Gradient damage processes in cementitious materials are generally produced by chemical and/or physical processes that travel from outside to inside. Depending on the type of damage, it can cause different effects such as decreased porosity, cracking, or steel corrosion in the case of carbonation, or increased porosity, micro-cracks, expansion, and spalling (also present in thermal damage) in the case of external attack by sulphates or acid attack. Therefore, estimating the boundaries of this damage is an essential task for concrete quality assessment. The first objective of this work was to use neural networks (NNs) for ultrasound tomographic reconstruction of concrete samples in order to estimate the advance front in gradient damage. Unlike the usual X-ray tomography, ultrasound tomography is affected by diffraction, among other factors. NNs can learn to compensate for these effects; however, they require a large amount of training data to achieve accurate results. In the case of cement-based materials, obtaining and measuring a real training database could be complicated, expensive, and time-consuming. For this purpose, a training process using simulated measurements was carried out. The second objective of this work was to demonstrate the feasibility of training neural networks through simulations, which reduces costs. Finally, the trained neural network for tomographic reconstruction was evaluated using real cylindrical concrete specimens. Each specimen consisted of an outer cylinder, representing externally exposed cement, and an inner cylinder, simulating the unaffected core. The Structural Similarity Index (SSIM) was used as a metric to assess the reconstruction accuracy, achieving values of 0.95 for simulated signals and up to 0.82 for real signals.

The development of automatic detection algorithms for fish vocalizations is essential for advancing passive acoustic monitoring and improving our understanding of marine soundscapes. We present an acoustic-feature-based detection framework that combines acoustic entropy and envelope modulation analysis to identify repetitive fish vocalizations in complex coastal environments. The framework was applied to passive acoustic recordings collected in the Cabo de San Antonio Marine Reserve (Spain), an area characterized by dynamic soundscapes and intense vessel traffic. Detection operates through two complementary configurations: an entropy-based mode that identifies temporally coherent low-entropy events, and a combined entropy–envelope modulation mode that validates detections using the relationship between the pulse repetition frequency (f₀) and its second-order modulation component (2·f₀). The combined configuration substantially reduced false-positive detections while simultaneously increasing true-positive detections and reducing false negatives. Event-level evaluation yielded a precision of 0.71, recall of 0.96, and F1-score of 0.82, compared with 0.52, 0.91, and 0.66, respectively, for the entropy-only configuration. Detected signals showed a marked nocturnal pattern with activity peaks around sunset. Their pulse period, peak frequency, and nocturnal occurrence were consistent with published descriptions of Sciaena umbra vocalizations, suggesting this species as a potential biological source while acknowledging that species-level attribution cannot be established from passive acoustic data alone. Overall, the proposed framework provides an interpretable feature-based approach for detecting structured fish vocalizations under the acoustically challenging conditions represented in this dataset.