A Hybrid Model Based on LSTM for Water Prediction Algorithm
- Resource Type
- Conference
- Authors
- Lv, Lei; Wang, Jingcheng; Li, Jichao; Zhang, Binbin; Gao, Song
- Source
- 2023 6th International Symposium on Autonomous Systems (ISAS) Autonomous Systems (ISAS), 2023 6th International Symposium on. :1-6 Jun, 2023
- Subject
- Aerospace
Robotics and Control Systems
Transportation
Water
Adaptation models
Adaptive systems
Heuristic algorithms
Time series analysis
Predictive models
Feature extraction
water forecast
short and long-term memory networks
time convolutional networks
empirical modal decomposition for adaptive integration
- Language
Focusing on the challenge of predicting water levels under highly nonlinear and non-smooth characteristics, we propose a data reconstruction blend prediction model based on Long Short-Term memory (LSTM) networks. The model utilizes a completely ensemble empirical model decomposition with adaptive noise to decompose the time series, and then applies the Temporal Convolutional Network (TCN) and LSTM structures as water prediction models. Through analysis of the predicted results from a pumping plant’s pumping port data, we demonstrate the superiority of our model over traditional approaches.