arXiv subjects

Rudolf Saathof

Publications and source records attributed to Rudolf Saathof.

4 recordsLinked to original sources

arXiv2026

OTProf: estimating high-resolution profiles of optical turbulence ($C_n^2$) from reanalysis using deep learning

Accurate high-resolution vertical profiles of optical turbulence ($C_n^2$), which reflect local meteorology and topography, are crucial for ground-based optical astronomy and free-space optical communication. However, measuring these profiles or generating them with numerical weather models requires substantial operational or computational effort. In this work, we present OTProf, a deep-learning method that estimates high-resolution $C_n^2$ profiles from widely available coarse-resolution ERA5 reanalysis data. We evaluate the approach in the Netherlands and compare it with the commonly used Hufnagel-Valley model. Overall, OTProf reproduces the vertical structure of $C_n^2$ more accurately than Hufnagel-Valley and yields more accurate estimates of the Fried parameter $r_0$ and the scintillation index $\sigma_I^2$. As typical in machine learning, the $C_n^2$ predictions are slightly smoothed compared to reference data, especially in cases of rare strong turbulence. This smoothing affects the integrated parameters, sometimes leading to overly optimistic $r_0$ and $\sigma_I^2$ values. Despite this limitation, OTProf offers a more accurate, efficient, and physically consistent alternative to traditional analytical models and computationally expensive mesoscale models.

physics.ao-ph↗

arXiv2025

Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling

Kilometer-scale weather data is crucial for real-world applications but remains computationally intensive to produce using traditional weather simulations. An emerging solution is to use deep learning models, which offer a faster alternative for climate downscaling. However, their reliability is still in question, as they are often evaluated using standard machine learning metrics rather than insights from atmospheric and weather physics. This paper benchmarks recent state-of-the-art deep learning models and introduces physics-inspired diagnostics to evaluate their performance and reliability, with a particular focus on geographic generalization and physical consistency. Our experiments show that, despite the seemingly strong performance of models such as CorrDiff, when trained on a limited set of European geographies (e.g., central Europe), they struggle to generalize to other regions such as Iberia, Morocco in the south, or Scandinavia in the north. They also fail to accurately capture second-order variables such as divergence and vorticity derived from predicted velocity fields. These deficiencies appear even in in-distribution geographies, indicating challenges in producing physically consistent predictions. We propose a simple initial solution: introducing a power spectral density loss function that empirically improves geographic generalization by encouraging the reconstruction of small-scale physical structures. The code for reproducing the experimental results can be found at https://github.com/CarloSaccardi/PSD-Downscaling

cs.LG↗

arXiv2024

OTCliM: generating a near-surface climatology of optical turbulence strength ($C_n^2$) using gradient boosting

This study introduces OTCliM (Optical Turbulence Climatology using Machine learning), a novel approach for deriving comprehensive climatologies of atmospheric optical turbulence strength ($C_n^2$) using gradient boosting machines. OTCliM addresses the challenge of efficiently obtaining reliable site-specific $C_n^2$ climatologies near the surface, crucial for ground-based astronomy and free-space optical communication. Using gradient boosting machines and global reanalysis data, OTCliM extrapolates one year of measured $C_n^2$ into a multi-year time series. We assess OTCliM's performance using $C_n^2$ data from 17 diverse stations in New York State, evaluating temporal extrapolation capabilities and geographical generalization. Our results demonstrate accurate predictions of four held-out years of $C_n^2$ across various sites, including complex urban environments, outperforming traditional analytical models. Non-urban models also show good geographical generalization compared to urban models, which capture non-general site-specific dependencies. A feature importance analysis confirms the physical consistency of the trained models. It also indicates the potential to uncover new insights into the physical processes governing $C_n^2$ from data. OTCliM's ability to derive reliable $C_n^2$ climatologies from just one year of observations can potentially reduce resources required for future site surveys or enable studies for additional sites with the same resources.

physics.ao-ph↗

arXiv2023

Π-ML: A dimensional analysis-based machine learning parameterization of optical turbulence in the atmospheric surface layer

Turbulent fluctuations of the atmospheric refraction index, so-called optical turbulence, can significantly distort propagating laser beams. Therefore, modeling the strength of these fluctuations ($C_n^2$) is highly relevant for the successful development and deployment of future free-space optical communication links. In this letter, we propose a physics-informed machine learning (ML) methodology, $Π$-ML, based on dimensional analysis and gradient boosting to estimate $C_n^2$. Through a systematic feature importance analysis, we identify the normalized variance of potential temperature as the dominating feature for predicting $C_n^2$. For statistical robustness, we train an ensemble of models which yields high performance on the out-of-sample data of $R^2=0.958\pm0.001$.

physics.ao-ph↗