiased spatio-temporal fusion approach over heterogeneous surface
Aoxiang Guo Sunweiyu Huang Lisheng Song Dong Chu Desheng Liu a Key Laboratory of Earth Surface Processes and Regional Response in the Yangtze-Huaihe River Basin, Anhui Province, School of Geography and Tourism, Anhui Normal University, Wuhu, Anhui, People's Republic of Chinab Zhejiang Key Laboratory of Digital Intelligence Monitoring and Restoration of Watershed Environment, Zhejiang Normal University, Jinhua, Zhejiang, People's Republic of Chinac Department of Geography, The Ohio State University, Columbus, OH, USA
2026/03/05
论文
Landscape and Urban Planning
PublisherJournal
UrbanPlanning
编委会
Editorial Board

出版日期:2027年1月 来源:《Landscape and Urban Planning》,第277卷 作者:

Landscape and Urban Planning
论文
Transportation Research Part A
PublisherJournal
UrbanComputing
行为转变窗口期:可持续出行导向的出行行为改变的前兆
Windows of change as precursors to changing travel behaviour aligned with sustainable mobility

出版日期:2026年12月;来源:《交通研究A辑:政策与实践》(Transportation Research Part A: Policy and Practice),第214卷;作者:David A. Hensher、John D. Nelson、Edward Wei、Thiranjaya Kandanaarachchi、Camila Balbontin、Chinh Ho、Corinne Mulley、Wen Liu

Transportation Research Part A
论文
GIScience & Remote Sensing
PublisherJournal
早期性与普适性:一种具有时空可迁移性的新型玉米早期动态制图方法
How early and how general: a novel early-stage dynamic corn mapping method with spatiotemporal transferability
Sihan Tan Lingbo Yang Ran Huang Suyang Zheng Zhenyu Lin Han Zhang Limin Wang a School of Artificial Intelligence, Hangzhou Dianzi University, Hangzhou, People's Republic of Chinab Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing, People's Republic of China
2026/02/06
论文
ISPRS Journal of Photogrammetry and Remote Sensing
PublisherJournal
基于Landsat的四十年河流浊度重建揭示美国河流空间异质性下降趋势
Four decades of Landsat-based river turbidity reconstruction reveal spatially heterogeneous declines across U.S. rivers

出版日期:2026年12月 来源:《ISPRS摄影测量与遥感杂志》(ISPRS Journal of Photogrammetry and Remote Sensing),第242卷 作者:李阳、韩炳乾、刘戈、宋开山、吕东梅、史坤、马悦、邵世迪、周宇 Jin、张继鹏、吕恒

ISPRS Journal of Photogrammetry and Remote Sensing
论文
Transportation Research Part D
PublisherJournal
UrbanComputing
街道坡度对行人可达性影响的情境化分析:面向可持续出行
Contextualising the impact of street slopes on pedestrian accessibility for sustainable mobility

出版日期:2026年12月;来源:《交通运输研究D辑:交通运输与环境》(Transportation Research Part D: Transport and Environment),第161卷;作者:Vasileios Milias、Panagiotis G. Tzouras、Ioanna Vourdanou、Konstantinos Markos、Konstantinos Kepaptsoglou、Alexandros Nikitas

Transportation Research Part D
论文
Landscape and Urban Planning
PublisherJournal
UrbanPlanning
大规模城市造林的条件性降温效应:生态系统功能与规划启示
Conditional cooling from large-scale urban afforestation: ecosystem functioning and planning implications

出版日期:2027年2月;来源:《景观与城市规划》(Landscape and Urban Planning),第278卷;作者:Fei Feng、Xiuzhi Chen、Lin Gu、Chengyang Xu、Dayong Fan、Yongxian Su、Mario Elia、Raffaele Lafortezza

Landscape and Urban Planning
论文
ISPRS Journal of Photogrammetry and Remote Sensing
PublisherJournal
Platform
PELNet:一种面向极化目标分解的通用物理嵌入学习框架
PELNet: A general physics-embedded learning framework for polarimetric target decomposition

