Preprints
Filtering by Subject: Computer Sciences
GANSim: Conditional Facies Simulation Using an Improved Progressive Growing of Generative Adversarial Networks (GANs)
Published: 2020-07-06
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Geology, Hydrology, Mathematics, Physical Sciences and Mathematics, Sedimentology, Statistical Models, Statistics and Probability
Conditional facies modeling combines geological spatial patterns with different types of observed data, to build earth models for predictions of subsurface resources. Recently, researchers have used generative adversarial networks (GANs) for conditional facies modeling, where an unconditional GAN is first trained to learn the geological patterns using the original GANs loss function, then [...]
Deep spatial transformers for autoregressive data-driven forecasting of geophysical turbulence
Published: 2020-07-06
Subjects: Artificial Intelligence and Robotics, Atmospheric Sciences, Climate, Computer Sciences, Dynamical Systems, Earth Sciences, Environmental Sciences, Fluid Dynamics, Geophysics and Seismology, Mathematics, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Physics
A deep spatial transformer based encoder-decoder model has been developed to autoregressively predict the time evolution of the upper layers stream function of a two-layered quasi-geostrophic (QG) system without any information about the lower layers stream function. The spatio-temporal complexity of QG flow is comparable to the complexity of 500hPa Geopotential Height (Z500) of fully coupled [...]
Machine learning and fault rupture: a review
Published: 2020-07-02
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Geophysics and Seismology, Mathematics, Physical Sciences and Mathematics, Theory and Algorithms
Geophysics has historically been a data-driven field, however in recent years the exponential increase of available data has lead to increased adoption of machine learning techniques and algorithm for analysis, detection and forecasting applications to faulting. This work reviews recent advances in the application of machine learning in the study of fault rupture ranging from the laboratory to [...]
Modelling massive AIS streams with quad trees and Gaussian Mixtures
Published: 2020-06-29
Subjects: Computer Sciences, Other Computer Sciences, Physical Sciences and Mathematics
Pressing issues related to the movement of people and goods can be tackled today thanks to improvements in tracking and communications technology that have made it possible to collect movement data on a big scale. Maritime data from the Automatic Identification System (AIS) is one of the fast growing sources of movement data. Existing approaches for AIS data [...]
Fully Automated Carbonate Petrography Using Deep Convolutional Neural Networks
Published: 2020-06-23
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Geology, Paleobiology, Paleontology, Physical Sciences and Mathematics, Sedimentology
Carbonate rocks are important archives of past ocean conditions as well as hosts of economic resources such as hydrocarbons, water, and minerals. Geologists typically perform compositional analysis of grain, matrix, cement and pore types in order to interpret depositional environments, diagenetic modification, and reservoir quality of carbonate strata. Such information can be obtained primarily [...]
An Ethical Decision-Making Framework with Serious Gaming: Smart Water Case Study on Flooding
Published: 2020-06-23
Subjects: Artificial Intelligence and Robotics, Civil and Environmental Engineering, Civil Engineering, Computer Sciences, Databases and Information Systems, Engineering, Engineering Education, Environmental Engineering, Hydraulic Engineering, Physical Sciences and Mathematics, Theory and Algorithms
Sensors and control technologies are being deployed extensively in both urban water networks and rural river systems, leading to unprecedented ability to sense and control our water environment. Because these sensor networks and control systems allow for higher resolution monitoring and decision making in both time and space, greater discretization of control will allow for an unprecedented [...]
Geological Facies Modeling Based on Progressive Growing of Generative Adversarial Networks (GANs)
Published: 2020-06-22
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Geology, Geophysics and Seismology, Hydrology, Physical Sciences and Mathematics, Sedimentology, Stratigraphy
Geological facies modeling has long been studied to predict subsurface resources. In recent years, generative adversarial networks (GANs) have been used as a new method for geological facies modeling with surprisingly good results. However, in conventional GANs, all layers are trained concurrently, and the scales of the geological features are not considered. In this study, we propose to train [...]
