A Hierarchical Classification Framework for Earth Science Data Based on Large Language Models and Label Graph Constraints
Applied Sciences · 23.05.2026 · 16 (11) · 5230
DOI: 10.3390/app16115230 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 23.05.2026. Verfasst von Le Zhao und 4 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Computer Network and Information Special Project Of Chinese Academy of Sciences.
Abstract (Originalsprache)
The rapid growth of Earth science observation and simulation data has made efficient data classification increasingly challenging, particularly under conditions of limited annotation resources and continuously evolving data semantics. Conventional classification methods rely heavily on large-scale labeled datasets, which are costly to construct and difficult to adapt to dynamic classification systems. This paper proposes a hierarchical classification framework for Earth science data that leverages large language models (LLMs) and explicitly incorporates hierarchical label relationships to constrain model inference and enhance classification consistency across complex, domain-specific semantic spaces. The framework further integrates retrieval-augmented generation (RAG) and knowledge graph (KG) techniques to introduce external domain knowledge and explicit semantic constraints, enhancing contextual understanding, interpretability, and adaptability to semantic evolution. A benchmark dataset with a two-level hierarchical label structure is constructed based on official NASA metadata. Experimental results demonstrate that by integrating few-shot learning and label space optimization strategies, the proposed framework steadily outperforms various baseline methods in hierarchical classification tasks. Compared with the Bert-BiLSTM model, it achieves an absolute improvement of 8.68% in Micro-F1 and 29.92% in Macro-F1 on the overall hierarchical paths. The framework demonstrates clear advantages in long-tailed data distributions, particularly for minority classes, highlighting its potential for scalable annotation and efficient management of large-scale Earth science datasets.
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- Computer Network and Information Special Project Of Chinese Academy of Sciences
Zitieren
APA
Zhao, L., Chen, Z., Li, G., Guo, H., & Li, J. (2026). A Hierarchical Classification Framework for Earth Science Data Based on Large Language Models and Label Graph Constraints. Applied Sciences, 16(11), 5230. https://doi.org/10.3390/app16115230
Vancouver
Zhao L, Chen Z, Li G, Guo H, Li J. A Hierarchical Classification Framework for Earth Science Data Based on Large Language Models and Label Graph Constraints. Applied Sciences. 2026;16(11):5230. doi:10.3390/app16115230
BibTeX
@article{Zhao2026,
author = {Zhao, Le and Chen, Zugang and Li, Guoqing and Guo, Hengliang and Li, Jing},
title = {A Hierarchical Classification Framework for Earth Science Data Based on Large Language Models and Label Graph Constraints},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {11},
pages = {5230},
doi = {10.3390/app16115230}
}
EUVIMED