出版日期:2026年12月;来源:《ISPRS摄影测量与遥感杂志》(ISPRS Journal of Photogrammetry and Remote Sensing),第242卷;作者:张淑荣、庄迪、张腊梅、邹斌、乔迪·J·马洛尔奎(Jordi J. Mallorqui)

ISPRS Journal of Photogrammetry and Remote Sensing
论文
ISPRS Journal of Photogrammetry and Remote Sensing
PublisherJournal
融合运动与深度信息:一种面向运动红外小目标检测的蒸馏双分支网络
Synergizing motion and depth: A distilled dual-branch network for moving infrared small target detection

出版日期:2026年12月;来源:《ISPRS摄影测量与遥感杂志》(ISPRS Journal of Photogrammetry and Remote Sensing),第242卷;作者:罗登艳、向艳萍、王虎、纪路平、唐松、叶茂

ISPRS Journal of Photogrammetry and Remote Sensing
论文
International Journal of Geographical Information Science
PublisherJournal
Tool
受大脑启发的城市空间表征
Brain-inspired representations of urban space
Ed Manley Daniel C. McNamee a School of Geography, University of Leeds, Leeds, UKb Champalimaud Centre for the Unknown, Lisbon, PortugalEd Manley is a professor at the University of Leeds, where he studies the role of spatial cognition in shaping mobility and urban complexity. He contributed to the conceptualisation, methodology, analysis, and writing the paper.Daniel C. McNamee studied mathematics at Trinity College Dublin and did his PhD at Caltech in computation and neural systems. Currently, he is Principal Investigator at Champalimaud Research in Lisbon, Portugal. He contributed to the conceptualisation, methodology, and writing the paper.
2026/06/29
论文
arXiv
SpatialIntelligence
Trajectory
四旋翼模型预测控制中的时间级联式规划与控制
Temporal Cascading of Planning and Control for Quadrotor MPC

许多涉及四旋翼的空中任务既要求即时响应能力,又需长时域规划以实现避障、能量效率优化或轨迹跟踪。高保真度模型可实现精确控制,但计算速度无法满足长时域需求;低保真度规划器虽具备良好可扩展性,却无法直接驱动系统,因而需采用级联架构。当前主流的分层方法使用简化模型进行规划,并依赖高保真度控制器执行跟踪,但此类分解本质上存在次优性:控制器受限于粗糙的规划结果,而传统MPC方案则通过缩短时域以保障实时性。本文提出UNIQUE——一种以时间级联替代分层堆叠的MPC架构。其中,规划问题被建模为单一多阶段MPC的第二尾部时域,而非独立求解。我们统一了不同时域的成本函数,为质点规划模型推导出可行性约束,并引入状态转换约束,将高保真度状态映射为具有物理意义的低保真度状态。通过并行运行质点模型求解器与混合整数求解器处理非凸性,并在规划时域内逐步实施三维障碍物平滑。仿真与真实飞行实验表明,在相同计算资源预算下,UNIQUE相较标准MPC及分层基线方法,闭环跟踪性能提升最高达75%。消融实验与帕累托分析进一步验证了该方法在时域长度、约束近似方式及平滑调度等不同变体下的性能优势。

Rudolf Reiter, Chao Qin, Leonard Bauersfeld
2025/12/14
论文
Transactions in GIS
PublisherJournal
GeoAI
分析网络空间使用行为及其与城市物理功能的关联:以澳门为例
Analyzing Cyber Internet Usage and its Association With Physical Urban Functions: A Case Study in Macau

《GIS学报》(Transactions in GIS),2026年9月,第30卷第6期。

Minglei Liao, Xintao Liu
2026/09/09
论文
Transactions in GIS
PublisherJournal
GeoAI
在生态约束型城市增长建模中整合人工神经网络、卷积神经网络与基于超像素的图卷积:ANN‐SGCCA 方法
Integrating ANN, CNN and Superpixel‐Based Graph Convolution in Ecologically Constrained Urban Growth Modeling: The ANN‐SGCCA Approach

