Short-Term Turbulence Prediction for Seeing Using Machine Learning

TL;DR

This paper develops machine learning models, including a novel probabilistic approach, to forecast atmospheric turbulence affecting optical systems up to two hours ahead, enhancing decision-making under uncertain conditions.

Contribution

It introduces FloTS, a normalizing flow-based probabilistic deep learning model, and compares it with statistical and neural network methods for short-term turbulence prediction.

Findings

FloTS outperforms other models in accuracy and uncertainty calibration.

Probabilistic models provide valuable uncertainty estimates for turbulence forecasting.

Deep learning approaches, especially FloTS, are effective for short-term atmospheric seeing prediction.

Abstract

Optical turbulence, driven by fluctuations of the atmospheric refractive index, poses a significant challenge to ground-based optical systems, as it distorts the propagation of light. This degradation affects both astronomical observations and free-space optical communications. While adaptive optics systems correct turbulence effects in real-time, their reactive nature limits their effectiveness under rapidly changing conditions, underscoring the need for predictive solutions. In this study, we address the problem of short-term turbulence forecasting by leveraging machine learning models to predict the atmospheric seeing parameter up to two hours in advance. We compare statistical and deep learning approaches, with a particular focus on probabilistic models that not only produce accurate forecasts but also quantify predictive uncertainty, crucial for robust decision-making in dynamic environments. Our evaluation includes Gaussian processes (GP) for statistical modeling, recurrent neural networks (RNNs) and long short-term memory networks (LSTMs) as deterministic baselines, and our novel implementation of a normalizing flow for time series (FloTS) as a flexible probabilistic deep learning method. All models are trained exclusively on historical seeing data, allowing for a fair performance comparison. We show that FloTS achieves the best overall balance between predictive accuracy and well-calibrated uncertainty.