检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Guo, Hao Wang, Han Zhu, Di Wu, Lun Fotheringham, A. Stewart Liu, Yu Institute of Remote Sensing and Geographical Information Systems School of Earth and Space Sciences Peking University Beijing China Lab Division of Landscape Architecture Faculty of Architecture The University of Hong Kong Pokfulam Hong Kong Lab Department of Geography Environment and Society University of Minnesota Twin Cities MinneapolisMN United States Spatial Data Science Center Department of Geography Florida State University TallahasseeFL United States

Modeling spatial heterogeneity in the data generation process is essential for understanding and predicting geographical phenomena. Despite their prevalence in geospatial tasks, neural network models usually assume spatial stationarity, which could limit their performance in the presence of spatial process heterogeneity. By allowing model parameters to vary over space, several approaches have been proposed to incorporate spatial heterogeneity into neural networks. However, current geographically weighting approaches are ineffective on graph neural networks, yielding no significant improvement in prediction accuracy. We assume the crux lies in the over-fitting risk brought by a large number of local parameters. Accordingly, we propose to model spatial process heterogeneity at the regional level rather than at the individual level, which largely reduces the number of spatially varying parameters. We further develop a heuristic optimization procedure to learn the region partition adaptively in the process of model training. Our proposed spatial-heterogeneity-aware graph convolutional network, named RegionGCN, is applied to the spatial prediction of county-level vote share in the 2016 US presidential election based on socioeconomic attributes. Results show that RegionGCN achieves significant improvement over the basic and geographically weighted GCNs. We also offer an exploratory analysis tool for the spatial variation of non-linear relationships through ensemble learning of regional partitions from RegionGCN. Our work contributes to the practice of Geospatial Artificial Intelligence (GeoAI) in tackling spatial heterogeneity. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Escalating Hydrological Extremes and Whiplashes in the Western U.S.: Challenges for Water Management and Frontline Communities

引用

earth's Future 2025年第5期13卷

作者： Wenzhao Li Surendra Maharjan Joshua B. Fisher Thomas Piechota Hesham El-Askary Earth Systems Science and Data Solutions Lab Chapman University Orange CA USA Schmid College of Science and Technology Chapman University Orange CA USA Fowler School of Engineering Chapman University Orange CA USA Department of Environmental Sciences Faculty of Science Alexandria University Alexandria Egypt

The Western U.S. is experiencing significant changes in its hydrological dynamics, marked by increased variability and rapid “whiplash” shifts between extreme drought and flood conditions. This study quantified these changes using a customized hydrological water year index, which correlated better with surface water storage in the basins than other drought/wetness indicators. Application of the index revealed heightened hydrological extremes and whiplash events post-2015 in all Western U.S. basins, with nearly 72% of stations facing critically dry conditions in 2021 and over 54% experiencing extreme wet conditions in 2023. Future projections indicate a decline of 8.5%–13.2% in non-extreme water year types across major basins, accompanied by increases in both extreme wet and dry water year types. Our findings suggest that similar levels of multi-year drought duration and water deficits will likely occur regardless of future warming scenarios. This trend significantly impacts agriculture, the environment, and urban water use sectors. Notably, vulnerable frontline communities with higher risks and lower resilience experience disproportionate impacts from droughts compared to other communities. An index created for the Western U.S. to quantify hydrological extremes and whiplashes and to categorize water year types Projected fewer normal water years and increasing dominance of hydrological extremes Extended drought causes equally severe water shortages regardless of warming scenarios, mostly impacting vulnerable frontline communities To effectively manage water resources in the Western U.S., it's essential to understand the increasing variability in water availability and the rapid shifts between extreme drought and flood conditions, known as “whiplashes.” This study applied a customized hydrological water year index that more accurately correlates with surface water storage than other commonly used drought or wetness indicators. Our analysis revealed a marked increase i

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monitoring mangrove dynamics and evaluating future afforestation potential in the Egyptian Red Sea

引用

Environmental and Sustainability Indicators 2025年 26卷

作者： Rasha M. Abou Samra Mansour Almazroui Wenzhao Li Hesham El-Askary Environmental Sciences Department Faculty of Science Damietta University PO Box 34517 New Damietta City Egypt Center of Excellence for Climate Change Research Department of Meteorology King Abdulaziz University Jeddah Saudi Arabia Climatic Research Unit School of Environmental Sciences University of East Anglia Norwich NR4 7TJ UK Earth Systems Science and Data Solutions Lab Chapman University Orange CA 92866 USA Schmid College of Science and Technology Chapman University Orange CA 92866 USA Department of Environmental Sciences Faculty of Science Alexandria University Moharem Bek Alexandria 21522 Egypt

