Silvia E. Restrepo | Searcharxiv

arXiv2026

Deep-learning-based prediction of Precipitable Water Vapor in the Chajnantor area

Astronomical observations at millimeter and submillimeter wavelengths heavily depend on the amount of Precipitable Water Vapor (PWV) in the atmosphere, directly affecting the sky transparency and degrading the quality of the signals received by radio telescopes. Predictions of PWV at different forecasting horizons is crucial to support telescope operations, engineering planning, and observational scheduling and efficiency of radio observatories installed in the Chajnantor area in northern Chile. We developed and validated a Long Short-Term Memory (LSTM) deep learning-based model to predict PWV at forecasting horizons of 12, 24, 36, and 48 hours using historical data from two 183 GHz radiometers and a weather station in the Chajnantor area. We find the LSTM method is able to predict PWV in the 12 and 24 hours forecasting horizons with Mean Absolute Percentage Error (MAPE) of 22% compared to 36% of the traditional Global Forecast System (GFS) method used by Atacama Pathfinder EXperiment (APEX) and the Root Mean Square Error (RMSE) in mm are reduced by 50%. We present a first application of deep learning techniques for preliminary predictions of PWV in the Chajnantor area. The prediction performance shows significant improvements to traditional methods in 12 and 24 hours time windows. We also propose upgrades to improve our method in short (< 1 hour) and long (> 36 hours) forecasting timescales for future work.

astro-ph.IM↗

arXiv2025

Using the antenna impedance to estimate soil electrical parameters for the MIST global 21-cm experiment

Radio experiments trying to detect the global $21$~cm signal from the early Universe are very sensitive to the electrical properties of their environment. For ground-based experiments with the antenna above the soil it is critical to characterize the effect from the soil on the sky observations. This characterization requires estimating the soil's electrical conductivity and relative permittivity in the same frequency range as the observations. Here we present our initial effort to estimate the conductivity and relative permittivity of the soil using the impedance of an antenna mounted at a distance above the surface. In this technique, the antenna used for soil characterization is the same as the antenna used for sky observations. To demonstrate the technique we use the antenna of the MIST global $21$~cm experiment. We measured the antenna impedance at three sites in the Greater Concepción area, Chile. The measurements were done between $25$ and $125$~MHz, matching the range used by MIST for sky observations. The soil parameters were estimated by fitting the impedance measurements with electromagnetic simulations of the antenna and soil. In this initial effort the soil was modeled as homogeneous. The conductivity at the three sites was found to be between $0.007$ and $0.049$~Sm$^{-1}$, and the relative permittivity between $1.6$ and $12.7$. The percent precision of the estimates at $68\%$ probability is, with one exception, better (lower) than $33\%$. The best-fit simulations have a better than $10\%$ agreement with the measurements relative to the peak values of the resistance and reactance across our frequency range. For MIST, these results represent a successful proof of concept of the use of the antenna impedance for soil characterization, and are expected to significantly improve in future implementations.

astro-ph.IM↗