Stephen Brown

Stephen Brown, William L. Rodi, Marco Seracini et al.

We consider the application of machine learning to the evaluation of geothermal resource potential. A supervised learning problem is defined where maps of 10 geological and geophysical features within the state of Nevada, USA are used to define geothermal potential across a broad region. We have available a relatively small set of positive training sites (known resources or active power plants) and negative training sites (known drill sites with unsuitable geothermal conditions) and use these to constrain and optimize artificial neural networks for this classification task. The main objective is to predict the geothermal resource potential at unknown sites within a large geographic area where the defining features are known. These predictions could be used to target promising areas for further detailed investigations. We describe the evolution of our work from defining a specific neural network architecture to training and optimization trials. Upon analysis we expose the inevitable problems of model variability and resulting prediction uncertainty. Finally, to address these problems we apply the concept of Bayesian neural networks, a heuristic approach to regularization in network training, and make use of the practical interpretation of the formal uncertainty measures they provide.

M. Saleem, Hugo Valle, Stephen Brown et al.

In the era of Big Data, with the increasing use of large-scale data-driven applications, the visualization of very large high-resolution images and extracting useful information (searching for specific targets or rare signal events) from these images can pose challenges to the current video-wall display technologies. At Bellarmine University, we have set up an Advanced Visualization and Computational Lab (AVCL) using a state-of-the-art next generation video-wall technology, called Hiperwall (Highly Interactive Parallelized Display Wall). The 16 feet wide by 4.5 feet high Hiperwall visualization system consists of eight display tiles that are arranged in a 4x2 tile format and has an effective resolution of 16.5 Megapixels. Using Hiperwall, we can perform interactive visual data analytics of large images by conducting comparative views of multiple large images in Astronomy and multiple data events in experimental High Energy Physics (HEP). Users can display a single large image across all the display tiles, or view many different images simultaneously on multiple display tiles. Hiperwall enables simultaneous visualization of multiple high resolution images and its contents on the entire display wall without loss of clarity. Hiperwall's middleware also allows researchers in geographically diverse locations to collaborate on large scientific experiments. In this paper we will provide a description of a new generation of display wall setup at Bellarmine University that is based on the Hiperwall technology, which is a robust visualization system for Big Data research.

Joey McCollum, Stephen Brown

The text-critical practice of grouping witnesses into families or texttypes often faces two obstacles: Contamination in the manuscript tradition, and co-dependence in identifying characteristic readings and manuscripts. We introduce non-negative matrix factorization (NMF) as a simple, unsupervised, and efficient way to cluster large numbers of manuscripts and readings simultaneously while summarizing contamination using an easy-to-interpret mixture model. We apply this method to an extensive collation of the New Testament epistle of Jude and show that the resulting clusters correspond to human-identified textual families from existing research.