Forecasting Precipitable Water Vapor Using LSTMs

TL;DR

This paper demonstrates that LSTM networks can effectively forecast GPS-based precipitable water vapor over short time intervals, achieving high accuracy and outperforming naive methods for up to 40 minutes ahead.

Contribution

The study applies LSTM networks to GPS-based PWV data, showing improved short-term forecasting accuracy over traditional methods.

Findings

LSTM achieves RMSE of 0.098 mm for 5-minute forecasts.

LSTM outperforms naive approaches for up to 40-minute lead times.

Model trained on over 1500 hours of data.

Abstract

Long-Short-Term-Memory (LSTM) networks have been used extensively for time series forecasting in recent years due to their ability of learning patterns over different periods of time. In this paper, this ability is applied to learning the pattern of Global Positioning System (GPS)-based Precipitable Water Vapor (PWV) measurements over a period of 4 hours. The trained model was evaluated on more than 1500 hours of recorded data. It achieves a root mean square error (RMSE) of 0.098 mm for a forecasting interval of 5 minutes in the future, and outperforms the naive approach for a lead-time of up to 40 minutes.