Contingency Space: A Semimetric Space for Classification Evaluation.

In Machine Learning, a supervised model's performance is measured using the evaluation metrics. In this study, we first present our motivation by revisiting the major limitations of these metrics, namely one-dimensionality, lack of context, lack of intuitiveness, uncomparability, binary restriction, and uncustomizability of metrics. In response, we propose Contingency Space, a bounded semimetric space that provides a generic representation for any performance evaluation metric. Then we showcase how this space addresses the limitations. In this space, each metric forms a surface using which we visually compare different evaluation metrics. Taking advantage of the fact that a metric's surface warps proportionally to the degree of which it is sensitive to the class-imbalance ratio of data, we introduce Imbalance Sensitivity that quantifies the skew-sensitivity. Since an arbitrary model is represented in this space by a single point, we introduce Learning Path for qualitative and quantitative analyses of the training process. Using the semimetric that contingency space is endowed with, we introduce Tau as a new cost sensitive and Imbalance Agnostic metric. Lastly, we show that contingency space addresses multi-class problems as well. Throughout this work, we define each concept through stipulated definitions and present every application with practical examples and visualizations.

Multivariate time series dataset for space weather data analytics.

We introduce and make openly accessible a comprehensive, multivariate time series (MVTS) dataset extracted from solar photospheric vector magnetograms in Spaceweather HMI Active Region Patch (SHARP) series. Our dataset also includes a cross-checked NOAA solar flare catalog that immediately facilitates solar flare prediction efforts. We discuss methods used for data collection, cleaning and pre-processing of the solar active region and flare data, and we further describe a novel data integration and sampling methodology. Our dataset covers 4,098 MVTS data collections from active regions occurring between May 2010 and December 2018, includes 51 flare-predictive parameters, and integrates over 10,000 flare reports. Potential directions toward expansion of the time series, either "horizontally" - by adding more prediction-specific parameters, or "vertically" - by generalizing flare into integrated solar eruption prediction, are also explained. The immediate tasks enabled by the disseminated dataset include: optimization of solar flare prediction and detailed investigation for elusive flare predictors or precursors, with both operational (research-to-operations), and basic research (operations-to-research) benefits potentially following in the future.

The unusual minimum of sunspot cycle 23 caused by meridional plasma flow variations.

Direct observations over the past four centuries show that the number of sunspots observed on the Sun's surface varies periodically, going through successive maxima and minima. Following sunspot cycle 23, the Sun went into a prolonged minimum characterized by a very weak polar magnetic field and an unusually large number of days without sunspots. Sunspots are strongly magnetized regions generated by a dynamo mechanism that recreates the solar polar field mediated through plasma flows. Here we report results from kinematic dynamo simulations which demonstrate that a fast meridional flow in the first half of a cycle, followed by a slower flow in the second half, reproduces both characteristics of the minimum of sunspot cycle 23. Our model predicts that, in general, very deep minima are associated with weak polar fields. Sunspots govern the solar radiative energy and radio flux, and, in conjunction with the polar field, modulate the solar wind, the heliospheric open flux and, consequently, the cosmic ray flux at Earth.