Preprints
Filtering by Subject: Computer Sciences
AEF-Econ: Toward Plug-and-Play Socioeconomic Foundation Embeddings from AlphaEarth for Urban Remote Sensing
Published: 2026-06-20
Subjects: Computational Engineering, Computer Sciences, Earth Sciences, Electrical and Computer Engineering, Engineering, Environmental Sciences, Geography, Human Geography, Nature and Society Relations, Remote Sensing, Social and Behavioral Sciences
AlphaEarth Foundations (AEF) unify global remote sensing foundation embeddings through multimodal self-supervised learning, but their pretraining focuses on physical land-surface signals, limiting plug-and-play use in socioeconomic tasks. We integrate seven heterogeneous data streams across 36 Chinese cities over eight years—AEF embeddings, population, nighttime lights, remote sensing indices, [...]
Operationalising EMS-98 Damage Classification: A UAV-to-GIS Pipeline for Macroseismic Survey Support
Published: 2026-05-22
Subjects: Computer Sciences, Databases and Information Systems, Geographic Information Sciences, Geography, Nature and Society Relations, Remote Sensing, Spatial Science
Post-earthquake macroseismic surveying often relies on ground-based visual inspections that are slow, costly, and difficult to scale in the immediate aftermath of a seismic event. Deep-learning damage detectors have advanced substantially in recent years, yet their outputs are rarely translated into operational deployment tools that yield a georeferenced dataframe of buildings aligned with the [...]
From 2D labels to 3D structure: Scalable label transfer and benchmarking of 3D vegetation models in rangeland ecosystems
Published: 2026-05-03
Subjects: Artificial Intelligence and Robotics, Biogeochemistry, Computer Sciences, Earth Sciences, Engineering, Environmental Monitoring, Environmental Sciences, Natural Resources and Conservation, Physical Sciences and Mathematics, Remote Sensing
Three-dimensional (3D) characterisation of vegetation structure at the level of individual growth forms is critical for understanding ecosystem function and resilience, yet remains challenging in rangelands because vegetation is sparse, low-stature, and structurally heterogeneous. Recent 3D deep-learning models perform strongly in forests, but their transfer beyond closed-canopy benchmarks is [...]
HydroScholar AI: A Collaborative Agent for End-to-End Automated Hydrological Research Lifecycle
Published: 2026-04-10
Subjects: Computer Sciences, Earth Sciences, Environmental Sciences, Physical Sciences and Mathematics
Hydrological research relies on multi-stage computational workflows that are often slow, fragmented across disparate tools, and inconsistently documented, limiting reproducibility. This study presents HydroScholar AI, an agentic, human-in-the-loop platform that consolidates the plan-to-paper research lifecycle into a single interactive automated framework. From a natural-language prompt, the [...]
Seventeen city types define distinct pathways for climate mitigation and adaptation worldwide
Published: 2026-04-01
Subjects: Computer Sciences, Environmental Studies, Geography, Planetary Sciences
Understanding that cities are main arenas of climate action, it remains unclear which cities should focus on what kind of action taking a global comparative lens. Recent contributions identified four different types of cities across seven world regions, while others specified a huge case study literature database on cities and climate change biased towards established, stagnant, and megacities, [...]
Injecting vegetation-based spatialization in the hydrogeological framework for erosion modelling
Published: 2026-03-31
Subjects: Applied Statistics, Biodiversity, Computer Sciences, Earth Sciences, Geomorphology, Numerical Analysis and Scientific Computing
Erosion processes and landslide are widespread across Italy and frequently cause significant damage to people, infrastructure, and ecosystems. These processes are primarily triggered by rainfall events, whose impact depends on multiple interacting factors, including geomorphology, soil properties, land use, and vegetation. Among these, vegetation plays an essential role in regulating hillslope [...]
HIGH-RESOLUTION DIGITAL TERRAIN MODEL FOR THE ITALIAN TERRITORY
Published: 2026-03-12
Subjects: Agriculture, Civil and Environmental Engineering, Computer Sciences, Earth Sciences, Engineering, Engineering Education, Environmental Sciences, Environmental Studies, Geography, Life Sciences, Mining Engineering, Physical Sciences and Mathematics, Risk Analysis, Social and Behavioral Sciences
High-resolution digital terrain models are essential for environmental planning and territorial analyses, and provide foundations for geomorphological and hydrological applications, including flood and landslide modelling and geo-hydrological hazard and risk assessments. In Italy, airborne LiDAR surveys have improved the representation of terrain morphology in the last decade, but their coverage [...]