《国际地理信息科学杂志》(Transactions in GIS),2026年9月,第30卷第6期。

Jiangfu Liao, Guofan Shao, Lina Tang
2026/09/09
论文
arXiv
GeoAI
GIS
VANTAGE-Bench:评估视觉-语言模型中的基础设施人工智能差距
VANTAGE-Bench: Evaluating the Infrastructure AI Gap in Vision-Language Models

随着视觉-语言模型(VLM)逐步迈向物理场景部署,当前研究重心仍集中于面向动作的具身人工智能(Embodied AI),其评测主要基于以主体为中心的消费级视频。这一取向忽视了一类广泛存在的物理人工智能——基础设施人工智能(Infrastructure AI),该范式依赖固定摄像头,以开环方式提供安全监控、运行日志等洞察。为此,我们提出VANTAGE-Bench基准,用于量化这一“基础设施人工智能差距”。该基准覆盖物流、交通与智能空间三大运营领域,统一涵盖图像与视频在语义、空间、时间及时空联合维度的能力评估,并突破多项选择题范式,引入包括密集视频描述与时空定位在内的八种任务形式;针对单目标跟踪(Single Object Tracking),新增单次前向轨迹协议(single-pass trajectory protocol),并据我们所知,首次在固定摄像头基础设施视频上开展此类评测,且以专业追踪器为评分基准。标注覆盖三类范式,总计3,346个媒体资产:3,342条视频-任务标注、4,281条图像-定位标注,以及27,404个检测框。对17个模型进行零样本评测后发现,相较于以消费者为中心的基准,性能缺口呈现集中性而非普遍性:事件验证、指代表达与时间定位任务在所有模型规模下均落后约9至24个百分点,而视频问答任务与VideoMME的差距则控制在5.3分以内,2D空间指向任务亦未表现出相对于BLINK的性能缺口。时间维度能力在绝对指标上最弱:无一系统在时间定位任务上的mIoU超过55.7,在密集视频描述任务上的SODA_c得分超过37.3。在跟踪任务中,前沿模型在短时域内与专业追踪器相差约5分,但随预测时域延长,性能差距显著扩大。开源权重模型在2D目标定位任务上全面领先,表明性能缺口既非单纯由模型规模亦非仅由闭源属性所致。

Zaid Pervaiz Bhat, Nimra Nayyar, Arihant Jain
2026/09/09
论文
arXiv
GeoAI
GIS
DGCPath:面向分布感知的生成式对比学习框架用于自监督路径表示学习——扩展版
DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version

得益于先进感知技术推动的车辆轨迹数据激增,路径表示学习已成为智能交通系统中的关键任务。尽管现有自监督方法已取得良好性能,但其对确定性对比学习范式及人工设计视图增强策略的依赖,本质上限制了其跨场景泛化能力。为解决上述局限,我们提出 DGCPath——一种面向分布感知的生成式对比学习框架,专用于路径表示学习。该框架在生成建模与分布式对比学习之间建立协同关系,从而获得鲁棒且可迁移的特征嵌入。具体而言,本框架包含:(1)基于扩散模型的视图生成器,能够从高斯噪声中自主生成语义一致但多样化的轨迹视图;(2)变分对比机制,在分布层面强制隐空间特征对齐,超越传统逐样本一致性约束;(3)新型生成式交叉监督模块,通过跨视图重建学习强化视图级一致性。在三个真实世界轨迹数据集上的全面评估表明,DGCPath 在两项不同下游任务中均优于当前最优基线方法,验证了其增强的泛化能力与表示有效性。