Mangrove forests are vital for ecosystem services and coastal management but face stressors from anthropogenic activities and climate change. This study estimates the extent and afforestation potential of mangroves along the Egyptian Red Sea coast from 1984 to 2022 using NDVI derived from Landsat-5 and Sentinel-2 data in Google earth Engine. Aboveground biomass (AGB), belowground biomass (BGB), carbon (C) stock, and CO 2 sequestration potential were evaluated using Sentinel-2 and elevation data. Future afforestation suitability (2020–2050) under SSP2-4.5 and SSP5-8.5 scenarios was assessed with the MaxEnt model. Mangrove area increased from 0.95 km 2 in 1984 to 1.46 km 2 in 2022, with Landsat-5 classification accuracy between 89 and 94 % and Sentinel-2 at 92–96 %. Mean AGB and BGB were 63.48 Mg/ha and 18.41 Mg/ha, while mean C stock and CO 2 sequestration were 40.94 Mg/ha and 150.25 Mg/ha, respectively, below global averages. Under SSP2-4.5, 18.60 km 2 and 21.40 km 2 were identified as highly and moderately suitable for afforestation, decreasing to 12.34 km 2 and 12.50 km 2 under SSP5-8.5. Under the SSP2-4.5 scenario, high-suitability areas for mangroves would be predominantly located along the northern coast, with fewer areas identified along the southern coast. Under the SSP5-8.5 scenario, high-suitability areas are expected to shift and concentrate only in the northern regions. Significant predictors under SSP2-4.5 included sea water velocity, bathymetry, and air temperature, while SSP5-8.5 highlighted bathymetry, sea surface temperature, and salinity. This study provides insights into mangrove dynamics, biomass potential, and afforestation opportunities, offering critical guidance for conservation and restoration strategies.

关键词： Carbon stock Mangroves MaxEnt model NDVI Species distribution

来源：评论

学校读者我要写书评

暂无评论

Linkages of the 2022 Unprecedented Global Heatwave Events to Triple-Dip La Niña

Linkages of the 2022 Unprecedented Global Heatwave Events to...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Sachi Perera Joshua B. Fisher Mohamed Allali Hesham El-Askary Computational and Data Sciences Graduate Program Schmid College of Science and Technology Chapman University Orange CA USA Earth Systems Science and Data Solution Lab Chapman University Orange CA USA Schmid College of Science and Technology Chapman University Orange CA USA Fowler School of Engineering Chapman University Orange CA USA Department of Environmental Sciences Faculty of Science Alexandria University Alexandria Egypt

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Heatwaves are influenced significantly by El Niño-Southern Oscillation (ENSO), which alters temperature and precipitation patterns throughout the world. Since 2020, we have witnessed a "triple dip" La Niña conditions persisting for three consecutive years resulting in severe weather and climate driven events globally. In this study, we identified the dominant frequency of Niño 3.4 Sea Surface Temperature (SST) signals and correlated them with regions experiencing unprecedented heat waves in 2022, namely, the Indian Ocean, the North Atlantic around England and Spain, and the Mediterranean Sea. The signal's power spectrum and its three highest power components are determined based on the signal's Singular Spectrum Analysis (SSA) for each region. Furthermore, the power spectrum coherence (PSC) of Niño 3.4 and other study regions is obtained to determine whether ENSO and heatwaves are linked. We find that Niño 3.4 and the Indian Ocean have the same dominant frequency for the highest power received, indicating ENSO's influence on the Indian heat wave. Additionally, we discovered that in March 2022, the Jet stream is essential in bringing warm Arctic waves southward, passing through Niño 3.4 and India. Furthermore, we found that no other region shared the dominant frequency of the Niño 3.4 region.

关键词： Heating systems Couplings Sea surface Precipitation Surface waves Indian Ocean Geoscience and remote sensing

来源：评论

学校读者我要写书评

暂无评论

Assessing Rice Phenological Features with Hyperspectral Imaging Insights from earth Surface Mineral Dust Source Investigation (EMIT)

Assessing Rice Phenological Features with Hyperspectral Imag...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Shahryar Fazli Wenzhao Li Surendra Maharjan Hesham El Askary Computational and Data Sciences Graduate Program Schmid College of Science and Technology Chapman University Orange CA USA Earth Systems Science and Data Solutions Lab Chapman University Orange CA USA Department of Environmental Sciences Faculty of Science Alexandria University Alexandria Egypt

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

In California's Central Valley, water management and crop health, particularly in rice cultivation, are critical. This paper details the application of earth surface Mineral dust source InvesTigation (EMIT) hyperspectral imaging, specifically employing Spectral Correlation Mapper (SCM) and Spectral Information Divergence (SID), for precise phenological analysis. By aligning EMIT data with Hyperion satellite references, we address spectral and geographical discrepancies. Our methodology includes seasonal sampling of spectral curves to capture the phenological stages of rice. Results show a strong correlation (R 2 = 0.86) between August EMIT and Reference dataset, emphasizing EMIT's utility in enhancing agricultural practices and water efficiency in the region, and highlighting the importance of understanding rice phenology for sustainable farming.

