Preprints
Filtering by Subject: Artificial Intelligence and Robotics
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 [...]
RainDisaggGAN - Temporal Disaggregation of Spatial Rainfall Fields with Generative Adversarial Networks
Published: 2020-03-31
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Hydrology, Physical Sciences and Mathematics
Creating spatially coherent rainfall patterns with high temporal resolution from data with lower temporal resolution is an important topic in many geoscientific applications. From a statistical perspective, this presents a high-dimensional and highly under-determined problem. However, recent advances in unsupervised machine learning provide methods for learning such high-dimensional probability [...]
Toward stable, general machine-learned models of the atmospheric chemical system
Published: 2020-03-23
Subjects: Artificial Intelligence and Robotics, Chemistry, Computer Sciences, Earth Sciences, Environmental Chemistry, Environmental Sciences, Physical Sciences and Mathematics
Atmospheric chemistry models—used as components in models that simulate air pollution and climate change—are computationally expensive. Previous studies have shown that machine-learned atmospheric chemical solvers can be orders of magnitude faster than traditional integration methods but tend to suffer from numerical instability. Here, we present a modeling framework that reduces error [...]
Realistic River Image Synthesis using Deep Generative Adversarial Networks
Published: 2020-02-20
Subjects: Artificial Intelligence and Robotics, Civil and Environmental Engineering, Computer Sciences, Engineering, Environmental Engineering, Physical Sciences and Mathematics
In this paper, we investigate an application of image generation for river satellite imagery. Specifically, we propose a generative adversarial network (GAN) model capable of generating high-resolution and realistic river images that can be used to support models in surface water estimation, river meandering, wetland loss and other hydrological research studies. First, we summarized an augmented, [...]
Advanced ML and AI Approaches for Proxy-based Optimization of CO2-Enhanced Oil Recovery in Heterogeneous Clastic Reservoirs
Published: 2019-12-04
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Design of Experiments and Sample Surveys, Earth Sciences, Multivariate Analysis, Other Earth Sciences, Physical Sciences and Mathematics, Programming Languages and Compilers, Statistics and Probability
Constructing a simpler model to represent a complex reservoir simulation that will be employed to define the optimum future development plans have been achieved through the use of different simulation techniques that include EOS-compositional reservoir simulation, Proxy Modeling as well as Design of Experiments. Once reliable history matching was achieved, the key five operational decision [...]
Analog forecasting of extreme-causing weather patterns using deep learning
Published: 2019-07-31
Subjects: Artificial Intelligence and Robotics, Atmospheric Sciences, Computational Engineering, Computer Sciences, Engineering, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics
Numerical weather prediction (NWP) models require ever-growing computing time/resources, but still, have difficulties with predicting weather extremes. Here we introduce a data-driven framework that is based on analog forecasting (prediction using past similar patterns) and employs a novel deep learning pattern-recognition technique (capsule neural networks, CapsNets) and impact-based [...]
Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM
Published: 2019-06-20
Subjects: Applied Mathematics, Artificial Intelligence and Robotics, Atmospheric Sciences, Climate, Computer Sciences, Dynamic Systems, Earth Sciences, Fluid Dynamics, Non-linear Dynamics, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Physics
In this paper, the performance of three deep learning methods for predicting short-term evolution and for reproducing the long-term statistics of a multi-scale spatio-temporal Lorenz 96 system is examined. The methods are: echo state network (a type of reservoir computing, RC-ESN), deep feed-forward artificial neural network (ANN), and recurrent neural network with long short-term memory [...]
Understanding Low Cloud Mesoscale Morphology with an Information Maximizing Generative Adversarial Network
Published: 2019-06-05
Subjects: Artificial Intelligence and Robotics, Atmospheric Sciences, Computer Sciences, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics
Generative adversarial networks (GANs) are a class of machine learning algorithms with two neural networks, one generator and one discriminator, playing adversarial games with each other. Information maximizing GANs (InfoGANs) is a particular GAN type that tries to maximize mutual information between a subset of latent variables and generated samples, thereby establishing a mapping between the [...]