Sean Bin Yang, Hao Miao, Zongyi Xu
2026/09/07
论文
International Journal of Digital Earth
PublisherJournal
Platform
一种可解释的集成学习框架用于复杂内陆水体总氮反演:以新丰江水库为例
An interpretable ensemble-learning framework for total nitrogen retrieval in complex inland waters: application to the Xinfengjiang Reservoir
Shuyi Gao Caige Sun Xulong Liu Xingda Chen Xiaofei Xu Xia Zhou Jianhui Xu a School of Geography, South China Normal University, Guangzhou, People's Republic of China b Guangzhou Institute of Geography, Guangdong Academy of Sciences, Guangzhou, People's Republic of China c Guangzhou Institute of Geochemistry, Chinese Academy of Sciences, Guangzhou, People's Republic of China d University of Chinese Academy of Sciences, Beijing, People's Republic of China e Guangdong Technology Center of Water Resources and Hydropower, Guangzhou, People's Republic of China
2026/08/24
论文
GIScience & Remote Sensing
PublisherJournal
GeoAI
利用Sentinel-1与Sentinel-2双传感器影像对干旱区森林叶面积指数进行分区协同估算
Partitioning and synergistic estimation of leaf area index in dryland forests using dual-sensor Sentinel 1 and 2 imagery
Vladislav Moshe Dubinin Yagil Osem Zeev Cohen Husein Muklada Dan Yakir Tarin Paz-Kagan a French Associates Institute for Agriculture and Biotechnology of Dryland, The Jacob Blaustein Institutes for Desert Research, Ben-Gurion University of the Negev, Sede Boqer Campus, Israel b Department of Natural Resources, Institute of Plant Sciences, Agricultural Research Organization, Volcani Center, Rishon LeZion, Israel c Institute of Plant Sciences, Agricultural Research Organization, Volcani Institute, Gilat, Israel d Earth and Planetary Sciences, Weizmann Institute, Rehovot, Israel
2026/08/19
论文
International Journal of Geographical Information Science
PublisherJournal
Multimodal
基于遥感与社交媒体数据的人口构成高分辨率制图:一种多模态、多输出建模方法
High-resolution mapping of demographic compositions based on remote sensing and social media data: a multimodal, multi-output modeling approach
Ge Qiu Yuchen Li Shaoqing Dai Kun Qin Zhanpeng Wang Yaolin Liu Jiping Liu Peng Jia a School of Resource and Environmental Sciences, Center for Metabolic and Panvascular Diseases, Wuhan University, Wuhan, Chinab Medical Remote Sensing Information Research Institute (MRSIRI), Renmin Hospital of Wuhan University, Wuhan, Chinac Chinese Academy of Surveying and Mapping, Beijing, Chinad International Institute of Spatial Lifecourse Health (ISLE), Wuhan University, Wuhan, Chinae School of Geography, University of Leeds, Leeds, UKf Duke Kunshan University, Kunshan, ChinaGe Qiu received his Ph.D. in Cartography and Geographic Information Systems from the School of Resource and Environmental Sciences, Wuhan University. His research interests are multi-source geospatial data fusion, spatial modeling and mapping, GeoAI, and health geography. His primary contributions to this study included conceptualization, methodology, investigation, formal analysis, software, validation, visualization, data curation, writing – original draft, and writing – review and editing.Yuchen Li is a Lecturer at the School of Geography, University of Leeds. His research interests are spatial analysis and modeling, spatial data mining, spatial statistics, transportation simulation, and public health modeling. His primary contributions to this study included methodology, validation, writing – original draft, and writing – review and editing.Shaoqing Dai is a postdoctoral researcher at the School of Resource and Environmental Sciences, Wuhan University. His research interests are health geography, spatial statistics, GeoAI, and urban visual intelligence. His primary contributions to this study included investigation, validation, visualization, and writing – review and editing.Kun Qin is a Ph.D. candidate at the School of Resource and Environmental Sciences, Wuhan University. His research interests include spatial modeling and mapping, spatiotemporal analysis, and health geography. His primary contributions to this study included software, visualization, data curation, and writing – review and editing.Zhanpeng Wang received his Ph.D. in Cartography and Geographic Information Systems from the School of Resource and Environmental Sciences, Wuhan University. His research interests are remote sensing, GeoAI, and health geography. His primary contributions to this study included investigation, visualization, data curation, and writing – review and editing.Yaolin Liu is a Professor at the School of Resource and Environmental Sciences, Wuhan University, and currently serves as the Chancellor of Duke Kunshan University. His research focuses on the application of geospatial technologies in land resource surveying, evaluation, planning, and management. His primary contributions to this study included conceptualization, validation, resources, supervision, project administration, and writing – review and editing.Jiping Liu is a Research Fellow and Deputy Director General at the Chinese Academy of Surveying and Mapping. His research interests are spatiotemporal big data analysis and mining, governmental geospatial information services, emergency geospatial information services, and 3D real-world modeling. His primary contributions to this study included conceptualization, investigation, validation, resources, supervision, funding acquisition, project administration, and writing – review and editing.Peng Jia is the founding director of the International Institute of Spatial Lifecourse Health (ISLE) and the Deputy Director of Medical Remote Sensing Information Research Institute (MRSIRI) at Renmin Hospital of Wuhan University. His research interests include health geography, spatial epidemiology, environmental health, and spatial science and technology. His primary contributions to this study included conceptualization, validation, resources, supervision, funding acquisition, project administration, and writing – review and editing.
2026/07/27
论文
arXiv
SpatialIntelligence
Trajectory
MAVEN-T:面向实时多智能体轨迹预测的强化异构蒸馏方法
MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction

