Preprints
Filtering by Subject: Computer Sciences
A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns
Published: 2019-01-01
Subjects: Applied Mathematics, Computer Sciences, Earth Sciences, Engineering, Environmental Sciences, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Planetary Sciences
Convolutional neural networks (CNNs) can potentially provide powerful tools for classifying and identifying patterns in climate and environmental data. However, because of the inherent complexities of such data, which are often spatio-temporal, chaotic, and non-stationary, the CNN algorithms must be designed/evaluated for each specific dataset and application. Yet to start, CNN, a supervised [...]
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 [...]
SSPipeline: A pipeline for estimating and characterizing uncertainty in coastal storm surge levels
Published: 2018-10-22
Subjects: Computer Sciences, Engineering, Numerical Analysis and Scientific Computing, Physical Sciences and Mathematics, Statistical Models, Statistics and Probability
Effective management of coastal risks demands projections of flood hazards that account for a wide variety of potential sources of uncertainty. Two typical approaches for estimating flood hazards include (1) direct physical process-based modeling of the storms themselves and (2) statistical modeling of the distributions and relevant characteristics of extreme sea level events. Recently, flexible [...]
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 [...]
Learning about climate change uncertainty enables flexible water infrastructure planning
Published: 2018-09-29
Subjects: Civil and Environmental Engineering, Civil Engineering, Climate, Computer Sciences, Earth Sciences, Engineering, Environmental Sciences, Hydrology, Numerical Analysis and Scientific Computing, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Statistics and Probability, Water Resource Management
Water resources planning requires making decisions about infrastructure development under substantial uncertainty in future regional climate conditions. However, uncertainty in climate change projections will evolve over the 100-year lifetime of a dam as new climate observations become available. Flexible strategies in which infrastructure is proactively designed to be changed in the future have [...]
Digital photogrammetry of historical aerial photographs using open-source software
Published: 2018-07-06
Subjects: Computer Sciences, Earth Sciences, Geomorphology, Physical Sciences and Mathematics, Programming Languages and Compilers, Software Engineering
Several collections of aerial photographs have been acquired in the Dominican Republic during the last 70 years. Although many of these sources are increasingly becoming available as scanned images, limited digital photogrammetric processing has been done, mainly because of the unaffordable prices of proprietary software licenses and the lack of clear workflows for processing historical photos. [...]
Preparing for the Utilization of Data Science / Data Analytics in Earth Science Research
Published: 2018-06-21
Subjects: Computational Engineering, Computer Sciences, Databases and Information Systems, Education, Engineering, Mathematics, Numerical Analysis and Scientific Computing, Physical Sciences and Mathematics, Science and Mathematics Education, Statistics and Probability
Data analytics is the process of examining large amounts of varying data types to uncover hidden patterns, unknown correlations and other useful information. The Earth Science Information Partners (ESIP) Earth Science Data Analytics (ESDA) Cluster was created to facilitate the co-analysis of Earth science data and information. In addition to pioneering the definition of ESDA, the cluster has [...]
Network Analysis of the American Geophysical Union’s Fall Meetings
Published: 2018-06-20
Subjects: Computer Sciences, Earth Sciences, Numerical Analysis and Scientific Computing, Physical Sciences and Mathematics
The American Geophysical Union (AGU) is an Earth and space science professional society based in the United States. AGU publishes scientific journals, sponsors meetings, and supports education and outreach efforts to promote public understanding of science. Research conducted by AGU members ranges from the Earth’s deep interior to the outer planets of our solar system. Little research exists on [...]
Fish species classification in underwater video monitoring using Convolutional Neural Networks
Published: 2018-05-15
Subjects: Animal Sciences, Aquaculture and Fisheries Life Sciences, Computer Sciences, Environmental Monitoring, Environmental Sciences, Life Sciences, Other Life Sciences, Physical Sciences and Mathematics, Software Engineering
This report presents a case study for automatic fish species classification in underwater video monitoring of fish passes. Although the presented approach is based on the FishCam monitoring system, it can be used with any video-based monitoring system. The presented classification scheme in this study, is based on Convolutional Neural Networks that do not require the calculation of any [...]
