Preprints
Filtering by Subject: Artificial Intelligence and Robotics
Automating glacier facies classification: pan-European dataset and deep learning baseline
Published: 2026-01-27
Subjects: Artificial Intelligence and Robotics, Glaciology
Glacier facies play a critical role in understanding the mass balance of glaciers, offering insights into accumulation and melting processes. Accurate mapping of glacier facies is therefore essential for monitoring glacier response to climate change and informing climate policies. In this study, we present the largest glacier facies dataset ever compiled for Europe, comprising 31 glaciers, 92 [...]
Democratizing Environmental Data via the Model Context Protocol: A Service-Oriented Architecture for Environmental Intelligence
Published: 2026-01-12
Subjects: Artificial Intelligence and Robotics, Environmental Health and Protection, Environmental Indicators and Impact Assessment, Environmental Monitoring, Meteorology, Software Engineering, Sustainability
Advances in Artificial Intelligence (AI), particularly agentic AI, have created opportunities to improve efficiency and accuracy in addressing sustainability and environmental problems. Agentic AIs autonomously plan and execute towards specific goals with minimal or no human intervention; however, accessing environmental data is challenging and requires expertise, due to inherent fragmentation [...]
HyTC-TaNet: A Hybrid Deep Learning Model Capturing Multi-day Temporal Dependencies for Daily Mean Air Temperature Estimation with Spatial Applicability Analysis
Published: 2026-01-06
Subjects: Agriculture, Artificial Intelligence and Robotics
High-resolution seismic reservoir monitoring with multitask and transfer learning
Published: 2026-01-02
Subjects: Artificial Intelligence and Robotics, Computational Engineering, Geophysics and Seismology, Oil, Gas, and Energy, Sustainability
High-resolution real-time monitoring of reservoir changes is essential during CO2 injection or hydrocarbon production. Here, we leverage convolutional neural networks (CNNs) that employ multitask (MTL) and transfer (TL) learning to accurately predict relevant reservoir parameters from time-lapse seismic data. CNNs are initially trained to estimate the P-wave velocity from 2D multicomponent [...]
A variational approach at uncertainty estimation in data-driven rainfall-runoff modeling
Published: 2025-12-27
Subjects: Artificial Intelligence and Robotics, Hydrology
Reliable uncertainty estimation is essential for decision making, evaluating model performance, and defining the limits of what can be inferred from data. While uncertainty estimation typically requires specifying prior assumptions about distributional form, we introduce an approach to learn the structure of uncertainty directly from data. Specifically, we introduce a variational long short-term [...]
Earth Embeddings: Towards AI-centric Representations of our Planet
Published: 2025-12-08
Subjects: Artificial Intelligence and Robotics, Earth Sciences, Environmental Sciences
This paper presents a new perspective for the flexible and efficient representation of geospatial data, tailored to and empowered by AI: Earth embeddings. Earth embeddings provide a unified and accessible vector representation of local geographic characteristics. They fuse different geospatial data sources across time and space, compress highly-correlated raw geospatial data into one dense [...]
The Data Behind AI Coastal Forecasting: Inputs, Sources, and Preprocessing Approaches
Published: 2025-11-13
Subjects: Artificial Intelligence and Robotics, Oceanography
Coastal zones, shaped by marine and terrestrial processes, are home to over 40% of the global population and contribute significantly to the global economy. However, their attractiveness also makes them vulnerable to extreme coastal water levels (ECWLs), which can lead to catastrophic flooding. ECWLs, driven by sea-level changes, waves, and tidal variations, have become more frequent and severe [...]
Recent climate change reduced Spanish forests' carbon sink capacity
Published: 2025-11-13
Subjects: Artificial Intelligence and Robotics, Ecology and Evolutionary Biology, Environmental Sciences, Forest Sciences, Life Sciences
Forests play a crucial role as carbon sinks and are central to climate mitigation strategies, yet their long-term reliability in this function is increasingly uncertain under climate change. Using deep learning techniques on a multi-source dataset—combining multi-spectral satellite data, airborne laser scanning, and ground-based measurements—we produced the most up-to-date high-resolution maps of [...]
Accelerating Geothermal Modeling with Low- and High-Fidelity Fourier Neural Operators
Published: 2025-11-10
Subjects: Artificial Intelligence and Robotics, Oil, Gas, and Energy
Geothermal reservoir models are costly to build and calibrate, and generating a single forecast can take hours. Operators tasked with field planning and optimization are constrained by the speed of these forecast simulations, limiting the number of scenarios they can explore. Machine learning can be a powerful tool to speed up computationally expensive tasks, but standard approaches using Neural [...]
The Tocantins Framework: A Machine Learning-Based Assessment of Intra-urban Thermal Anomalies
Published: 2025-11-10
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 [...]
Multi-Agent Geophysical AI Workflow for Automated Reservoir Characterization
Published: 2025-11-06
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 [...]
ForestCast: Forecasting Deforestation Risk at Scale with Deep Learning
Published: 2025-10-31
Subjects: Artificial Intelligence and Robotics, Environmental Monitoring
Deforestation is a major threat to biodiversity and the stability of the climate. Current monitoring solutions provide reactive alerts only after deforestation has occurred, rendering them largely insufficient for prevention. Proactive deforestation prevention necessitates forecasting at-risk areas, however, previous forecasting efforts have been constrained by their reliance on simple [...]
A Computer Vision Framework for Estimating Surface Habitability from Mars Using Convolutional Analysis
Published: 2025-10-22
Subjects: Artificial Intelligence and Robotics, Biology, Earth Sciences, Other Planetary Sciences, Planetary Geology, Planetary Geomorphology, Planetary Sciences, Planetary Sedimentology, Statistical Methodology, Theory and Algorithms
Identifying signs of life in extraterrestrial environments is one of the growing challenges in planetary science. Conventional approaches of detecting habitability rely heavily on direct contact with biosignatures or geological analyses, but limited data and mission costs hold back such methods. This work introduces a computer vision-based pipeline that analyzes planetary surface images to [...]
AI-Powered Flood Risk Assessment for Gilgit-Baltistan Using Multi-Source Satellite Data and Machine Learning
Published: 2025-09-20
Subjects: Artificial Intelligence and Robotics, Geography, Geomorphology, Glaciology, Hydrology
Flood disasters are intensifying worldwide due to climate change, with mountainous regions among the most vulnerable yet least studied. This paper presents an AI-powered flood risk assessment framework for Gilgit-Baltistan, Pakistan, a high-mountain region prone to flash floods and glacial lake outburst floods (GLOFs). Multi-source satellite datasets—including CHIRPS precipitation, JRC Global [...]
Efficient Self-Attention Based Joint Optimization for Lithology and Petrophysical Parameter Estimation in the Athabasca Oil Sands
Published: 2025-09-17
Subjects: Artificial Intelligence and Robotics, Earth Sciences, Geology, Geophysics and Seismology
Accurately identifying lithology and petrophysical parameters, such as porosity and water saturation, are essential in reservoir characterization. Manual interpretation of well-log data, the conventional approach, is not only labor-intensive but also susceptible to human errors. To address these challenges of lithology identification and petrophysical parameter estimation in the Athabasca Oil [...]