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

Empirically derived forecasting curves for three forecasting techniques. (left) Forecasting curve for forecasting based on total magnetic flux. (middle) Forecasting curve for forecasting based on free-energy proxy only. (right) Forecasting curves for forecasting based on free-energy proxy combined with previous flare activity (black: for ARs that have had no recent X- or M-class flares and orange: for ARs that have had recent X- or M-class flares). The 40,000 magnetograms are sorted by either total magnetic flux in Figure 2, left, or free-energy proxy in Figure 2, middle and right, and then binned. A diamond is centered on the average measure and average event rate in each bin having total magnetic flux LΦ > 1022 Mx or free-energy proxy LWLSG > 104 G. The vertical line in each bin is the 1σ uncertainty in the event rate based on Poisson statistics. Each dashed line is a least squares linear fit through the diamonds.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

fig02: Empirically derived forecasting curves for three forecasting techniques. (left) Forecasting curve for forecasting based on total magnetic flux. (middle) Forecasting curve for forecasting based on free-energy proxy only. (right) Forecasting curves for forecasting based on free-energy proxy combined with previous flare activity (black: for ARs that have had no recent X- or M-class flares and orange: for ARs that have had recent X- or M-class flares). The 40,000 magnetograms are sorted by either total magnetic flux in Figure 2, left, or free-energy proxy in Figure 2, middle and right, and then binned. A diamond is centered on the average measure and average event rate in each bin having total magnetic flux LΦ > 1022 Mx or free-energy proxy LWLSG > 104 G. The vertical line in each bin is the 1σ uncertainty in the event rate based on Poisson statistics. Each dashed line is a least squares linear fit through the diamonds.

Mentions: To make a forecast based on two parameters (as in Next MAG4), where the second parameter has only two discrete states, we first group the sample by the second parameter: for example, whether the active region has or has not produced an X- or M-class flare in the previous 24 h (Tb = 24 h) before the time of the magnetogram, and for each group obtain a separate forecasting curve (Figure 2). That is, in this example, we obtain one forecasting curve for the recently flaring active regions and another forecasting curve for the active regions that have not recently flared. If the two forecasting curves are essentially the same, this implies that the secondary parameter does not provide additional information that improves the performance over that of the forecasting technique that is based on only the primary parameter. When the two forecasting curves differ by a statistically significant amount, this indicates that the two-parameter technique performs better than the corresponding single-parameter technique. Depending on the relative sample size and the relative number of events, the number of bins used might be different for the two forecasting curves, as is the case in the present example.


MAG4 versus alternative techniques for forecasting active region flare productivity.

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

Empirically derived forecasting curves for three forecasting techniques. (left) Forecasting curve for forecasting based on total magnetic flux. (middle) Forecasting curve for forecasting based on free-energy proxy only. (right) Forecasting curves for forecasting based on free-energy proxy combined with previous flare activity (black: for ARs that have had no recent X- or M-class flares and orange: for ARs that have had recent X- or M-class flares). The 40,000 magnetograms are sorted by either total magnetic flux in Figure 2, left, or free-energy proxy in Figure 2, middle and right, and then binned. A diamond is centered on the average measure and average event rate in each bin having total magnetic flux LΦ > 1022 Mx or free-energy proxy LWLSG > 104 G. The vertical line in each bin is the 1σ uncertainty in the event rate based on Poisson statistics. Each dashed line is a least squares linear fit through the diamonds.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

fig02: Empirically derived forecasting curves for three forecasting techniques. (left) Forecasting curve for forecasting based on total magnetic flux. (middle) Forecasting curve for forecasting based on free-energy proxy only. (right) Forecasting curves for forecasting based on free-energy proxy combined with previous flare activity (black: for ARs that have had no recent X- or M-class flares and orange: for ARs that have had recent X- or M-class flares). The 40,000 magnetograms are sorted by either total magnetic flux in Figure 2, left, or free-energy proxy in Figure 2, middle and right, and then binned. A diamond is centered on the average measure and average event rate in each bin having total magnetic flux LΦ > 1022 Mx or free-energy proxy LWLSG > 104 G. The vertical line in each bin is the 1σ uncertainty in the event rate based on Poisson statistics. Each dashed line is a least squares linear fit through the diamonds.
Mentions: To make a forecast based on two parameters (as in Next MAG4), where the second parameter has only two discrete states, we first group the sample by the second parameter: for example, whether the active region has or has not produced an X- or M-class flare in the previous 24 h (Tb = 24 h) before the time of the magnetogram, and for each group obtain a separate forecasting curve (Figure 2). That is, in this example, we obtain one forecasting curve for the recently flaring active regions and another forecasting curve for the active regions that have not recently flared. If the two forecasting curves are essentially the same, this implies that the secondary parameter does not provide additional information that improves the performance over that of the forecasting technique that is based on only the primary parameter. When the two forecasting curves differ by a statistically significant amount, this indicates that the two-parameter technique performs better than the corresponding single-parameter technique. Depending on the relative sample size and the relative number of events, the number of bins used might be different for the two forecasting curves, as is the case in the present example.

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