轨迹预测是自动驾驶系统的关键组成部分,因为未来运动直接影响碰撞检测、行为规划与控制。该任务在密集交互、异质行为、多模态未来以及车载计算资源受限等条件下仍具挑战性。现有基于图、注意力机制和生成式的方法虽提升了交互推理或不确定性建模能力,但其高容量设计往往难以满足实时部署需求。轻量级预测器及传统蒸馏方法虽可降低推理开销,却通常依赖静态模仿,且未显式校正与安全性相关联的教师模型偏差。本文提出\textbf{MAVEN-T},一种面向实时多智能体轨迹预测的强化异构蒸馏框架。其中,高容量教师模型采用具备环视感知能力的图编码器建模有向局部交互,结合高效时序滤波与移窗空间注意力机制,并通过稀疏混合专家(Mixture-of-Experts)解码头输出特定驾驶意图的未来轨迹;紧凑型学生模型基于GRU与Squeeze-and-Excitation模块构建,并配备低秩适配(Low-Rank Adapted)策略头,通过特征级、注意力级与语义级蒸馏进行训练。为进一步使预测结果契合下游行为需求,学生模型进一步利用近端策略优化(Proximal Policy Optimization)奖励进行微调,奖励信号涵盖避撞、乘坐舒适性与行驶进展;同时,复杂度感知的课程学习(complexity-aware curriculum)与弹性权重固化(Elastic Weight Consolidation)保障了分阶段训练的稳定性。实验在NGSIM、HighD、MoCAD、Argoverse~2及Waymo Open Motion数据集上评估了所提方法在精度、效率、泛化性、鲁棒性及闭环安全性方面的表现。学生模型实现6.2$\times$参数压缩、3.7$\times$推理加速,并在NVIDIA Jetson AGX Orin平台上达到14.6 ms延迟,同时保持具有竞争力的预测精度。

Wenchang Duan, Zhenguo Gao, Jinguo Xian
2026/04/11
论文
Transport Policy
PublisherJournal
Platform
交通运输脱碳:推动能源转型并塑造气候韧性
Decarbonising transportation: Driving the energy transition and shaping climate resilience

出版日期:2026年11月;来源:《Transport Policy》,第188卷;作者:Olatunji A. Shobande、Lawrence Ogbeifun、Aviral Kumar Tiwari

