OceanGPT: A Large Language Model for Ocean Science Tasks

Zhen Bi♠♡♤ , Ningyu Zhang♠♡♤* , Yida Xue , Yixin Ou Daxiong Ji♡♢ Guozhou Zheng♡♣ Huajun Chen♠♡*

College Computer Science and Technology, Zhejiang University Donghai Laboratory Ocean College, Zhejiang University Zhoushan-Zhejiang University Ocean Research Center School of Software Technology, Zhejiang University
*Corresponding Author

Capabilities of OceanGPT

Abstract

(Warning: The model in this paper might produce hallucinations and reader discretion is recommended) Ocean science, which delves into the oceans that are reservoirs of life and biodiversity, is of great significance given that oceans cover over 70% of our planet's surface. Recently, advances in Large Language Models (LLMs) have transformed the paradigm in science. Despite the success in other domains, current LLMs often fall short in catering to the needs of domain experts like oceanographers, and the potential of LLMs for ocean science is under-explored. The intrinsic reason may be the immense and intricate nature of ocean data as well as the necessity for higher granularity and richness in knowledge. To alleviate these issues, we introduce OceanGPT, the first-ever LLM in the ocean domain, which is expert in various ocean science tasks. We propose DoInstruct, a novel framework to automatically obtain a large volume of ocean domain instruction data, which generates instructions based on multi-agent collaboration. Additionally, we construct the first oceanography benchmark, OceanBench, to evaluate the capabilities of LLMs in the ocean domain. Though comprehensive experiments, OceanGPT not only shows a higher level of knowledge expertise for oceans science tasks but also gains preliminary embodied intelligence capabilities in ocean technology.



Framework Design

The overview of our framework OceanGPT


  • OceanGPT is the first ocean LLM, which shows superiority for various ocean science tasks. It can answer oceanographic questions according to the instructions of oceanographers, demonstrating expertise in oceanography.
DoInstruct is an automated domain instruction evolving framework that constructs the ocean instruction dataset by multi-agent collaboration. Our framework effectively alleviates the difficulty of obtaining ocean domain data. To effectively simulate and obtain those data, DoInstruct obtain ocean instructions by multi-agent collaboration. Each agent is considered as an expert in a specific domain (topic) and is responsible for generating the corresponding data.


Main Results

OceanGPT obtains better performance than previous open-sourced LLMs.


OceanGPT excels in a range of ocean science tasks.


DoInstruct are the effective ocean data generators by multi-agent collaboration.



Exploring the Potential



OceanGPT for Ocean Science. OceanGPT demonstrates a higher level of knowledge expertise when describing the content of radioactive nuclide research. Its textual content is not only clear in structure and well-organized, but also covers various aspects of radioactive nuclide research, from experimental design to data analysis, and then to risk assessment and disposal guidelines.

OceanGPT for Ocean Engineering. We integrate machine code instructions into its training data. OceanGPT can instruct underwater robots via code or console commands, allowing them to execute basic path-finding operations. Though we make preliminary attempts for ocean robot interaction, it paves the way for future advanced oceanic models to undertake intricate robotic control and planning tasks.

This website is adapted from Nerfies, licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.