Preprints
Filtering by Subject: Computer Sciences
Using convex optimization to efficiently apportion tracer and pollutant sources from point concentration observations
Published: 2023-09-05
Subjects: Computer Sciences, Earth Sciences, Environmental Sciences, Mathematics
Rivers transport elements, minerals, chemicals, and pollutants produced in their upstream basins. A sample from a river is a mixture of all of its upstream sources, making it challenging to pinpoint the contribution from each individual source. Here, we show how a nested sample design and convex optimization can be used to efficiently unmix downstream samples of a well-mixed, conservative tracer [...]
SeisMIC - an Open Source Python Toolset to Compute Velocity Changes from Ambient Seismic Noise
Published: 2023-09-01
Subjects: Computer Sciences, Earth Sciences, Environmental Monitoring, Environmental Sciences, Geophysics and Seismology, Physical Sciences and Mathematics
We present SeisMIC, a fast, versatile, and adaptable open-source software to estimate seismic velocity changes from ambient seismic noise. SeisMIC includes a broad set of tools and functions to facilitate end-to-end processing of ambient noise data, from data retrieval and raw data analysis via spectrogram computation, over waveform coherence analysis, to post-processing of the final velocity [...]
Understanding Drought Awareness from Web Data
Published: 2023-08-17
Subjects: Computer Sciences, Earth Sciences, Mathematics, Oceanography and Atmospheric Sciences and Meteorology, Statistics and Probability
We used computer vision (U-Net) model to leverage Standardized Precipitation Evapotranspiration Index (SPEI), Google Trends Search Interest (SI), and Twitter data to understand patterns with which people in Continental United States (CONUS) indicate awareness of and interest in droughts. We found significant statistical relationships between the occurrence of meteorological droughts (MD), as [...]
Earth System Data Cubes: Avenues for advancing Earth system research
Published: 2023-07-11
Subjects: Computer Sciences, Earth Sciences, Environmental Sciences
Recent advancements in Earth system science have been marked by the exponential increase in the availability of diverse, multivariate datasets characterised by moderate to high spatio-temporal resolutions. Earth System Data Cubes (ESDCs) have emerged as one suitable solution for transforming this flood of data into a simple yet robust data structure. ESDCs achieve this by organising data into an [...]
ChatGPT as a mapping assistant: A novel method to enrich maps with generative AI and content derived from street-level photographs
Published: 2023-06-06
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Geographic Information Sciences, Geography, Other Computer Sciences, Other Geography, Spatial Science
This paper explores the concept of leveraging generative AI as a mapping assistant for enhancing the efficiency of collaborative mapping. We present results of an experiment that combines multiple sources of volunteered geographic information (VGI) and large language models (LLMs). Three analysts described the content of crowdsourced Mapillary street-level photographs taken along roads in a small [...]
Calling for a National Model Benchmarking Facility
Published: 2023-04-14
Subjects: Biology, Computer Sciences, Earth Sciences, Ecology and Evolutionary Biology, Environmental Sciences, Life Sciences, Oceanography and Atmospheric Sciences and Meteorology, Other Life Sciences, Physical and Environmental Geography, Physical Sciences and Mathematics, Planetary Sciences, Systems Biology
The modern world uses predictive computer models for many important purposes, including weather predictions, epidemic management, flood forecasting and warnings, and economic policymaking. We need to know how much we can trust the projections of these models, not only to achieve more accurate projections for systems, but also to undertake scientific learning about systems by incrementally testing [...]
Mapping glacier basal sliding with machine learning
Published: 2023-01-13
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Geophysics and Seismology
During the RESOLVE project ("High-resolution imaging in subsurface geophysics: development of a multi-instrument platform for interdisciplinary research"), continuous surface displacement and seismic array observations were obtained on Glacier d'Argentière in the French Alps for 35 days in May 2018. The data set is used to perform a detailed study of targeted processes within the highly dynamic [...]
