Deep-learning-based prediction of precipitable water vapor in the Chajnantor area
Open Access
- 6 January 2026
- journal article
- research article
- Published by EDP Sciences in Astronomy & Astrophysics
- Vol. 705, A68
Abstract
Context . Astronomical observations at millimeter and submillimeter wavelengths strongly depend on the amount of precipitable water vapor (PWV) in the atmosphere, which directly affects the sky transparency and decreases the signal-to-noise ratio of the signals received by radio telescopes. Aims . Predictions of PWV at different forecasting horizons are crucial to supporting the telescope operations, engineering planning, scheduling and observational efficiency of radio observatories installed in the Chajnantor area in northern Chile. Methods . 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. Results . We find that the LSTM method is able to predict PWV in the 12- and 24-hour forecasting horizons with a mean absolute percentage error of ~22% compared to ~36% for the traditional Global Forecast System method used by the Atacama Pathfinder Experiment, and the root mean square error is reduced by ~50%. Conclusions . We present a first application of deep learning techniques for preliminary predictions of PWV in the Chajnantor area. The prediction performance shows significant improvements compared to traditional methods in 12- and 24-hour time windows. We also propose strategies to improve our method on shorter (36 hour) forecasting timescales.Keywords
All Related Versions
Funding Information
- Gobierno Regional del Bio-Bío (FIC-R IA 40036152-0)
- ANID (FONDECYT Iniciación 11221231)
- ANID (FONDECYT Regular 1251819)
- ANID (FONDECYT Regular 1240843)
- Chinese Academy of Sciences South America Center for Astronomy (CCJRF1803)
- Chinese Academy of Sciences South America Center for Astronomy (CCJRF2101)
- Chinese Academy of Sciences South America Center for Astronomy (E52H540201)
- ANID (NCN2023_002)
- ANID (FB210003)
This publication has 23 references indexed in Scilit:
- A new Egyptian Grid Weighted Mean Temperature (EGWMT) model using hourly ERA5 reanalysis data in GNSS PWV retrievalScientific Reports, 2024
- Satellite-based atmospheric characterization for sites of interest in millimeter and sub-millimeter astronomyAstronomy & Astrophysics, 2024
- Machine learning-based seeing estimation and prediction using multi-layer meteorological data at Dome A, AntarcticaAstronomy and Computing, 2023
- Adaptability of Financial Time Series Prediction Based on BiLSTMProcedia Computer Science, 2022
- A Global Assessment of Precipitable Water Vapor Derived From GNSS Zenith Tropospheric Delays With ERA5, NCEP FNL, and NCEP GFS ProductsEarth and Space Science, 2021
- Twenty years of precipitable water vapor measurements in the Chajnantor areaAstronomy & Astrophysics, 2020
- Estimating and forecasting the precipitable water vapor from GOES satellite data at high altitude sitesAstronomy & Astrophysics, 2014
- Parque Astronómico de Atacama: An Ideal Site for Millimeter, Submillimeter, and Mid-Infrared AstronomyPublications of the Astronomical Society of the Pacific, 2014
- Thirty Meter Telescope Site Testing X: Precipitable Water VaporPublications of the Astronomical Society of the Pacific, 2010
- The Atacama Pathfinder EXperiment (APEX) – a new submillimeter facility for southern skies –Astronomy & Astrophysics, 2006