A data-driven two-microphone method for in situ sound absorption measurements of porous materialsa).

This work presents a data-driven approach to estimating the sound absorption coefficient of an infinite porous slab using a neural network and a two-microphone measurement on a finite porous sample. A one-dimensional-convolutional network predicts the sound absorption coefficient from the complex-valued transfer function between the sound pressure measured at the two microphone positions. The network is trained and validated with numerical data generated by a boundary element model using the Delany-Bazley-Miki model, demonstrating accurate predictions for various numerical samples.

Regional climate projections using a deep-learning-based model-ranking and downscaling framework: application to European climate zones.

Accurate regional climate projection calls for high-resolution downscaling of Global Climate Models (GCMs). This work presents a deep-learning-based multi-model evaluation and downscaling framework ranking 32 Coupled Model Intercomparison Project Phase 6 (CMIP6) models using a Deep Learning-TOPSIS (DL-TOPSIS) mechanism and refines outputs using advanced deep-learning models. Using nine performance criteria, five Köppen-Geiger climate zones-Tropical, Arid, Temperate, Continental, and Polar-are investigated over four seasons.

Aeroacoustic source characterization at fan test facility with spherical harmonics of the half-space.

Acoustic measurements of sources in non-ideal acoustic environments, often the case in industrial product development, issue challenges in source characterization. This study investigates the room-acoustical effects of a bespoke fan test facility on aeroacoustic source characterization via a second-order scheme of spherical harmonics of the half-space. An experimental test of a compact monopole-like sound source reveals the influence of the room's transfer function at low frequencies.

On the representation of wavefronts localized in space-time and wavenumber-frequency domains.

This Letter reports evidence suggesting a representation system for transient waves with band limited spectra, referred to here as localized waves in the space-time and wavenumber-frequency domains. A theoretical analysis with a transient monopole shows that the wavenumber-frequency pressure spectrum is distributed over hyperbolic regions of propagating waves and evanescent waves. An experimental analysis is performed, applying dictionary learning to reverberant sound fields measured with a microphone array in three rooms.

On modified wavenumber filters for rail contribution estimations.

This brief communication exposes an overview of various wavenumber filters to separate the rail contribution to pass-by noise via the wave signature extraction method [Zea, Manzari, Squicciarini, Feng, Thompson, and Lopez Arteaga, J. Sound Vib. , 24-42 (2017)].