Residual U-Net with Attention for Detecting Clouds in Satellite Imagery
Published: 2023-01-13
Subjects: Computer Sciences, Earth Sciences, Physical Sciences and Mathematics
Semantic segmentation of clouds in Earth observation imagery is an important task in a variety of remote sensing contexts: from the application of atmospheric corrections to being able to accurately omit cloud pixels when extracting information about ground features. Here we introduce a deep learning approach based on the popular U-Net architecture. The core of the architecture is an U-Net with [...]
Technical note: A procedure to clean, decompose and aggregate time series
Published: 2022-11-17
Subjects: Computer Sciences, Earth Sciences, Environmental Sciences, Physical Sciences and Mathematics, Statistics and Probability
Errors, gaps and outliers complicate and sometimes invalidate the analysis of time series. While most fields have developed their own strategy to clean the raw data, no generic procedure has been promoted to standardize the pre-processing. This lack of harmonization makes the inter-comparison of studies difficult, and leads to screening methods that can be arbitrary or case-specific. This study [...]
CloudSEN12 - a global dataset for semantic understanding of cloud and cloud shadow in Sentinel-2
Published: 2022-09-24
Subjects: Computer Sciences, Earth Sciences, Physical Sciences and Mathematics
Accurately characterizing clouds and their shadows is a long-standing problem in the Earth Observation community. Recent works showcase the necessity to improve cloud detection methods for imagery acquired by the Sentinel-2 satellites. However, the lack of consensus and transparency in existing reference datasets hampers the benchmarking of current cloud detection methods. Exploiting the [...]
Autonomous Passage Planning for a Polar Vessel
Published: 2022-08-31
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Environmental Sciences, Oceanography and Atmospheric Sciences and Meteorology, Other Earth Sciences, Other Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Sustainability
We introduce a method for long-distance maritime route planning in polar regions, taking into account complex changing environmental conditions. The method allows the construction of optimised routes, describing the three main stages of the process: discrete modelling of the environmental conditions using a non-uniform mesh, the construction of mesh-optimal paths, and path smoothing. In order to [...]
Space-time landslide hazard modeling via Ensemble Neural Networks
Published: 2022-06-02
Subjects: Applied Statistics, Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Geomorphology, Physical Sciences and Mathematics, Statistics and Probability
For decades, a full numerical description of the spatio-temporal dynamics of a landslide could be achieved only via physics-based models. The part of the geomorphology community focusing on data-driven model has instead focused on predicting where landslides may occur via susceptibility models. Moreover, they have estimated when landslides may occur via models that belong to the [...]
Democratizing Deep Learning Applications in Earth and Climate Sciences on the Web: EarthAIHub
Published: 2022-04-20
Subjects: Computer Sciences, Earth Sciences, Engineering, Environmental Sciences
Most deep learning application studies have limited accessibility and reproducibility for researchers and students in many domains, especially in earth and climate sciences. In order to provide a step towards improving accessibility to deep learning models in such disciplines, this study presents a community-driven framework and repository, EarthAIHub, that is powered by TensorFlow.js, where deep [...]
A computational framework for time dependent deformation in viscoelastic magmatic systems
Published: 2022-04-01
Subjects: Applied Mathematics, Computer Sciences, Earth Sciences, Mathematics
Time-dependent ground deformation is a key observable in active magmatic systems, but is challenging to characterize. Here we present a numerical framework for modeling transient deformation and stress around a subsurface, spheroidal pressurized magma reservoir within a viscoelastic half-space with variable material coefficients, utilizing a high-order finite-element method and explicit [...]
Practical Reproducibility in Geography and Geosciences
Published: 2022-03-28
Subjects: Computer Sciences, Earth Sciences, Environmental Sciences, Higher Education
Reproducible research is often perceived as a technological challenge, but it is rooted in the challenge to improve scholarly communication in an age of digitisation. When computers become involved and researchers want to allow other scientists to inspect, understand, evaluate, and build upon their work, they need to create a research compendium that includes the code, data, computing [...]