A statistical interpolation code for ocean analysis and forecasting

We present a data assimilation package for use with ocean circulation models in analysis, forecasting and system evaluation applications. The basic functionality of the package is centered on a multivariate linear statistical estimation for a given predicted/background ocean state, observations and error statistics. Novel features of the package include support for multiple covariance models, and the solution of the least squares normal equations either using the covariance matrix or its inverse - the information matrix. The main focus of this paper, however, is on the solution of the analysis equations using the information matrix, which offers several advantages for solving large problems efficiently. Details of the parameterization of the inverse covariance using Markov Random Fields are provided and its relationship to finite difference discretizations of diffusion equations are pointed out. The package can assimilate a variety of observation types from both remote sensing and in-situ platforms. The performance of the data assimilation methodology implemented in the package is demonstrated with a yearlong global ocean hindcast with a 1/4°ocean model. The code is implemented in modern Fortran, supports distributed memory, shared memory, multi-core architectures and uses Climate and Forecasts compliant Network Common Data Format for Input/Output. The package is freely available with an open source license from www.tendral.com/tsis/

Matlab Software for Supervised Habitat Mapping of Freshwater Systems Using Image Processing

We present a software package for the supervised classification of images useful for cover-type mapping of freshwater habitat (e.g., water surface, gravel bars, vegetation). The software allows the user to select a representative subset of pixels within a specific area of interest in the image that the user has identified as a cover-type habitat of interest. We developed a graphical user interface (GUI) that allows the user to select single pixels using a dot, line, or group of pixels within a defined polygon that appears to the user to have a spectral similarity. Histogram plots for each band of the selected ground-truth subset aid the user in determining whether to accept or reject it as input data for the classification processes. A statistical model, or classifier, is then built using this pixel subset to assign every pixel in the image to a best-fit group based on reflectance or spectral similarity. Ideally, a classifier incorporates both spectral and spatial information. In our software, we implement quadratic discriminant analysis (QDA) for spectral classification and choose three spatial methods—mode filtering, probability label relaxation, and Markov random fields—to incorporate spatial context after computation of the spectral type. This multi-step interactive process makes the software quantitatively robust, broadly applicable, and easily usable for cover-type mapping of rivers, their floodplains, wetlands often components of these functionally linked freshwater systems. Indeed, this supervised classification approach is helpful for a wide range of cover-type mapping applications in freshwater systems but also estuarine and coastal systems as well. However, it can also aid many other applications, specifically for automatic and quantitative extraction of pixels that represent the water surface area of rivers and floodplains.

Optimizing image segmentation of pavement defects using graph-based method

Pavement defect detection and classification systems based on machine learning algorithms are already very advanced and are increasingly demonstrating their outstanding advantages. One of the most important steps in the processing is image segmentation. In this paper, some image segmentation algorithms used in practice are presented, compared and evaluated. The advantages and disadvantages of each algorithm are evaluated and compared based on the criteria PA, MPA, F1. We propose a method to optimize the process of image segmentation of pavement defects using a combination of Markov Random Fields and graph theory. Experiments were conducted on 3 datasets from Portugal, Russia and Vietnam. Empirical results show that the segmentation of pavement defects is more accurate and effective when the two methods are combined.

Spatial and Temporal Modelling of Hoki Distribution using Gaussian Markov Random Fields

<p>In order to carry out assessment of marine stock levels, an accurate estimate of the current year's population abundance must be formulated. Standardized catch per unit of effort (CPUE) values are, in theory, proportional to population abundance. However, this only holds if the species catchability is constant over time. In almost all cases it is not, due to the existence of spatial and temporal variation. In this thesis, we fit various models to test different combinations and structures of spatial and temporal autocorrelation within hoki (Macruronus novaezelandiae) CPUE. A Bayesian approach was taken, and the spatial and temporal components were modelled using Gaussian Markov random fields. The data was collected from summer research trawl surveys carried out by the National Institute of Water and Atmospheric Research (NIWA) and the Ministry for Primary Industries (MPI). It allowed us to model spatial distribution using both areal and point reference approaches. To fit the models, we used the software Stan (Gelman et al., 2015) which implements Hamiltonian Monte Carlo. Model comparison was carried out using the Watanabe-Akaike information criterion (WAIC, (Watanabe, 2010)). We found that trawl year was the most important factor to explain variation in research survey hoki CPUE. Furthermore, the areal approach provided better indices of abundance than the point reference approach.</p>

Spatial and Temporal Modelling of Hoki Distribution using Gaussian Markov Random Fields

<p>In order to carry out assessment of marine stock levels, an accurate estimate of the current year's population abundance must be formulated. Standardized catch per unit of effort (CPUE) values are, in theory, proportional to population abundance. However, this only holds if the species catchability is constant over time. In almost all cases it is not, due to the existence of spatial and temporal variation. In this thesis, we fit various models to test different combinations and structures of spatial and temporal autocorrelation within hoki (Macruronus novaezelandiae) CPUE. A Bayesian approach was taken, and the spatial and temporal components were modelled using Gaussian Markov random fields. The data was collected from summer research trawl surveys carried out by the National Institute of Water and Atmospheric Research (NIWA) and the Ministry for Primary Industries (MPI). It allowed us to model spatial distribution using both areal and point reference approaches. To fit the models, we used the software Stan (Gelman et al., 2015) which implements Hamiltonian Monte Carlo. Model comparison was carried out using the Watanabe-Akaike information criterion (WAIC, (Watanabe, 2010)). We found that trawl year was the most important factor to explain variation in research survey hoki CPUE. Furthermore, the areal approach provided better indices of abundance than the point reference approach.</p>

Multi-feature data repository development and analytics for image cosegmentation in high-throughput plant phenotyping

Cosegmentation is a newly emerging computer vision technique used to segment an object from the background by processing multiple images at the same time. Traditional plant phenotyping analysis uses thresholding segmentation methods which result in high segmentation accuracy. Although there are proposed machine learning and deep learning algorithms for plant segmentation, predictions rely on the specific features being present in the training set. The need for a multi-featured dataset and analytics for cosegmentation becomes critical to better understand and predict plants’ responses to the environment. High-throughput phenotyping produces an abundance of data that can be leveraged to improve segmentation accuracy and plant phenotyping. This paper introduces four datasets consisting of two plant species, Buckwheat and Sunflower, each split into control and drought conditions. Each dataset has three modalities (Fluorescence, Infrared, and Visible) with 7 to 14 temporal images that are collected in a high-throughput facility at the University of Nebraska-Lincoln. The four datasets (which will be collected under the CosegPP data repository in this paper) are evaluated using three cosegmentation algorithms: Markov random fields-based, Clustering-based, and Deep learning-based cosegmentation, and one commonly used segmentation approach in plant phenotyping. The integration of CosegPP with advanced cosegmentation methods will be the latest benchmark in comparing segmentation accuracy and finding areas of improvement for cosegmentation methodology.