Preprints
Filtering by Subject: Artificial Intelligence and Robotics
Validation Challenges in Large-Scale Tree Crown Segmentations from Remote Sensing Imagery Using Deep Learning: A Case Study in Germany
Published: 2025-07-25
Subjects: Artificial Intelligence and Robotics, Forest Sciences
Deep-learning–based individual tree-crown (ITC) mapping has become increasingly prominent in remote sensing, yet rigorous validation of these predictions at large spatial scales remains challenging. Using data from an extensive case study involving the mapping of approximately 218.7 million trees across the German federal states of Sachsen and Sachsen-Anhalt from multispectral aerial imagery, [...]
Aquascan: Graph-Based Learning for Distributed Marine Sensing
Published: 2025-07-04
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Environmental Monitoring, Environmental Sciences, Oceanography, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Water Resource Management
Marine monitoring faces unprecedented challenges as climate change and human activities reshape ocean ecosystems. Traditional tracking methods struggle with the scale and complexity of modern marine sensing needs. This paper proposes distributed networks of low-cost drifting sensors and presents a comparative study of heterogeneous graph neural networks (GNNs) versus Kalman filters for predicting [...]
Natural forests of the world - a 2020 baseline for deforestation and degradation monitoring
Published: 2025-04-29
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Environmental Sciences, Geographic Information Sciences, Remote Sensing
Informed decisions to reduce deforestation, protect biodiversity, and curb carbon emissions require not just knowing where forests are, but understanding their composition. Identifying natural forests, which serve as critical biodiversity hotspots and major carbon sinks, is particularly valuable. We developed a novel global natural forest map for 2020 at 10 m resolution. This map can support [...]
Enhancing and Interpreting Deep Learning for Sea Ice Charting using the AutoICE Benchmark
Published: 2025-04-24
Subjects: Analysis, Artificial Intelligence and Robotics, Environmental Monitoring, Oceanography
Accurate mapping of sea ice is crucial for marine navigation and monitoring climate change. Automating sea ice mapping remains challenging due to remotely-sensed signal ambiguity, the dynamic nature of sea ice, and limited field measurements. The AutoICE challenge recently introduced a benchmark to advance deep learning for sea ice mapping. Top-performing solutions used the U-Net architecture [...]
Mapping Responsible AI Workflows for Geospatial Data Science: Developing the I-GUIDE Data Ethics Toolkit
Published: 2025-04-23
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Environmental Sciences, Geographic Information Sciences, Geography, Library and Information Science, Sustainability
AI workflows in geospatial data science promise substantial societal benefits yet pose persistent challenges of ethical risk, transparency, and reproducibility. Current guidance, ranging from high‑level principles to isolated documentation templates, remains difficult to translate into day‑to‑day research practice, especially for teams operating under tight deadlines. This paper reports the [...]
Three times accelerated glacier area loss in Svalbard revealed by deep learning
Published: 2025-03-22
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Glaciology, Physical Sciences and Mathematics
The rapid warming in polar regions highlights the need to monitor climate change impacts such as glacier retreat and related global sea level rise. Glacier area is an essential climate variable but its tracking is complicated by the labour-intensive manual digitisation of satellite imagery. Here we introduce ICEmapper, a deep learning model that maps glacier outlines from Sentinel-1 time series [...]
How to deal w___ missing input data
Published: 2025-03-14
Subjects: Artificial Intelligence and Robotics, Hydrology, Water Resource Management
Deep learning hydrologic models have made their way from research to applications. More and more national hydrometeorological agencies, hydro power operators, and engineering consulting companies are building Long Short-Term Memory (LSTM) models for operational use cases. All of these efforts come across similar sets of challenges—challenges that are different from those in controlled scientific [...]
Predicting Land Surface Temperature With Uncertainty Estimation Using a Community Sensor Network and Machine Learning
Published: 2025-01-31
Subjects: Artificial Intelligence and Robotics, Environmental Indicators and Impact Assessment, Environmental Monitoring, Sustainability
Urban Heat Islands (UHIs) are areas in cities that experience higher temperatures than surrounding areas due to construction features such as buildings, roads, and a general lack of vegetation. UHIs, which pose a threat to public health while also increasing energy usage, are often defined using land surface temperatures. Our study demonstrates how a community sensor network from the Baltimore [...]
