The analysis of acoustic wave fields is important for a large number of engineering designs, communication and health-related reasons. The visualization of wavefronts gives valuable information about the type of transducers and excitation signals more suitable for the test itself. This article is dedicated to the development of a fast procedure for acoustic fields visualization in underwater conditions, by means of laser Doppler vibrometer measurements. The ultrasonic probe is a focused transducer excited by a chirp signal. The scope of this work is to evaluate experimentally the properties of the sound beam in order to get reliable information about the transducer itself to be used in many kinds of engineering tests and transducer design.

In the aeronautics sector, aircraft parts are inspected during manufacture, assembly and service, to detect defects eventually present. Defects can be of different types, sizes and orientations, appearing in materials presenting a complex structure. Among the different inspection techniques, Non Destructive Testing (NDT) presents several advantages as they are noninvasive and cost effective. Within the NDT methods, Ultrasonic (US) waves are widely used to detect and characterize defects. However, due the so-called blind zone, they cannot be easily employed for defects close to the surface being inspected. On the other hand, another NDT technique such Eddy Current (EC) can be used only for detecting flaws close to the surface, due to the presence of the EC skin effect. The work presented in this article aims to combine the use of these two NDT methods, exploiting their complementary advantages. To reach this goal, a data fusion method is developed, by using Machine Learning techniques such as Artificial Neural Networks (ANNs). A simulated training database involving simulations of US and EC signals propagating in an Aluminum block in the presence of Side Drill Holes (SDHs) has been implemented, to train the ANNs. Measurements have been then performed on an Aluminum block, presenting tree different SDHs at specific depths. The trained ANNs were used to characterize the different real SDHs, providing an experimental validation. Eventually, particular attention has been addressed to the estimation errors corresponding to each flaw. Experimental results will show that depths and radii estimations error were confined on average within a range of 4%, recording a peak of 11% for the second SDHs.

Explosive volcanic blasts can occur suddenly and without any clear precursors. Many volcanoes have erupted in the last years with no evident change in the eruptive parameters and with dramatic consequences for the population living nearby the volcano and the tourists visiting the active areas. In recent years, a big effort has been made to develop Early Warning systems to issue timely alerts to the population. At Stromboli volcano, the development of sensitive instruments to measure the deformation (tilt) of the ground has revealed that the volcano edifice is inflating tens of minutes before the explosion following a recurrent exponential ramp-like pattern. This scale-invariant of ground deformation has allowed the development of a quasi-deterministic Early Warning system which is operative since 2019. In this article we show how Artificial Intelligence and Machine Learning can be successfully applied to improve the efficiency and the sensitivity of Early Warning systems, provided the availability of a comprehensive experimental data set on past explosive events. The approach presented here for the Stromboli case demonstrates promising results also in forecasting the intensity of explosive events, offering valuable insights and new perspectives into the potential risks associated with volcanic activities.

Multimodal sensing is essential in order to reach the robustness required of autonomous vehicle perception systems. Infrared (IR) imaging is of particular interest due to its low cost and complementarity with traditional RGB sensors. However, the lack of IR data in many datasets and simulation tools limits the development and validation of sensor fusion algorithms that exploit this complementarity. To address this, we propose an augmentation method that synthesizes realistic IR data from RGB images using gradient-boosting decision trees. We demonstrate that this method is an effective alternative to traditional deep learning methods for image translation such as CNNs and GANs, particularly in data-scarce situations. The proposed approach generates high-quality synthetic IR, i.e., Near-Infrared (NIR) and thermal images from RGB images, enhancing datasets such as MS2, EPFL, and Freiburg. Our synthetic images exhibit good visual quality when evaluated using metrics such as $R^2$, PSNR, SSIM, and LPIPS, achieving an $R^2$ of 0.98 on the MS2 dataset and a PSNR of $21.3$ dB on the Freiburg dataset. We also discuss the application of this method to synthetic RGB images generated by the CARLA simulator for autonomous driving. Our approach provides richer datasets with a particular focus on IR modalities for sensor fusion along with a framework for generating a wider variety of driving scenarios within urban driving datasets, which can help to enhance the robustness of sensor fusion algorithms.