Transport Policy
论文
Transportation Research Part D
PublisherJournal
海运业脱碳:岸电与电子燃料——以大加那利岛为例
Decarbonizing the maritime sector: cold ironing and e-fuels. Case study: Gran Canaria

出版日期:2026年11月;来源:《交通研究D辑:交通与环境》,第160卷;作者:Pablo Yánez-Rosales、Paula Ferreira、Julieta Schallenberg-Rodriguez、Alexis Lozano-Medina、B. del Rio-Gamero

Transportation Research Part D
论文
arXiv
SpatialIntelligence
Trajectory
EyeMakeYou:面向身份、任务与主观状态条件的扩散模型用于高频注视合成
EyeMakeYou: Identity-, Task-, and Subjective-State-Conditioned Diffusion for High-Frequency Gaze Synthesis

眼动生物特征(EMB)是一种新兴的行为模态,适用于用户身份认证,尤其在虚拟现实(VR)与增强现实(AR)系统中,其注视动力学蕴含显著的被试特异性特征。然而,构建鲁棒的EMB系统需大量多样且高质量的注视记录,而此类数据采集成本高昂,且往往难以满足模型开发所需的规模。生成式模型可缓解数据稀缺问题,但现有方法或仅合成通用注视行为,或主要依据身份进行信号个性化,未能联合建模用户的任务与主观状态。因此,所生成信号虽在视觉上逼真,却可能无法保留生物特征识别所需的行为特性。为解决该局限,我们提出 EyeMakeYou——一种面向被试特异性的高频注视合成的多条件去噪扩散框架。EyeMakeYou 以去除身份信息的参考轨迹为输入,生成时长5秒、采样率1000 Hz的双变量注视速度序列,并在去噪过程中联合条件化于身份嵌入、任务嵌入,以及关于整体难度、精神疲劳度和眼部疲劳度的自评量表评分。其优化目标融合了扩散噪声预测与身份保持,并引入多分辨率谱损失、漂移一致性损失及事件加权的局部平滑性损失。在 GazeBase 数据集上的实验表明,EyeMakeYou 在中位空间精度及嵌入特征空间中真实–合成样本相似性方面均优于现有生成方法,同时保留了若干主观报告与眼动特征之间依赖于任务的关联性。上述结果支持条件扩散作为面向生物特征识别与交互应用的注视数据增强的一种实用方法。

Kamrul Hasan, Mehedi Hasan Raju, Oleg V. Komogortsev
2026/09/04
论文
GIScience & Remote Sensing
PublisherJournal
1990–2022年中亚地表水动态的高精度月度遥感监测(基于遥感数据空缺填补技术)
High-precision monthly monitoring of surface water dynamics in Central Asia from 1990 to 2022 using remote sensing gap-filling techniques
Wenjing Huang Fuqiang Wang Weili Duan Junguo Liu Jingxiu Qin Kamshat Tussupova Huan Yang Lei Tang Xiaoyu Meng a North China University of Water Resources and Electric Power, Zhengzhou, People's Republic of China b Henan Provincial Key Laboratory of Water Resources Conservation and Intensive Utilization in the Yellow River Basin, Zhengzhou, Henan, People's Republic of China c Yellow River Research Institute, North China University of Water Resources and Electric Power, Zhengzhou, People's Republic of China d Henan Provincial Key Laboratory of Hydrosphere and Watershed Water Security, Zhengzhou, Henan, People's Republic of China e Key Laboratory of Ecological Safety and Sustainable Development in Arid Lands, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi, People's Republic of China f Kazakh National University of Water Management and Irrigation, Taraz, Kazakhstan g Key Research Institute of Yellow River Civilization and Sustainable Development & Collaborative Innovation Center on Yellow River Civilization of Henan Province, Henan University, Kaifeng, People's Republic of China
2026/07/29
1 / 310