High solar activity predictions through an artificial neural network

Abstract

The effects of high-energy particles coming from the Sun on human health as well as in the integrity of outer space electronics make the prediction of periods of high solar activity (HSA) a task of significant importance. Since periodicities in solar indexes have been identified, long-term predictions can be achieved. In this paper, we present a method based on an artificial neural network to find a pattern in some harmonics which represent such periodicities. We used data from 1973 to 2010 to train the neural network, and different historical data for its validation. We also used the neural network along with a statistical analysis of its performance with known data to predict periods of HSA with different confidence intervals according to the three-sigma rule associated with solar cycles 24–26, which we found to occur before 2040.

Pattern Recognition Through Empirical Mode Decomposition for Temperature Time Series Between 1986 and 2019 in Mexico City Downtown for Global Warming Assessment

“…3b), while the closest minimum of solar activity was reported almost one year before, at August 28th, 1986 [94], which reinforces this hypothesis. In order to identify if the periodicities found in the subsequent Intrinsic Mode Functions (D i (t) ∀i = 3, • • • , 22) are probably driven by solar activity, they are compared with those reported by [94,95]. The later records, which are obtained from different sun activity indicators as Ground Level Enhancements (GLEs), number of sunspots, etc., are a set of short term periods within the solar activity, and can be observed in Table 4.…”

“…Furthermore, it is interesting to note that the first minimum in such time series occurred at August 23th, 1987 (see Fig. 3b), while the closest minimum of solar activity was reported almost one year before, at August 28th, 1986 [94], which reinforces this hypothesis. In order to identify if the periodicities found in the subsequent Intrinsic Mode Functions (D i (t) ∀i = 3, • • • , 22) are probably driven by solar activity, they are compared with those reported by [94,95].…”

“…In this sense, it is important to note that the last EMD frequency components, D i (t) ∀ i > 10, have shorter periods than those reported by [94,95], so no match can be made. Nevertheless, they constitute themselves a good hint for researches to investigate the existence of such very short periods in the solar activity.…”

“…Comparison of the obtained periods through the application of EMD with those reported in the literature for the solar activity[94,95] for the coincident IMFs, along with the relative error between both.…”

Sistema híbrido basado en redes neuronales artificiales y descomposición modal empírica para la evaluación de la interrelación entre la irradiancia solar total y el calentamiento global

“…De todos estos fenómenos, el mayor forzamiento térmico natural sobre la Tierra es indiscutiblemente la variabilidad solar, misma que ha probado ser multiperiódica [26]. Existen diferentesíndices que pueden dar cuenta de la variabilidad solar como lo son mismos los ciclos solares [4,38,40], las manchas solares [17,41], la presencia de Ground Level Enhancements en los rayos cósmicos solares [2,6,38,46], el viento solar y elíndice geomagnético [14,34], el campo magnético solar [37], entre otros.…”