Limits...
MAG4 versus alternative techniques for forecasting active region flare productivity.

Falconer DA, Moore RL, Barghouty AF, Khazanov I - Space Weather (2014)

Bottom Line: We present a statistical method of measuring the difference in performance between MAG4 and comparable alternative techniques that forecast an active region's major-flare productivity from alternative observed aspects of the active region.We find that (1) Present MAG4 far outperforms both McIntosh Active-Region Class and Total Magnetic Flux, (2) Next MAG4 significantly outperforms Present MAG4, (3) the performance of Next MAG4 is insensitive to the forward and backward temporal windows used, in the range of one to a few days, and (4) forecasting from the free-energy proxy in combination with either any broad category of McIntosh active-region classes or any Mount Wilson active-region class gives no significant performance improvement over forecasting from the free-energy proxy alone (Present MAG4).Quantitative comparison of performance of pairs of forecasting techniques Next MAG4 forecasts major flares more accurately than Present MAG4 Present MAG4 forecast outperforms McIntosh AR Class and total magnetic flux.

View Article: PubMed Central - PubMed

Affiliation: Heliophysics and Planetary Science Office ZP13 MSFC/NASA Huntsville, Alabama, USA ; Center for Space Plasma and Aeronomic Research, University of Alabama in Huntsville Huntsville, Alabama, USA.

ABSTRACT

: MAG4 is a technique of forecasting an active region's rate of production of major flares in the coming few days from a free magnetic energy proxy. We present a statistical method of measuring the difference in performance between MAG4 and comparable alternative techniques that forecast an active region's major-flare productivity from alternative observed aspects of the active region. We demonstrate the method by measuring the difference in performance between the "Present MAG4" technique and each of three alternative techniques, called "McIntosh Active-Region Class," "Total Magnetic Flux," and "Next MAG4." We do this by using (1) the MAG4 database of magnetograms and major flare histories of sunspot active regions, (2) the NOAA table of the major-flare productivity of each of 60 McIntosh active-region classes of sunspot active regions, and (3) five technique performance metrics (Heidke Skill Score, True Skill Score, Percent Correct, Probability of Detection, and False Alarm Rate) evaluated from 2000 random two-by-two contingency tables obtained from the databases. We find that (1) Present MAG4 far outperforms both McIntosh Active-Region Class and Total Magnetic Flux, (2) Next MAG4 significantly outperforms Present MAG4, (3) the performance of Next MAG4 is insensitive to the forward and backward temporal windows used, in the range of one to a few days, and (4) forecasting from the free-energy proxy in combination with either any broad category of McIntosh active-region classes or any Mount Wilson active-region class gives no significant performance improvement over forecasting from the free-energy proxy alone (Present MAG4).

Key points: Quantitative comparison of performance of pairs of forecasting techniques Next MAG4 forecasts major flares more accurately than Present MAG4 Present MAG4 forecast outperforms McIntosh AR Class and total magnetic flux.

No MeSH data available.


Related in: MedlinePlus

Comparison of the performance of the four forecasting techniques in terms of their distributions and average values of each of five performance metrics. Each panel is for a different performance metric. The distribution of the measured metric for 2000 runs is shown for each forecasting technique: McIntosh AR Class (blue), Total Magnetic Flux (red), Present MAG4 (black), and Next MAG4 (green). The vertical line shows the average of the distribution, while the horizontal line shows the standard deviation of the distribution. For each metric, the McIntosh AR Class technique and the Total Magnetic Flux technique perform worst (note that a lower value is better for FAR). In all cases Next MAG4 performs best, with Present MAG4 in second place in average value of the metric. For some metrics the difference in performance between some of the techniques is not statistically significant.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4508933&req=5

fig03: Comparison of the performance of the four forecasting techniques in terms of their distributions and average values of each of five performance metrics. Each panel is for a different performance metric. The distribution of the measured metric for 2000 runs is shown for each forecasting technique: McIntosh AR Class (blue), Total Magnetic Flux (red), Present MAG4 (black), and Next MAG4 (green). The vertical line shows the average of the distribution, while the horizontal line shows the standard deviation of the distribution. For each metric, the McIntosh AR Class technique and the Total Magnetic Flux technique perform worst (note that a lower value is better for FAR). In all cases Next MAG4 performs best, with Present MAG4 in second place in average value of the metric. For some metrics the difference in performance between some of the techniques is not statistically significant.

Mentions: In equation 6, the index k2 refers to the Present MAG4 technique. The distributions (Mij(k)), the average (Mj(k)), and standard deviation (σj(k) for each forecasting technique and each metric are shown in Figure 3. In equation 6, it is appropriate to use the standard deviations of the two distributions instead of the standard deviations of the two means, because when the difference between two means is much less than the combined standard deviation of the two distributions (the denominator in equation 6), in almost half of the random division runs the difference in the metric between the two techniques is in the opposite direction to that of the difference in the two means.


