Filling Gaps in Daily Temperature Data with a CNN-LSTM Model

Thea Camille-Maxime; Olena Belozerova

Filling Gaps in Daily Temperature Data with a CNN-LSTM Model

Автор(и)

Thea Camille-Maxime Department of Computer Science and Applied Mathematics, National University of Water and Environmental Engineering https://orcid.org/0009-0002-6709-7364
Olena Belozerova Department of Computer Science and Applied Mathematics, National University of Water and Environmental Engineering https://orcid.org/0000-0001-9934-1013

Ключові слова:

meteorology data, time series imputation, missing weather data, convolutional neural network, LSTM

Анотація

The challenge of missing data poses a significant difficulty in the practical use of recorded meteorological data, a concern that has become apparent in Ukraine in recent years. This paper presents a deep learning methodology for imputing consecutive missing data within weather station records. By integrating convolutional neural network and Long Short-Term Memory (LSTM) layers, both recognized as prominent techniques in weather data forecasting and imputation, this approach provides reliable results for filling gaps in daily air temperature data.