Search for: All records

We develop, advance, and promote a previously existing framework called the Qualitative-Quantitative-Qualitative workflow (Q1Q2Q3, pronounced “Q-Q-Q”) to systematically guide the content of interdisciplinary collaborations and improve the teaching of statistics and data science. The Q1Q2Q3 workflow is designed to help statisticians and data scientists develop skills and techniques for collaboration to work with domain experts across academic fields, industry sectors, and organizations. The Q1Q2Q3 workflow explicitly emphasizes the importance of the qualitative context of a project, as well as the qualitative interpretation of quantitative findings. We explain Q1Q2Q3 and provide guidance for implementing each stage of the workflow. We describe how we teach Q1Q2Q3 within a statistics and data science collaboration course and present data evaluating its effectiveness. We also describe how Q1Q2Q3 can be useful for educators teaching introductory, projects-based, and technical statistics and data science courses. We believe that the Q1Q2Q3 workflow is an easy-to-implement technique that is beneficial and necessary for statistics and data science education and practice. It can be used to weave ethics into each stage of practice so that statisticians and data scientists can successfully transform evidence into action for the benefit of society. 

The explosive growth in supercomputers capacity has changed simulation paradigms. Simulations have shifted from a few lengthy ones to an ensemble of multiple simulations with varying initial conditions or input parameters. Thus, an ensemble consists of large volumes of multi-dimensional data that could go beyond the exascale boundaries. However, the disparity in growth rates between storage capabilities and computing resources results in I/O bottlenecks. This makes it impractical to utilize conventional postprocessing and visualization tools for analyzing such massive simulation ensembles. In situ visualization approaches alleviate I/O constraints by saving predetermined visualizations in image databases during simulation. Nevertheless, the unavailability of output raw data restricts the flexibility of post hoc exploration of in situ approaches. Much research has been conducted to mitigate this limitation, but it falls short when it comes to simultaneously exploring and analyzing parameter and ensemble spaces. In this paper, we propose an expert-in-the-loop visual exploration analytic approach. The proposed approach leverages: feature extraction, deep learning, and human expert–AI collaboration techniques to explore and analyze image-based ensembles. Our approach utilizes local features and deep learning techniques to learn the image features of ensemble members. The extracted features are then combined with simulation input parameters and fed to the visualization pipeline for in-depth exploration and analysis using human expert + AI interaction techniques. We show the effectiveness of our approach using several scientific simulation ensembles. 

Abstract The auroral substorm has been extensively studied over the last six decades. However, our understanding of its driving mechanisms is still limited and so is our ability to accurately forecast its onset. In this study, we present the first deep learning‐based approach to predict the onset of a magnetic substorm, defined as the signature of the auroral electrojets in ground magnetometer measurements. Specifically, we use a time history of solar wind speed (V_x), proton number density, and interplanetary magnetic field (IMF) components as inputs to forecast the occurrence probability of an onset over the next 1 hr. The model has been trained and tested on a data set derived from the SuperMAG list of magnetic substorm onsets and can correctly identify substorms ∼75% of the time. In contrast, an earlier prediction algorithm correctly identifies ∼21% of the substorms in the same data set. Our model's ability to forecast substorm onsets based on solar wind and IMF inputs prior to the actual onset time, and the trend observed in IMFB_zprior to onset together suggest that a majority of the substorms may not be externally triggered by northward turnings of IMF. Furthermore, we find that IMFB_zandV_xhave the most significant influence on model performance. Finally, principal component analysis shows a significant degree of overlap in the solar wind and IMF parameters prior to both substorm and nonsubstorm intervals, suggesting that solar wind and IMF alone may not be sufficient to forecast all substorms, and preconditioning of the magnetotail may be an important factor.