Spatial Statistics on the Geospatial Web
Published: 2020-06-17
Subjects: Computational Engineering, Computer Sciences, Engineering, Physical Sciences and Mathematics
The Geospatial Web provides data as well as processing functionality using web interfaces. Typical examples of such processes are models and predictions for spatial data, known as spatial statistics. Such analyses are written by domain experts in scripting languages and rarely exposed as web services. We present a concept of script annotations for automatic deployment in server runtime [...]
Large model parameter and structural uncertainties in global projections of urban heat waves
Published: 2020-06-10
Subjects: Atmospheric Sciences, Civil and Environmental Engineering, Computer Sciences, Earth Sciences, Engineering, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Risk Analysis, Statistics and Probability
Urban heat waves (UHWs) are strongly associated with socioeconomic impacts. Reliable projections of these extremes are pressingly needed for local actions in the context of extreme event preparedness and mitigation. Such information, however, is not available because current multi-model projections largely lack a representation of urban areas. Here, we use a newly-developed urban climate emulator [...]
Stress Recovery for the Particle-in-cell Finite Element Method
Published: 2020-05-26
Subjects: Applied Mathematics, Computer Sciences, Earth Sciences, Geophysics and Seismology, Mathematics, Numerical Analysis and Computation, Numerical Analysis and Scientific Computing, Physical Sciences and Mathematics, Tectonics and Structure
The interelement stress in the Finite Element Method is not continuous in nature, and stress projections from quadrature points to mesh nodes often causes oscillations. The widely used particle-in-cell method cannot avoid this issue and produces worse results when there are mixing materials of large strength (e.g., viscosity in Stokes problems) contrast in one element. The post-processing methods [...]
Hidden Stories: Topic Modeling in Hydrology Literature
Published: 2020-05-25
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Hydrology, Library and Information Science, Physical Sciences and Mathematics, Social and Behavioral Sciences
Hydrologic research generates large volumes of peer-reviewed literature across a number of evolving sub-topics. It’s becoming increasingly difficult for scientists and practitioners to synthesize this full body of literature. This study explores topic modeling as a form of unsupervised learning applied to 42,154 article-abstracts from six high-impact (Impact Factor > 0.9) journals (Water [...]
Automated Seismic Source Characterisation Using Deep Graph Neural Networks
Published: 2020-05-25
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Geophysics and Seismology, Physical Sciences and Mathematics
Most seismological analysis methods require knowledge of the geographic location of the stations comprising a seismic network. However, common machine learning tools used in seismology do not account for this spatial information, and so there is an underutilised potential for improving the performance of machine learning models. In this work, we propose a Graph Neural Network (GNN) approach that [...]
Addressing Model Data Archiving Needs for the Department of Energy’s Environmental Systems Science Community
Published: 2020-05-08
Subjects: Computer Sciences, Environmental Sciences, Environmental Studies, Physical Sciences and Mathematics, Social and Behavioral Sciences
Researchers in the Department of Energy’s ESS program use a variety of models to advance robust, scale-aware predictions of terrestrial and subsurface ecosystems. ESS projects typically conduct field observations and experiments coupled with modeling exercises using a model-experimental (ModEx) approach that enables iterative co-development of experiments and models, and ensures that experimental [...]
Estimating Submicron Aerosol Mixing State at the Global Scale with Machine Learning and Earth System Modeling
Published: 2020-05-07
Subjects: Atmospheric Sciences, Civil and Environmental Engineering, Computational Engineering, Computer Sciences, Earth Sciences, Engineering, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics
This study integrates machine learning and particle-resolved aerosol simulations to develop emulators that predict sub-micron aerosol mixing state indices from the Earth System Model (ESM) simulations. The emulators predict aerosol mixing state using only ESM bulk aerosol species concentrations, which do not by themselves carry mixing state information. Here we used PartMC as the [...]
SymAE: an autoencoder with embedded physical symmetries for passive time-lapse monitoring
Published: 2020-04-13
Subjects: Applied Mathematics, Computer Sciences, Earth Sciences, Geophysics and Seismology, Physical Sciences and Mathematics
We introduce SymAE, an auto-encoder architecture that learns to separate multichannel passive-seismic datasets into qualitatively interpretable components: one component corresponds to path-specific effects associated with subsurface properties while the other component corresponds to the spectral signature of the passive sources. This information is represented by two latent codes produced by [...]