PIAD-SRNN: Physics-Informed Adaptive Decomposition in State-Space RNN
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916837803950080 |
|---|---|
| author | Mohammadshirazi, Ahmad Neogi, Pinaki Prasad Guha Ramnath, Rajiv |
| author_facet | Mohammadshirazi, Ahmad Neogi, Pinaki Prasad Guha Ramnath, Rajiv |
| contents | Time series forecasting often demands a trade-off between accuracy and efficiency. While recent Transformer models have improved forecasting capabilities, they come with high computational costs. Linear-based models have shown better accuracy than Transformers but still fall short of ideal performance. We propose PIAD-SRNN, a physics-informed adaptive decomposition state-space RNN, that separates seasonal and trend components and embeds domain equations in a recurrent framework. We evaluate PIAD-SRNN's performance on indoor air quality datasets, focusing on CO2 concentration prediction across various forecasting horizons, and results demonstrate that it consistently outperforms SoTA models in both long-term and short-term time series forecasting, including transformer-based architectures, in terms of both MSE and MAE. Besides proposing PIAD-SRNN which balances accuracy with efficiency, this paper also provides four curated datasets. Code and data: https://github.com/ahmad-shirazi/DSSRNN |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00994 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PIAD-SRNN: Physics-Informed Adaptive Decomposition in State-Space RNN Mohammadshirazi, Ahmad Neogi, Pinaki Prasad Guha Ramnath, Rajiv Machine Learning Artificial Intelligence Time series forecasting often demands a trade-off between accuracy and efficiency. While recent Transformer models have improved forecasting capabilities, they come with high computational costs. Linear-based models have shown better accuracy than Transformers but still fall short of ideal performance. We propose PIAD-SRNN, a physics-informed adaptive decomposition state-space RNN, that separates seasonal and trend components and embeds domain equations in a recurrent framework. We evaluate PIAD-SRNN's performance on indoor air quality datasets, focusing on CO2 concentration prediction across various forecasting horizons, and results demonstrate that it consistently outperforms SoTA models in both long-term and short-term time series forecasting, including transformer-based architectures, in terms of both MSE and MAE. Besides proposing PIAD-SRNN which balances accuracy with efficiency, this paper also provides four curated datasets. Code and data: https://github.com/ahmad-shirazi/DSSRNN |
| title | PIAD-SRNN: Physics-Informed Adaptive Decomposition in State-Space RNN |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.00994 |