Related papers: Towards an Artificial-Intelligence-Based Optical S…
We design an optical feedback network making use of machine learning techniques and demonstrate via simulations its ability to correct for the effects of turbulent propagation on optical modes. This artificial neural network scheme only…
The influence of atmospheric turbulence on acquired imagery makes image interpretation and scene analysis extremely difficult and reduces the effectiveness of conventional approaches for classifying and tracking objects of interest in the…
Adaptive optics (AO) is a technology in modern ground-based optical telescopes to compensate the wavefront distortions caused by atmospheric turbulence. One method that allows to retrieve information about the atmosphere from telescope data…
Accurate characterization of atmospheric optical turbulence is essential for evaluating astronomical sites and optimizing adaptive optics systems. The Multistar Turbulence Monitor (MTM) infers the vertical distribution of the…
Atmospheric turbulence significantly affects imaging systems which use light that has propagated through long atmospheric paths. Images captured under such condition suffer from a combination of geometric deformation and space varying blur.…
Atmospheric turbulence degrades the performance of free-space optical (FSO) communication and remote sensing systems by introducing phase and intensity distortions. While a majority of research focuses on mitigating these effects to ensure…
Knowledge of the optical refractive index structure parameter $C_n^2$ is of interest for Free Space Optics (FSO) and ground-based optical astronomy, as it depicts the strength of the expected scintillation on the received optical waves.…
Coherent imaging through scatter is a challenging task in computational imaging. Both model-based and data-driven approaches have been explored to solve the inverse scattering problem. In our previous work, we have shown that a deep…
We propose a lightweight deep convolutional neural network (lCNN) to estimate cosmological parameters from simulated three-dimensional dark matter (DM) halo distributions and associated statistics. The training dataset comprises 2000…
We parameterize sub-grid scale (SGS) fluxes in sinusoidally forced two-dimensional turbulence on the $\beta$-plane at high Reynolds numbers (Re$\sim$25000) using simple 2-layer Convolutional Neural Networks (CNN) having only…
We explore the potential of feed-forward deep neural networks (DNNs) for emulating cloud superparameterization in realistic geography, using offline fits to data from the Super Parameterized Community Atmospheric Model. To identify the…
High mobility channel estimation is crucial for beyond 5G (B5G) or 6G wireless communication networks. This paper is concerned with channel estimation of high mobility OFDM communication systems. First, a two-dimensional compressed sensing…
We describe a new concept to correct for scintillation noise on high-precision photometry in large and extremely large telescopes using telemetry data from adaptive optics (AO) systems. Most wide-field AO systems designed for the current…
Deep neural networks (DNNs) have achieved superior performance in various prediction tasks, but can be very vulnerable to adversarial examples or perturbations. Therefore, it is crucial to measure the sensitivity of DNNs to various forms of…
CO-SLIDAR is a very promising technique for the metrology of near ground $C_n^2$ profiles. It exploits both phase and scintillation measurements obtained with a dedicated wavefront sensor and allows profiling on the full line of sight…
Recent research efforts in optical computing have gravitated towards developing optical neural networks that aim to benefit from the processing speed and parallelism of optics/photonics in machine learning applications. Among these…
In adaptive optics, the tracker and wavefront sensor commonly measure irradiance centroids (in their respective focal planes) to estimate the turbulence-degraded wavefront in the pupil plane. Several factors affect the accuracy of these…
Recently, deep neural networks (DNNs) have shown advantages in accelerating optimization algorithms. One approach is to unfold finite number of iterations of conventional optimization algorithms and to learn parameters in the algorithms.…
We derive limits for wave optics simulations of plane wave propagation in non-Kolmogorov turbulence using the split-step method and thin phase screens. These limits are used to inform two simulation campaigns where the relationship between…
Turbulence plays an important role in astrophysical phenomena, including core-collapse supernovae (CCSN), but current simulations must rely on subgrid models since direct numerical simulation (DNS) is too expensive. Unfortunately, existing…