MAG4 versus alternative techniques for forecasting active region flare productivity.

Falconer DA, Moore RL, Barghouty AF, Khazanov I - Space Weather (2014)

Comparison of the performance of the four forecasting techniques in terms of their distributions and average values of each of five performance metrics. Each panel is for a different performance metric. The distribution of the measured metric for 2000 runs is shown for each forecasting technique: McIntosh AR Class (blue), Total Magnetic Flux (red), Present MAG4 (black), and Next MAG4 (green). The vertical line shows the average of the distribution, while the horizontal line shows the standard deviation of the distribution. For each metric, the McIntosh AR Class technique and the Total Magnetic Flux technique perform worst (note that a lower value is better for FAR). In all cases Next MAG4 performs best, with Present MAG4 in second place in average value of the metric. For some metrics the difference in performance between some of the techniques is not statistically significant.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4508933&req=5

fig03: Comparison of the performance of the four forecasting techniques in terms of their distributions and average values of each of five performance metrics. Each panel is for a different performance metric. The distribution of the measured metric for 2000 runs is shown for each forecasting technique: McIntosh AR Class (blue), Total Magnetic Flux (red), Present MAG4 (black), and Next MAG4 (green). The vertical line shows the average of the distribution, while the horizontal line shows the standard deviation of the distribution. For each metric, the McIntosh AR Class technique and the Total Magnetic Flux technique perform worst (note that a lower value is better for FAR). In all cases Next MAG4 performs best, with Present MAG4 in second place in average value of the metric. For some metrics the difference in performance between some of the techniques is not statistically significant.
Mentions: In equation 6, the index k2 refers to the Present MAG4 technique. The distributions (Mij(k)), the average (Mj(k)), and standard deviation (σj(k) for each forecasting technique and each metric are shown in Figure 3. In equation 6, it is appropriate to use the standard deviations of the two distributions instead of the standard deviations of the two means, because when the difference between two means is much less than the combined standard deviation of the two distributions (the denominator in equation 6), in almost half of the random division runs the difference in the metric between the two techniques is in the opposite direction to that of the difference in the two means.

Bottom Line: We present a statistical method of measuring the difference in performance between MAG4 and comparable alternative techniques that forecast an active region's major-flare productivity from alternative observed aspects of the active region.We find that (1) Present MAG4 far outperforms both McIntosh Active-Region Class and Total Magnetic Flux, (2) Next MAG4 significantly outperforms Present MAG4, (3) the performance of Next MAG4 is insensitive to the forward and backward temporal windows used, in the range of one to a few days, and (4) forecasting from the free-energy proxy in combination with either any broad category of McIntosh active-region classes or any Mount Wilson active-region class gives no significant performance improvement over forecasting from the free-energy proxy alone (Present MAG4).Quantitative comparison of performance of pairs of forecasting techniques Next MAG4 forecasts major flares more accurately than Present MAG4 Present MAG4 forecast outperforms McIntosh AR Class and total magnetic flux.

View Article: PubMed Central - PubMed

Affiliation: Heliophysics and Planetary Science Office ZP13 MSFC/NASA Huntsville, Alabama, USA ; Center for Space Plasma and Aeronomic Research, University of Alabama in Huntsville Huntsville, Alabama, USA.

ABSTRACT

: MAG4 is a technique of forecasting an active region's rate of production of major flares in the coming few days from a free magnetic energy proxy. We present a statistical method of measuring the difference in performance between MAG4 and comparable alternative techniques that forecast an active region's major-flare productivity from alternative observed aspects of the active region. We demonstrate the method by measuring the difference in performance between the "Present MAG4" technique and each of three alternative techniques, called "McIntosh Active-Region Class," "Total Magnetic Flux," and "Next MAG4." We do this by using (1) the MAG4 database of magnetograms and major flare histories of sunspot active regions, (2) the NOAA table of the major-flare productivity of each of 60 McIntosh active-region classes of sunspot active regions, and (3) five technique performance metrics (Heidke Skill Score, True Skill Score, Percent Correct, Probability of Detection, and False Alarm Rate) evaluated from 2000 random two-by-two contingency tables obtained from the databases. We find that (1) Present MAG4 far outperforms both McIntosh Active-Region Class and Total Magnetic Flux, (2) Next MAG4 significantly outperforms Present MAG4, (3) the performance of Next MAG4 is insensitive to the forward and backward temporal windows used, in the range of one to a few days, and (4) forecasting from the free-energy proxy in combination with either any broad category of McIntosh active-region classes or any Mount Wilson active-region class gives no significant performance improvement over forecasting from the free-energy proxy alone (Present MAG4).

Key points: Quantitative comparison of performance of pairs of forecasting techniques Next MAG4 forecasts major flares more accurately than Present MAG4 Present MAG4 forecast outperforms McIntosh AR Class and total magnetic flux.

No MeSH data available.


Related in: MedlinePlus