关键词： earth Correlation Satellites Accuracy Uncertainty Phenology Minerals

来源：评论

学校读者我要写书评

暂无评论

Deciphering Water Quality and Algal Dynamics in Clear Lake Through Hyperspectral Analysis Using Emit data

Deciphering Water Quality and Algal Dynamics in Clear Lake T...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Wenzhao Li Shahryar Fazli Surendra Maharjan Hesham El-Askary Earth Systems Science and Data Solutions Lab Schmid College of Science and Technology Chapman University Orange CA USA Computational and Data Sciences Graduate Program Schmid College of Science and Technology Chapman University Orange CA USA Department of Environmental Sciences Faculty of Science Alexandria University Alexandria Egypt

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

This study evaluates the potential application of hyperspectral earth Surface Mineral Dust Source Investigation (EMIT) remote sensing for monitoring harmful algal blooms (HABs) and water quality in Clear Lake, California. The research focuses on correlating the chlorophyll-a (Chl-a) concentrations with EMIT spectral signatures, using waterbody-wide statistical analysis of Chl-a and EMIT data sampling at various lake locations. Results demonstrate distinct spectral signatures associated with varying Chl-a levels, highlighting the potential of hyperspectral imaging in differentiating algae levels and assessing water quality variables. It also indicates the EMIT’s utility in filling data gaps and offering high-resolution monitoring. This study underscores the need for further research in hyperspectral imaging for aquatic ecosystems, especially under challenging atmospheric conditions, enhancing our understanding of water quality dynamics.

关键词： Satellites Statistical analysis Algae Water quality Lakes Filling Minerals

来源：评论

学校读者我要写书评

暂无评论

Extending regionalization algorithms to explore spatial process heterogeneity

arXiv

引用

arXiv 2022年

作者： Guo, Hao Python, Andre Liu, Yu Institute of Remote Sensing and Geographical Information Systems School of Earth and Space Sciences Peking University Beijing China Beijing Key Lab of Spatial Information Integration and Its Applications Peking University Beijing China Center for Data Science Zhejiang University Hangzhou China

In spatial regression models, spatial heterogeneity may be considered with either continuous or discrete specifications. The latter is related to delineation of spatially connected regions with homogeneous relationships between variables (spatial regimes). Although various regionalization algorithms have been proposed and studied in the field of spatial analytics, methods to optimize spatial regimes have been largely unexplored. In this paper, we propose two new algorithms for spatial regime delineation, two-stage K-Models and Regional-K-Models. We also extend the classic Automatic Zoning Procedure to spatial regression context. The proposed algorithms are applied to a series of synthetic datasets and two real-world datasets. Results indicate that all three algorithms achieve superior or comparable performance to existing approaches, while the two-stage K-Models algorithm largely outperforms existing approaches on model fitting, region reconstruction, and coefficient estimation. Our work enriches the spatial analytics toolbox to explore spatial heterogeneous processes. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sustainable Development Goals Through Future Vapor Pressure Deficit Analysis In The Nile River Basin

Enhancing Sustainable Development Goals Through Future Vapor...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Surendra Maharjan Wenzhao Li Shahryar Fazli Hani Sewilam Hesham El-Askary Computational and Data Sciences Graduate Program Schmid College of Science and Technology Chapman University Orange CA USA Earth Systems Science and Data Solutions Lab Chapman University Orange CA USA The Center for Applied Research on the Environment and Sustainability The American University in Cairo Cairo Egypt Department of Engineering Hydrology RWTH Aachen University Aachen Germany Department of Environmental Sciences Faculty of Science Alexandria University Alexandria Egypt

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Vapor Pressure Deficit (VPD) is crucial in meteorology and agriculture for understanding plant-environment interactions. Its application as an indicator in agricultural practices notably advances Sustainable Development Goals such as Zero Hunger (SDG 2) and Climate Action (SDG 13). This research focuses on the impact of climate change on agricultural productivity and food security in the Nile River Basin (NRB), emphasizing the role of VPD, temperature, and precipitation. Utilizing Coupled Model Intercomparison Project Phase 6 (CMIP6) datasets from NEX-GDDP-CMIP6, the study analyzes key climatic variables that influence agricultural conditions. The study applies the Mann-Kendall test to evaluate VPD trends from 2000 to 2060 under two Shared Socioeconomic Pathways (SSPs), SSP2-4.5 and SSP5-8.5. The study's findings on the implications of rising VPD levels in the Nile River Basin (NRB), particularly under the SSP 5-8.5 scenario, highlight a critical challenge for the region's agricultural productivity and food security. The increased VPD, indicative of drier conditions, leads to a moisture deficit for crops, potentially reducing agricultural yields. This scenario poses a significant threat to food security, as lower crop yields can result in food shortages and higher food prices, adversely affecting vulnerable populations. The study underscores the necessity of integrating VPD insights into agricultural and water resource management strategies to uphold food security against climatic variations in support of the SDGs.

