A MaaS-based solution to large model development for earth science

Zhihang Jiang; Xiaoran Yan; Phuminh Lam; Feng Lin

doi:10.1117/12.3024679

2 May 2024 A MaaS-based solution to large model development for earth science

Zhihang Jiang, Xiaoran Yan, Phuminh Lam, Feng Lin

Proceedings Volume 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024; 131643B (2024) https://doi.org/10.1117/12.3024679
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2024, 2024, Langkawi, Malaysia

Abstract

In this paper, we present an innovative approach to address the challenges posed by the large-scale model development required for Earth Science projects. Leveraging ModelScope, a Model as a Service (MaaS) platform, and Artificial Intelligence Generated Content (AIGC) techniques, we are proposing a practical solution for generating geographical visualizations from textual inputs based on Earth Science entities. The method can efficiently convert texts to images and videos, providing a dynamic portrayal of the Earth's evolution and future. By utilizing the elastic GPU computational resources and extensive datasets offered by ModelScope, we can bypass the need for physical server setup and significantly reduced the data collection burden for researchers. Using data from diverse sources, including historical records, geological maps, satellite images, and climate models, we will employ natural language processing, computer vision, and deep learning techniques to create realistic and informative visualizations. Our concept offer various levels of detail and complexity suitable for education, entertainment, and decision-making purposes. This framework will not only advances Earth Science visualization but also highlights the potential and challenges of MaaS and AIGC in Earth science research, underscoring their broader applicability in the geography domain.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Zhihang Jiang, Xiaoran Yan, Phuminh Lam, and Feng Lin "A MaaS-based solution to large model development for earth science", Proc. SPIE 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024, 131643B (2 May 2024); https://doi.org/10.1117/12.3024679

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Earth sciences

Visual process modeling

Visualization

Elasticity

Modeling

Artificial intelligence

Show All Keywords

Keywords/Phrases

Search In:

Publication Years