PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series Article Swipe

MAKE IMPACT

Haobo Li , Eunho Jung , Zixin Chen , Zhaowei Wang , Yuneng Wang , Huamin Qu , Alexis K.H. Lau · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2506.14786

Multimodal time series forecasting is foundational in various fields, such as utilizing satellite imagery and numerical data for predicting typhoons in climate science. However, existing multimodal approaches primarily focus on utilizing text data to help time series forecasting, leaving the visual data in existing time series datasets untouched. Furthermore, it is challenging for models to effectively capture the physical information embedded in visual data, such as satellite imagery's temporal and geospatial context, which extends beyond images themselves. To address this gap, we propose physics-informed positional encoding (PIPE), a lightweight method that embeds physical information into vision language models (VLMs). PIPE introduces two key innovations: (1) a physics-informed positional indexing scheme for mapping physics to positional IDs, and (2) a variant-frequency positional encoding mechanism for encoding frequency information of physical variables and sequential order of tokens within the embedding space. By preserving both the physical information and sequential order information, PIPE significantly improves multimodal alignment and forecasting accuracy. Through the experiments on the most representative and the largest open-sourced satellite image dataset, PIPE achieves state-of-the-art performance in both deep learning forecasting and climate domain methods, demonstrating superiority across benchmarks, including a 12% improvement in typhoon intensity forecasting over prior works. Our code is provided in the supplementary material.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2506.14786

PDF

https://arxiv.org/pdf/2506.14786

OA Status

green

OpenAlex ID

https://openalex.org/W4415312748

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415312748

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2506.14786

Digital Object Identifier

Title

PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-05-27

Full publication date if available

Authors

Haobo Li, Eunho Jung, Zixin Chen, Zhaowei Wang, Yuneng Wang, Huamin Qu, Alexis K.H. Lau

List of authors in order

Landing page

https://arxiv.org/abs/2506.14786

Publisher landing page

PDF URL

https://arxiv.org/pdf/2506.14786

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2506.14786

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload