Chenghu Zhou
YOU?
Author Swipe
View article: Quantifying the spatial heterogeneity of geographical flows
Quantifying the spatial heterogeneity of geographical flows Open
Geographical flows describe the movements and connections of materials, energy, and information among locations and are commonly represented by origin-destination (OD) flows (flows for short). The spatial heterogeneity of such flows is cha…
View article: FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling
FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling Open
Foundation models have shown remarkable cross-domain generalization in language and vision, inspiring the development of graph foundation models (GFMs). However, existing GFMs typically assume centralized access to multi-domain graphs, whi…
View article: Breaking the limitations of scenes and sensors variability: A novel unsupervised domain adaptive instance segmentation framework for agricultural field extraction
Breaking the limitations of scenes and sensors variability: A novel unsupervised domain adaptive instance segmentation framework for agricultural field extraction Open
View article: Amplified local cooling effect of forestation in warming Europe
Amplified local cooling effect of forestation in warming Europe Open
Forests exhibit local cooling or warming effects compared to adjacent openlands through biophysical processes. These temperature effects are predicted by earth system models to evolve in response to climate change. However, such temporal p…
View article: A typology of global relief classes derived from digital elevation models at 1 arcsec resolution
A typology of global relief classes derived from digital elevation models at 1 arcsec resolution Open
Understanding land surface morphology and its relief components, which record the dynamics of the planet's evolution and interaction of multiple environmental factors, constitutes a critical aspect of Earth system science. Advances in Eart…
View article: Ecosystem-dependent two-stage changes in soil organic carbon stock across the contiguous United States from 1970 to 2014
Ecosystem-dependent two-stage changes in soil organic carbon stock across the contiguous United States from 1970 to 2014 Open
View article: Assessing relative contributions of climate and socio-environmental factors to ecosystem health through space–time interpretable machine learning
Assessing relative contributions of climate and socio-environmental factors to ecosystem health through space–time interpretable machine learning Open
View article: Deep Learning and COVID-19: Two Pathways to Scientific Evolution
Deep Learning and COVID-19: Two Pathways to Scientific Evolution Open
COVID-19 and deep learning have each marked pivotal milestones in the evolution of modern science. Since the onset of the pandemic, researchers from diverse disciplines have converged to address urgent, real-world challenges, while deep le…
View article: Regional-scale soil carbon predictions can be enhanced by transferring global-scale soil–environment relationships
Regional-scale soil carbon predictions can be enhanced by transferring global-scale soil–environment relationships Open
View article: Spatio-temporal mapping reveals changes in soil organic carbon stocks across the contiguous United States since 1955
Spatio-temporal mapping reveals changes in soil organic carbon stocks across the contiguous United States since 1955 Open
Understanding spatio-temporal patterns of soil organic carbon (SOC) is critical for global climate change mitigation and sustainable soil management. However, information on long term dynamics of SOC over large area is lacking. Supported b…
View article: DMIMRec: Disentangled Multi-Interest Representation Learning for Multimodal Recommendation Systems
DMIMRec: Disentangled Multi-Interest Representation Learning for Multimodal Recommendation Systems Open
View article: Deep Learning and COVID-19: Two Pathways to Scientific Evolution
Deep Learning and COVID-19: Two Pathways to Scientific Evolution Open
COVID-19 and deep learning have each marked pivotal milestones in the evolution of modern science. Since the onset of the pandemic, researchers from diverse disciplines have converged to address urgent, real-world challenges, while deep le…
View article: DeepReport: An AI-assisted Idea Generation System for Scientific Research
DeepReport: An AI-assisted Idea Generation System for Scientific Research Open
View article: Global non-uniformity in biophysical surface temperature responses to cropland expansion over non-forest vegetation
Global non-uniformity in biophysical surface temperature responses to cropland expansion over non-forest vegetation Open
Cropland changes modulate local temperature by altering terrestrial biophysical properties, yet the global sign and magnitude of this impact remain uncertain due to fragmented distributions and complex natural land-cover conversions. Using…
View article: Increased Socioeconomic Impacts With Future Intensifying Flash Droughts in China
Increased Socioeconomic Impacts With Future Intensifying Flash Droughts in China Open
Amid global warming and rapid urbanization, China faces the challenge of an increasing frequency and severity of flash droughts. However, the impact of flash droughts on the socioeconomic conditions has not been sufficiently explored. Here…
View article: Mapping global distributions, environmental controls, and uncertainties of apparent topsoil and subsoil organic carbon turnover times
Mapping global distributions, environmental controls, and uncertainties of apparent topsoil and subsoil organic carbon turnover times Open
The turnover time (τ) of global soil organic carbon is central to the functioning of terrestrial ecosystems. Yet our spatially explicit understanding of the depth-dependent variations and environmental controls of τ at a global scale remai…
