SMGformer: integrating STL and multi-head self-attention in deep learning model for multi-step runoff forecasting
Authors:
Open Access
- 9 October 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-24
Abstract
Accurate runoff forecasting is of great significance for water resource allocation flood control and disaster reduction. However, due to the inherent strong randomness of runoff sequences, this task faces significant challenges. To address this challenge, this study proposes a new SMGformer runoff forecast model. The model integrates Seasonal and Trend decomposition using Loess (STL), Informer’s Encoder layer, Bidirectional Gated Recurrent Unit (BiGRU), and Multi-head self-attention (MHSA). Firstly, in response to the nonlinear and non-stationary characteristics of the runoff sequence, the STL decomposition is used to extract the runoff sequence’s trend, period, and residual terms, and a multi-feature set based on ‘sequence-sequence’ is constructed as the input of the model, providing a foundation for subsequent models to capture the evolution of runoff. The key features of the input set are then captured using the Informer’s Encoder layer. Next, the BiGRU layer is used to learn the temporal information of these features. To further optimize the output of the BiGRU layer, the MHSA mechanism is introduced to emphasize the impact of important information. Finally, accurate runoff forecasting is achieved by transforming the output of the MHSA layer through the Fully connected layer. To verify the effectiveness of the proposed model, monthly runoff data from two hydrological stations in China are selected, and eight models are constructed to compare the performance of the proposed model. The results show that compared with the Informer model, the 1th step MAE of the SMGformer model decreases by 42.2% and 36.6%, respectively; RMSE decreases by 37.9% and 43.6% respectively; NSE increases from 0.936 to 0.975 and from 0.487 to 0.837, respectively. In addition, the KGE of the SMGformer model at the 3th step are 0.960 and 0.805, both of which can maintain above 0.8. Therefore, the model can accurately capture key information in the monthly runoff sequence and extend the effective forecast period of the model.Keywords
Funding Information
- The support of the special project for collaborative innovation of science and technology in 2021 (202121206)
This publication has 62 references indexed in Scilit:
- A hybrid optimization prediction model for PM2.5 based on VMD and deep learningAtmospheric Pollution Research, 2024
- Incorporating multiple grid-based data in CNN-LSTM hybrid model for daily runoff prediction in the source region of the Yellow River BasinJournal of Hydrology: Regional Studies, 2024
- Integrated Multi-Head Self-Attention Transformer model for electricity demand prediction incorporating local climate variablesEnergy and AI, 2023
- Improving the accuracy of multi-step prediction of building energy consumption based on EEMD-PSO-Informer and long-time seriesComputers and Electrical Engineering, 2023
- Evaluation of Transformer model and Self-Attention mechanism in the Yangtze River basin runoff predictionJournal of Hydrology: Regional Studies, 2023
- Motion prediction for beating heart surgery with GRUBiomedical Signal Processing and Control, 2023
- Host load prediction in cloud computing with Discrete Wavelet Transformation (DWT) and Bidirectional Gated Recurrent Unit (BiGRU) networkComputer Communications, 2022
- Monthly runoff prediction at Baitarani river basin by support vector machine based on Salp swarm algorithmAin Shams Engineering Journal, 2022
- Estimating reference evapotranspiration using hybrid adaptive fuzzy inferencing coupled with heuristic algorithmsComputers and Electronics in Agriculture, 2021
- Monthly runoff forecasting based on LSTM–ALO modelStochastic Environmental Research and Risk Assessment, 2018