Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model
This work addresses the problem of inefficient and inaccurate spatio-temporal modeling for researchers and practitioners in deep learning, though it appears incremental as it builds on existing convolution and transformer methods.
The paper tackles the challenge of modeling spatio-temporal physical processes by addressing issues like poor long-term prediction and inefficiency in existing models, proposing EarthFarseer, which achieves state-of-the-art performance with better local fidelity and fast convergence across eight datasets.
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community. Many recent studies have concentrated on meticulously reconciling various advantages, leading to designed models that are neither simple nor practical. To address this issue, this paper presents a systematic study on existing shortcomings faced by off-the-shelf models, including lack of local fidelity, poor prediction performance over long time-steps,low scalability, and inefficiency. To systematically address the aforementioned problems, we propose an EarthFarseer, a concise framework that combines parallel local convolutions and global Fourier-based transformer architectures, enabling dynamically capture the local-global spatial interactions and dependencies. EarthFarseer also incorporates a multi-scale fully convolutional and Fourier architectures to efficiently and effectively capture the temporal evolution. Our proposal demonstrates strong adaptability across various tasks and datasets, with fast convergence and better local fidelity in long time-steps predictions. Extensive experiments and visualizations over eight human society physical and natural physical datasets demonstrates the state-of-the-art performance of EarthFarseer. We release our code at https://github.com/easylearningscores/EarthFarseer.