View article: The patterns of the <i>Populus euphratica</i> forest and cropland changes upstream of the Tarim River under the policy-driven human activities during 1960–2023
The patterns of the <i>Populus euphratica</i> forest and cropland changes upstream of the Tarim River under the policy-driven human activities during 1960–2023 Open
The natural Populus euphratica forest surrounding the Tarim River has experienced significant deforestation since the 1960s. This forest loss is primarily attributed to cropland expansion and the excessive use of agricultural water resourc…
View article: Globally interconnected solar-wind system addresses future electricity demands
Globally interconnected solar-wind system addresses future electricity demands Open
Accelerating energy transition towards renewables is central to net-zero emissions. However, building a global power system dominated by solar and wind energy presents immense challenges. Here, we demonstrate the potential of a globally in…
View article: A novel approach of generating pseudo revisited soil sample data based on environmental similarity for space-time soil organic carbon modelling
A novel approach of generating pseudo revisited soil sample data based on environmental similarity for space-time soil organic carbon modelling Open
View article: Towards Unbiased Federated Graph Learning: Label and Topology Perspectives
Towards Unbiased Federated Graph Learning: Label and Topology Perspectives Open
Federated Graph Learning (FGL) enables privacy-preserving, distributed training of graph neural networks without sharing raw data. Among its approaches, subgraph-FL has become the dominant paradigm, with most work focused on improving over…
View article: Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization
Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization Open
Recent advances in large pre-trained models showed promising results in few-shot learning. However, their generalization ability on two-dimensional Out-of-Distribution (OoD) data, i.e., correlation shift and diversity shift, has not been t…
View article: Federated Prototype Graph Learning
Federated Prototype Graph Learning Open
In recent years, Federated Graph Learning (FGL) has gained significant attention for its distributed training capabilities in graph-based machine intelligence applications, mitigating data silos while offering a new perspective for privacy…
View article: Identifying actionable statements in Chinese health guidelines: a cross-sectional study
Identifying actionable statements in Chinese health guidelines: a cross-sectional study Open
Objective The purpose of this study is to validate the taxonomy and framework using Chinese guidelines and identify actionable statements. Design and setting We searched five databases, to identify the health guidelines from 1 January 2020…
View article: Contrasting temporal dynamics of land surface temperature responses to different types of forest loss
Contrasting temporal dynamics of land surface temperature responses to different types of forest loss Open
View article: Observed different impacts of potential tree restoration on local surface and air temperature
Observed different impacts of potential tree restoration on local surface and air temperature Open
Tree restoration can cool or warm the local climate through biophysical processes. However, the magnitude of these effects remains unconstrained at large scales, as most previous observational studies rely on land surface temperature (Ts) …
View article: Global reconstruction of gridded aridity index and its spatial and temporal characterization from 2003 to 2022
Global reconstruction of gridded aridity index and its spatial and temporal characterization from 2003 to 2022 Open
Aridity index (AI) is an effective estimator of drought status, and spatiotemporally continuous long-term AI dataset is critical for drought assessment and applications. Due to the spatial heterogeneity of global climate and topography, th…
View article: Recent climate change strengthens the local cooling of European forests
Recent climate change strengthens the local cooling of European forests Open
Forests exhibit cooling or warming effects compared to adjacent openlands through biophysical processes. The local temperature effects are predicted by earth system models to evolve in response to climate change. However, these temporal dy…
View article: Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models
Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models Open
Given a style-reference image as the additional image condition, text-to-image diffusion models have demonstrated impressive capabilities in generating images that possess the content of text prompts while adopting the visual style of the …
View article: A Data Model and Method Framework for Cyberspace Map Visualization
A Data Model and Method Framework for Cyberspace Map Visualization Open
Integrating cyberspace and geographic space through map visualization is a valuable approach for revealing distribution patterns and relational dynamics in cyberspace. The interdisciplinary integration of network science and geographic sci…
View article: Sm-Nd Isotope Data Compilation from Geoscientific Literature Using an Automated Tabular Extraction Method
Sm-Nd Isotope Data Compilation from Geoscientific Literature Using an Automated Tabular Extraction Method Open
The rare earth elements Sm and Nd significantly address fundamental questions about crustal growth, such as its spatiotemporal evolution and the interplay between orogenesis and crustal accretion. Their relative immobility during high-grad…