Open access
Aug 2026
Employing Long-Short-Term Memory Cells for Univariate Time Series Imputation in Weather Sensors Data
This study presents an imputation method that integrates forecasting and backcasting using Long-Short-Term Memory (LSTM) architecture for predicting blocks of consecutive missing values using a randomly generated absent group of data from a weather dataset.
Antonios Raptakis, Leonard Dervishi, Kristine Bauer et al.
· Applied Sciences · 0 citations