• Rudra Krishna

Accurate seismic signal analysis is vital for earthquake detection, subsurface imaging, and geotechnical assessments. However, field-acquired seismic data is often contaminated by various noise sources. Traditional low-pass filters, like sinc-based FIR filters, reduce high-frequency noise but may distort signal features. This study presents a hybrid denoising approach combining a sinc FIR filter with a machine learning (ML) enhancement using a linear regression (LinearFit) model. A clean seismic signal was simulated and degraded with additive white Gaussian noise, then sequentially processed through the sinc filter and ML model. Results show that while the sinc filter effectively suppresses noise, the LinearFit ML model further reduces residual errors and better preserves signal integrity, offering an efficient and interpretable tool for seismic signal denoising

Seismic Denoising, Sinc Filter, Linear Regression, Machine Learning, Signal Processing, MATLAB, Gaussian

"Hybrid Signal Denoising in Seismic Applications Using Sinc Filtering and Machine Learning Regression", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.f553-f559, March-2025, Available :http://www.jetir.org/papers/JETIR2503594.pdf

"Hybrid Signal Denoising in Seismic Applications Using Sinc Filtering and Machine Learning Regression", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppf553-f559, March-2025, Available at : http://www.jetir.org/papers/JETIR2503594.pdf