Bridging ERA5 Reanalysis Data and Regulatory Air Dispersion Modelling: A Transparent Workflow Implemented through the WindRose Toolkit
Published: 2026-03-08
Subjects: Computer Sciences, Earth Sciences, Environmental Sciences, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics
Regulatory atmospheric dispersion models such as AERMOD and CALPUFF are widely adopted for Environmental Impact Assessments involving atmospheric emissions. Despite their scientific maturity and regulatory acceptance, the practical application of these modelling systems outside the North American context is often constrained by the limited availability of suitable meteorological datasets. In many [...]
Sub-pixel mapping of disturbance and tree mortality dynamics from Sentinel-2 time series around the globe
Published: 2026-02-24
Subjects: Artificial Intelligence and Robotics, Biogeochemistry, Computer Sciences, Earth Sciences, Engineering, Environmental Monitoring, Environmental Sciences, Natural Resources and Conservation, Physical Sciences and Mathematics
Elevated forest disturbances and excess tree mortality are increasingly reported worldwide. Yet existing assessments are either based on patchy terrestrial observations or on large-scale satellite products, which are limited in resolution to pixel-level, binary tree loss detection. This leaves a blind spot on fine-scale disturbances where only a few trees are declining in an otherwise intact [...]
The Tocantins Framework: A Machine Learning-Based Assessment of Intra-urban Thermal Anomalies
Published: 2025-11-11
Subjects: Applied Statistics, Artificial Intelligence and Robotics, Computer Sciences, Environmental Indicators and Impact Assessment, Environmental Sciences, Statistics and Probability, Sustainability
The Urban Heat Island (UHI) effect has been extensively studied at the city scale. Yet, the Intra-Urban Heat Island and the Intra-Urban Cool Island effects remain poorly characterized due to the absence of standardized quantification frameworks. This study introduces the Tocantins Framework, a dual-metric system combining machine learning and spatial morphology to identify and quantify [...]
Flood Radar: Multi-Sensor SAR-Based Flood Mapping and Evacuation Modeling — A Case Study of the July 2025 Texas Flood
Published: 2025-11-08
Subjects: Computer Sciences, Earth Sciences, Oceanography and Atmospheric Sciences and Meteorology, Planetary Sciences
Floods remain among the most destructive natural hazards worldwide, causing an average of USD 40 billion in annual damage and affecting more than 2.5 billion people between 1994 and 2014. The Central Texas flood of July 2025 was one of the most catastrophic in recent decades, triggered by the remnants of Tropical Storm Barry that delivered over 508 mm of rain within two days. This study presents [...]
Multi-Agent Geophysical AI Workflow for Automated Reservoir Characterization
Published: 2025-11-07
Subjects: Artificial Intelligence and Robotics, Computational Engineering, Computer Sciences, Earth Sciences, Engineering, Geophysics and Seismology
Traditional geophysical workflows like reservoir characterization are driven in a collaborative manner where teams of geoscientists share their individual analyses to inform key decisions made by executives. However, these workflows are repetitive, time-consuming, prone to human error, and introduce subjective bias. While researchers have used automation to address these limitations via deep [...]
Vector Graphics-Based Geospatial Contour Maps: A Web-Native Interactive Approach for Modern Geospatial Data Science Applications
Published: 2025-10-14
Subjects: Computer Engineering, Computer Sciences, Earth Sciences, Engineering, Environmental Sciences, Graphics and Human Computer Interfaces
Visualizing scalar fields (e.g., temperature, precipitation etc.) on the web is often done via pre‑rendered raster tiles. While simple to serve and fast to access, rasters limit interactivity (feature picking, dynamic styling) and typically require heavy pre‑generation pipelines. Raster tiles remain the dominant method for web-based scalar field visualization, but they are storage-heavy and [...]
Artificial Intelligence in Earth Science: A GeoAI Perspective
Published: 2025-08-04
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Engineering, Environmental Sciences, Physical Sciences and Mathematics
GeoAI, or geospatial artificial intelligence, has transformative potential for Earth science by integrating geospatial data with artificial intelligence to enhance environmental monitoring, predictive modeling, and decision-making. This commentary, based on the Greg Leptoukh Lecture at AGU 2024, explores the evolving role of GeoAI in addressing pressing challenges—from environmental change in the [...]
Reduced-order modelling of Cascadia’s slow slip cycles
Published: 2025-07-25
Subjects: Computer Sciences, Earth Sciences, Numerical Analysis and Scientific Computing, Physical Sciences and Mathematics
Slow-slip events (SSEs) modulate the earthquake cycle in subduction zones, yet understanding their physics remains challenging due to sparse observations and high computational cost of physics-based simulations. We present a scientific machine-learning approach using a data-driven reduced-order modelling (ROM) framework to efficiently simulate the SSE cycle governed by rate-and-state friction in [...]