Abstract
Multi-step-ahead prediction is considered of major significance for time series analysis in many real life problems. Existing methods mainly focus on one-step-ahead forecasting, since multiple step forecasting generally fails due to accumulation of prediction errors. This paper presents a novel approach for predicting plant growth in agriculture, focusing on prediction of plant Stem Diameter Variations (SDV). The proposed approach consists of three main steps. At first, wavelet decomposition is applied to the original data, so as to facilitate model fitting and reduce noise. Then an encoder-decoder framework is developed using Long Short Term Memory (LSTM) and used for appropriate feature extraction from the data. Finally, a recurrent neural network including LSTM and an attention mechanism is proposed for modelling long-term dependencies in the time series data. Experimental results are presented which illustrate the good performance of the proposed approach and that it significantly outperforms the existing models, in terms of error criteria such as RMSE, MAE and MAPE.
Original language | English |
---|---|
Article number | INS16166 |
Pages (from-to) | 35-50 |
Number of pages | 16 |
Journal | Information Sciences |
Volume | 560 |
Early online date | 1 Feb 2021 |
DOIs | |
Publication status | Published - 1 Jun 2021 |
Bibliographical note
AcknowledgementsThis research was supported as part of SMARTGREEN, an Interreg project supported by the North Sea Programme of the European Regional Development Fund of the European Union. We would like to thank all growers (UK and EU), for providing us with the presented data sets. We also wish to thank the reviewers of the paper. Their valuable feedback, suggestions and comments helped us to improve the quality of this work.
Keywords
- Multi-step prediction
- Wavelet analysis
- Deep neural networks
- Attention mechanism
- Time-series analysis
- LSTM
- Plant growth prediction