Investigation of the Likelihood of Green Infrastructure (GI) Enhancement along Linear Waterways or on Derelict Sites (DS) Using Machine Learning.
Published: 2019-05-08
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Environmental Monitoring, Environmental Sciences, Geographic Information Sciences, Geography, Physical Sciences and Mathematics, Social and Behavioral Sciences, Spatial Science
Studies evaluating potential of Green Infrastructure (GI) development using traditional Boolean logic-based multi-criteria analysis methods are not capable of predicting future GI development under dynamic urban scape. This study evaluated robust soft-computing-based methods of artificial intelligence (Artificial Neural Network, Adaptive Neuro-Fuzzy Interface-System) and used statistical [...]
Reconstruction of Cloud Vertical Structure with a Generative Adversarial Network
Published: 2019-02-20
Subjects: Artificial Intelligence and Robotics, Atmospheric Sciences, Computer Sciences, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics
We demonstrate the feasibility of solving atmospheric remote sensing problems with machine learning using conditional generative adversarial networks (CGANs), implemented using convolutional neural networks (CNNs). We apply the CGAN to generating two-dimensional cloud vertical structures that would be observed by the CloudSat satellite-based radar, using only the collocated Moderate-Resolution [...]
Gap Filling of High-Resolution Soil Moisture for SMAP/Sentinel-1: A Two-Layer Machine Learning-Based Framework
Published: 2019-02-11
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Environmental Sciences, Hydrology, Physical Sciences and Mathematics, Water Resource Management
As the most recent 3 km soil moisture product from the Soil Moisture Active Passive (SMAP) mission, the SMAP/Sentinel-1 L2_SM_SP product has a unique capability to provide global-scale 3 km soil moisture estimates through the fusion of radar and radiometer microwave observations. The spatial and temporal availability of this high-resolution soil moisture product depends on concurrent radar and [...]
Calibration of astigmatic particle tracking velocimetry based on generalized Gaussian feature extraction
Published: 2018-11-20
Subjects: Artificial Intelligence and Robotics, Computer Sciences, Earth Sciences, Engineering, Fluid Dynamics, Hydrology, Life Sciences, Physical Sciences and Mathematics, Physics
Flow and transport in porous media are driven by pore scale processes. Particle tracking in transparent porous media allows for the observation of these processes at the time scale of ms. We demonstrate an application of defocusing particle tracking using brightfield illumination and a CMOS camera sensor. The resulting images have relatively high noise levels. To address this challenge, we [...]
Quantifying natural delta variability using a multiple-point geostatistics prior uncertainty model
Published: 2018-09-30
Subjects: Artificial Intelligence and Robotics, Civil and Environmental Engineering, Computer Sciences, Earth Sciences, Electrical and Computer Engineering, Engineering, Environmental Engineering, Geology, Geomorphology, Other Civil and Environmental Engineering, Other Engineering, Physical Sciences and Mathematics, Sedimentology, Stratigraphy, Theory and Algorithms
We address the question of quantifying uncertainty associated with autogenic pattern variability in a channelized transport system by means of a modern geostatistical method. This question has considerable relevance for practical subsurface applications as well, particularly those related to uncertainty quantification relying on Bayesian approaches. Specifically, we show how the autogenic [...]
Non-crossing nonlinear regression quantiles by monotone composite quantile regression neural network, with application to rainfall extremes
Published: 2017-12-05
Subjects: Artificial Intelligence and Robotics, Climate, Computer Sciences, Earth Sciences, Hydrology, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Statistical Models, Statistics and Probability
The goal of quantile regression is to estimate conditional quantiles for specified values of quantile probability using linear or nonlinear regression equations. These estimates are prone to "quantile crossing", where regression predictions for different quantile probabilities do not increase as probability increases. In the context of the environmental sciences, this could, for example, lead to [...]