Extreme geomagnetic storms: Probabilistic forecasts and their uncertainties. Issue 1 (10th January 2017)

• Record Type: Journal Article
• Authors: Riley, Pete; Love, Jeffrey J.
• Is Part Of: Space weather. Volume 15:Issue 1(2017:Jan.)
• Page Start: 53
• Page End: 64
• Publication Date: 2017-01-10
• Subjects: extreme events -- geomagnetic storms -- space weather; Space environment -- Periodicals; 551.509992
• DOI: 10.1002/2016SW001470
• Languages: English
• ISSNs: 1542-7390

Abstract

Abstract: Extreme space weather events are low‐frequency, high‐risk phenomena. Estimating their rates of occurrence, as well as their associated uncertainties, is difficult. In this study, we derive statistical estimates and uncertainties for the occurrence rate of an extreme geomagnetic storm on the scale of the Carrington event (or worse) occurring within the next decade. We model the distribution of events as either a power law or lognormal distribution and use (1) Kolmogorov‐Smirnov statistic to estimate goodness of fit, (2) bootstrapping to quantify the uncertainty in the estimates, and (3) likelihood ratio tests to assess whether one distribution is preferred over another. Our best estimate for the probability of another extreme geomagnetic event comparable to the Carrington event occurring within the next 10 years is 10.3% 95% confidence interval (CI) [0.9, 18.7] for a power law distribution but only 3.0% 95% CI [0.6, 9.0] for a lognormal distribution. However, our results depend crucially on (1) how we define an extreme event, (2) the statistical model used to describe how the events are distributed in intensity, (3) the techniques used to infer the model parameters, and (4) the data and duration used for the analysis. We test a major assumption that the data represent time stationary processes and discuss the implications. If the current trends persist, suggesting that we are entering a period of lower activity, our forecasts may represent upper limits rather than best estimates. Key Points: The probability of another extreme event is sensitive to the definition of "extreme" Likelihood of a Carrington event ( Dst < −850) over the next decade is 10.3% 95% CI [0.9, 18.7] The uncertainties and assumptions used to derive forecasts are equally important