关键词： Productivity Climate change Precipitation Food security Agriculture Rivers Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Cyberinfrastructure deployments on public research clouds enable accessible Environmental data science education 23

Cyberinfrastructure deployments on public research clouds en...

引用

2023 Practice and Experience in Advanced Research Computing, PEARC 2023

作者： Mcintosh, Tyler L Verleye, Erick Balch, Jennifer K Cattau, Megan E Ilangakoon, Nayani T Korinek, Nathan Nagy, R. Chelsea Sanovia, James Skidmore, Edwin Swetnam, Tyson L Tuff, Ty Quarderer, Nathan Wessman, Carol A Earth Lab Cooperative Institute for Research in Environmental Sciences University of Colorado Boulder BoulderCO United States Environmental Data Science Innovation and Inclusion Lab University of Colorado Boulder BoulderCO United States Human-Environment Systems Boise State University BoiseID United States Department of Geography University of Colorado Boulder BoulderCO United States BIO5 Institute University of Arizona TucsonAZ United States Ecology and Evolutionary Biology Department University of Colorado Boulder BoulderCO United States Cooperative Institute for Research in Environmental Sciences University of Colorado Boulder BoulderCO United States

ISBN: (纸本)9781450399852

Modern science depends on computers, but not all scientists have access to the scale of computation they need. A digital divide separates scientists who accelerate their science using large cyberinfrastructure from those who do not, or who do not have access to the compute resources or learning opportunities to develop the skills needed. The exclusionary nature of the digital divide threatens equity and the future of innovation by leaving people out of the scientific process while over-amplifying the voices of a small group who have resources. However, there are potential solutions: recent advancements in public research cyberinfrastructure and resources developed during the open science revolution are providing tools that can help bridge this divide. These tools can enable access to fast and powerful computation with modest internet connections and personal computers. Here we contribute another resource for narrowing the digital divide: scalable virtual machines running on public cloud infrastructure. We describe the tools, infrastructure, and methods that enabled successful deployment of a reproducible and scalable cyberinfrastructure architecture for a collaborative data synthesis working group in February 2023. This platform enabled 45 scientists with varying data and compute skills to leverage 40,000 hours of compute time over a 4-day workshop. Our approach provides an open framework that can be replicated for educational and collaborative data synthesis experiences in any data- and compute-intensive discipline. © 2023 Owner/Author.

关键词： Personal computers

来源：评论

学校读者我要写书评

暂无评论

A generalized machine learning model for long-term coral reef monitoring in the Red Sea

引用

Heliyon 2024年第18期10卷 e38249页

作者： Gapper, Justin J. Maharjan, Surendra Li, Wenzhao Linstead, Erik Tiwari, Surya P. Qurban, Mohamed A. El-Askary, Hesham Earth Systems Science and Data Solutions Lab Chapman University Orange 92866 CA United States Schmid College of Science and Technology Chapman University Orange 92866 CA United States Fowler School of Engineering Chapman University Orange 92866 CA United States Center for Environment and Water The Research Institute King Fahd University of Petroleum and Minerals (KFUPM) Dhahran 31261 Saudi Arabia National Center for Wildlife Saudi Arabia Department of Environmental Sciences Faculty of Science Alexandria University Moharem Bek Alexandria 21522 Egypt

Coral reefs, despite covering less than 0.2 % of the ocean floor, harbor approximately 35 % of all known marine species, making their conservation critical. However, coral bleaching, exacerbated by climate change and phenomena such as El Niño, poses a significant threat to these ecosystems. This study focuses on the Red Sea, proposing a generalized machine learning approach to detect and monitor changes in coral reef cover over an 18-year period (2000–2018). Using Landsat 7 and 8 data, a Support Vector Machine (SVM) classifier was trained on depth-invariant indices (DII) derived from the Gulf of Aqaba and validated against ground truth data from Umluj. The classifier was then applied to Al Wajh, demonstrating its robustness across different sites and times. Results indicated a significant decline in coral cover: 11.4 % in the Gulf of Aqaba, 3.4 % in Umluj, and 13.6 % in Al Wajh. This study highlights the importance of continuous monitoring using generalized classifiers to mitigate the impacts of environmental changes on coral reefs. © 2024 The Authors

关键词： Classification Landsat Machine learning Spatiotemporal coral change analysis SVM

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：