Spatial association between regionalizations using the information-theoretical V-measure
Published: 2018-04-19
Subjects: Categorical Data Analysis, Computer Sciences, Environmental Sciences, Geographic Information Sciences, Geography, Numerical Analysis and Scientific Computing, Physical Sciences and Mathematics, Social and Behavioral Sciences, Statistics and Probability, Theory and Algorithms
There is a keen interest in inferring spatial associations between different variables spanning the same study area. We present a method for quantitative assessment of such associations in the case where spatial variables are either in the form of regionalizations or in the form of thematic maps. The proposed index of spatial association – called the V-measure – is adapted from a measure [...]
In-depth examination of spatio-temporal figures in open reproducible research (Preprint)
Published: 2018-04-11
Subjects: Computer Sciences, Earth Sciences, Graphics and Human Computer Interfaces, Physical Sciences and Mathematics
Figures such as maps and time series are essential means to visualize spatio-temporal results in scientific papers. Being able to recompute them using the underlying source code and data is thus a core aspect in reproducible research. However, many scientists see the preparation of code and data for publication as an additional burden without immediate benefits. In this work, we investigate [...]
The Extraordinary Mediocrity of the Holocene
Published: 2018-03-15
Subjects: Climate, Computer Sciences, Earth Sciences, Environmental Sciences, Oceanography and Atmospheric Sciences and Meteorology, Other Physical Sciences and Mathematics, Physical Sciences and Mathematics, Planetary Sciences
The extinction of multiple genera of large-bodied mammals during the Holocene interglacial transition has been attributed to three hypothesized causes: human migration, climate change, and an extra-terrestrial impact. Two of these hypotheses, climate change and extra-terrestrial impactor, would predict that the Holocene interglacial transition was uniquely stressful for large-bodied mammals. To [...]
Global assessment and mapping of changes in mesoscale landscapes: 1992–2015
Published: 2018-02-15
Subjects: Categorical Data Analysis, Computer Sciences, Earth Sciences, Environmental Sciences, Geographic Information Sciences, Geography, Longitudinal Data Analysis and Time Series, Numerical Analysis and Scientific Computing, Physical Sciences and Mathematics, Social and Behavioral Sciences, Spatial Science, Statistics and Probability
Monitoring global land cover changes is important because of concerns about their impact on environment and climate. The release by the European Space Agency (ESA) of a set of worldwide annual land cover maps covering the 1992–2015 period makes possible a quantitative assessment of land change on the global scale. While ESA land cover mapping effort was motivated by the need to better [...]
Towards machine ecoregionalization of Earth’s landmass using pattern segmentation method
Published: 2018-02-15
Subjects: Categorical Data Analysis, Computer Sciences, Earth Sciences, Environmental Sciences, Geographic Information Sciences, Geography, Numerical Analysis and Scientific Computing, Physical Sciences and Mathematics, Social and Behavioral Sciences, Spatial Science, Statistics and Probability
We present and evaluate a quantitative method for delineation of ecophysigraphic regions throughout the entire terrestrial landmass. The method uses the new pattern-based segmentation technique which attempts to emulate the qualitative, weight-of-evidence approach to a delineation of ecoregions in a computer code. An ecophysiographic region is characterized by homogeneous physiography defined by [...]
Multi-scale segmentation algorithm for pattern-based partitioning of large categorical rasters
Published: 2018-01-28
Subjects: Computer Sciences, Earth Sciences, Geography, Numerical Analysis and Scientific Computing, Other Earth Sciences, Physical Sciences and Mathematics, Social and Behavioral Sciences, Spatial Science
Analyzing large Earth Observation (EO) data on the broad spatial scales frequently involves regionalization of patterns. To automate this process we present a segmentation algorithm designed specifically to delineate segments containing quasi-stationary patterns. The algorithm is designed to work with patterns of a categorical variable. This makes it possible to analyze very large spatial [...]