A Conversational Intelligent Assistant for Enhanced Operational Support in Floodplain Management with Multimodal Data
Published: 2024-12-19
Subjects: Artificial Intelligence and Robotics, Civil and Environmental Engineering, Computer Sciences, Databases and Information Systems, Earth Sciences, Environmental Engineering, Environmental Sciences, Environmental Studies, Hydraulic Engineering, Hydrology, Water Resource Management
Floodplain management is crucial for mitigating flood risks and enhancing community resilience, yet floodplain managers often face significant challenges, including the complexity of data analysis, regulatory compliance, and effective communication with diverse stakeholders. This study introduces Floodplain Manager AI, an innovative artificial intelligence (AI) based virtual assistant designed to [...]
Tracking Drought Impacts from Texts: Towards AI-Assisted Drought Impact Detection
Published: 2024-12-06
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Environmental Indicators and Impact Assessment, Environmental Sciences, Hydrology
Drought is recognized for its extensive and varied impacts. Based on the drought-related textual datasets from the National Drought Mitigation Center, our research applies advanced artificial intelligence techniques, including deep learning and natural language processing, to enhance the monitoring of multifaceted drought impacts in the United States. This study also delves into predicting [...]
Towards statistical modeling of chlorophyll-a concentrations in Balikpapan Bay, Indonesia: Implications for algal bloom detection
Published: 2024-10-26
Subjects: Artificial Intelligence and Robotics, Biogeochemistry, Environmental Monitoring, Marine Biology, Oceanography
This study presents a comprehensive statistical analysis of chlorophyll-a dynamics in Balikpapan Bay, Indonesia, combining time series analysis, extreme value modeling, and machine learning techniques to understand phytoplankton variability near Indonesia's planned new capital city. Analysis of daily chlorophyll-a concentrations (2019-2021) revealed a non-Gaussian distribution (skewness = 2.212, [...]
Application of machine learning methods to forecast petrophysical properties in basalts of the Serra Geral Group: Implications for carbon storage
Published: 2024-10-22
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Environmental Sciences, Geophysics and Seismology, Oil, Gas, and Energy, Physical Sciences and Mathematics
This study applies machine learning techniques for forecasting petrophysical properties (density, porosity, and permeability) in the basalts of the Serra Geral Group, located in the Paraná Basin, Brazil. These properties are crucial for the successful implementation of carbon capture and storage (CCS), an important technology to combat climate change. Employing machine learning models—XGBoost, [...]
DARTS: Multi-year database of AI-detected retrogressive thaw slumps in the circum-arctic permafrost region
Published: 2024-10-20
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Geomorphology, Physical Sciences and Mathematics
Retrogressive Thaw Slumps (RTS) and Active Layer Detachment Slides (ALD) are widespread thermal mass-wasting hillslope failures triggered by thawing permafrost. Despite increasing rates of these failures, knowledge about their pan-arctic spatial and temporal distribution remains limited. We present the Database of AI-detected Arctic RTS and ALD footprints (DARTS), the largest hillslope [...]
MicroCrystalNet: An Efficient Convolutional Neural Network for Microcrystal Classification using Scanning Electron Microscope Petrography
Published: 2024-08-22
Subjects: Artificial Intelligence and Robotics, Engineering, Other Engineering, Other Environmental Sciences
Morphological characterization of microcrystalline rock textures typically relies upon the visual interpretation and manual measurement of scanning electron microscopy (SEM) imagery: a practice fraught with subjectivity, inefficiency, sampling bias, and data loss. We introduce a state-of-the-art computer vision pipeline, built on deep learning architectures, for segmenting and classifying [...]
Implementation of the Peruvian Earthquake Early Warning System
Published: 2024-06-12
Subjects: Artificial Intelligence and Robotics, Geophysics and Seismology
We present the implementation and testing of the seismological components of the Peruvian Earthquake Early Warning System (Sistema de Alerta Sísmica Peruano, SASPe). SASPe is designed to send alert messages to areas located within a given distance from the epicenter of large (magnitude ≥ 6.0) subduction earthquakes, with a first alert based on data available 3 seconds after the arrival [...]