RT Journal Article
T1 A Hybrid Deep Learning Approach for Enhancing the Lorentzian Curve Fit Algorithm for Schumann Resonance
A1 Cano-Domingo, Carlos
A1 Stoean, Ruxandra
A1 Joya-Caparrós, Gonzalo
A1 Novas-Castellano, Nuria
A1 Fernández-Ros, Manuel
A1 Gázquez-Parra, José A.
K1 Redes neuronales artificiales
K1 Aprendizaje automático (Inteligencia artificial)
AB Schumann Resonance (SR) represents a set of very weak signals formed by the electromagnetic wave propagation along the Earth-ionosphere cavity. Traditionally, SR studies have focused on extracting only their first mode using the average frequency spectrum over long segments. However, advances in sensor technology and digitalization now allow for the analysis of multiple modes, which can significantly enhance our understanding and characterization of SR signals. Even in this context, standard techniques, such as Lorentzian Curve Fit (LCF), often fail to retain the characteristics of the signal when the multiple modes are included, especially under harsh weather conditions. This limitation arises from the mathematical challenges of fitting procedures over noisy, highly variable signals, which become more pronounced when extracting more than three modes. In this paper, we put forward a solution to this problem. Its novelty stems from a Deep Learn-ing (DL) methodology based on three different autoencoder strategies andtwo learning schemes to denoise signals, handle multiple SR modes simultaneously,while adapt to their non-stationarity and variability. The resultsdemonstrate that the DL model achieves high performance even when fittinga Lorentzian function is impossible, by effectively extracting multiple SRmodes under challenging conditions. This outcome provides compelling evidencefor further investigation into the use of DL data reduction techniquesfor analyzing SR signals.
PB Elsevier
YR 2025
FD 2025-12-01
LK https://hdl.handle.net/10630/41469
UL https://hdl.handle.net/10630/41469
LA eng
NO Carlos Cano-Domingo, Ruxandra Stoean, Gonzalo Joya, Nuria Novas, Manuel Fernández-Ros, Jose A. Gázquez Parra, A hybrid deep learning approach for enhancing the Lorentzian curve fit algorithm for Schumann resonance, Expert Systems with Applications, Volume 293, 2025, 128681, ISSN 0957-4174, https://doi.org/10.1016/j.eswa.2025.128681. (https://www.sciencedirect.com/science/article/pii/S0957417425022997)
NO Romanian Ministry of Research and Innovation, CCCDI – UEFISCDI, project number 178PCE/2021, PN-III-P4- ID-PCE-2020-0788, within PNCDI III.
NO Electronics Technology Department of the University of Malaga
NO CETPartnership, the European Partnership under Joint Call 2022
NO Ministry of Economics and Competitiveness of Spain financed this work, under Project TEC2014-60132-P, in part by Innovation, Science and Enterprise, Andalusian Regional Government through the Electronics, Communications, and Telemedicine TIC019 Research Group of the University of Almeria, Spain and in part by the European Union FEDER Program and CIAMBITAL Group by I+D+I Project UAL18-TIC-A025-A, the University of Almeria, and the European Regional Development Fund (FEDER).
NO European Commission
NO Ministry of Economics and Competitiveness of Spain
NO University of Almería
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 19 ene 2026