Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GRMLR: Knowledge-Enhanced Small-Data Learning for Deep-Sea Cold Seep Stage Inference

Chenxu Zhou, Zelin Liu, Rui Cai, Houlin Gong, Yikang Yu, Jia Zeng, Yanru Pei, Liang Zhang, Weishu Zhao, Xiaofeng Gao

Abstract

Deep-sea cold seep stage assessment has traditionally relied on costly, high-risk manned submersible operations and visual surveys of macrofauna. Although microbial communities provide a promising and more cost-effective alternative, reliable inference remains challenging because the available deep-sea dataset is extremely small ($n = 13$) relative to the microbial feature dimension ($p = 26$), making purely data-driven models highly prone to overfitting. To address this, we propose a knowledge-enhanced classification framework that incorporates an ecological knowledge graph as a structural prior. By fusing macro-microbe coupling and microbial co-occurrence patterns, the framework internalizes established ecological logic into a \underline{\textbf{G}}raph-\underline{\textbf{R}}egularized \underline{\textbf{M}}ultinomial \underline{\textbf{L}}ogistic \underline{\textbf{R}}egression (GRMLR) model, effectively constraining the feature space through a manifold penalty to ensure biologically consistent classification. Importantly, the framework removes the need for macrofauna observations at inference time: macro-microbe associations are used only to guide training, whereas prediction relies solely on microbial abundance profiles. Experimental results demonstrate that our approach significantly outperforms standard baselines, highlighting its potential as a robust and scalable framework for deep-sea ecological assessment.

GRMLR: Knowledge-Enhanced Small-Data Learning for Deep-Sea Cold Seep Stage Inference

Abstract

Deep-sea cold seep stage assessment has traditionally relied on costly, high-risk manned submersible operations and visual surveys of macrofauna. Although microbial communities provide a promising and more cost-effective alternative, reliable inference remains challenging because the available deep-sea dataset is extremely small () relative to the microbial feature dimension (), making purely data-driven models highly prone to overfitting. To address this, we propose a knowledge-enhanced classification framework that incorporates an ecological knowledge graph as a structural prior. By fusing macro-microbe coupling and microbial co-occurrence patterns, the framework internalizes established ecological logic into a \underline{\textbf{G}}raph-\underline{\textbf{R}}egularized \underline{\textbf{M}}ultinomial \underline{\textbf{L}}ogistic \underline{\textbf{R}}egression (GRMLR) model, effectively constraining the feature space through a manifold penalty to ensure biologically consistent classification. Importantly, the framework removes the need for macrofauna observations at inference time: macro-microbe associations are used only to guide training, whereas prediction relies solely on microbial abundance profiles. Experimental results demonstrate that our approach significantly outperforms standard baselines, highlighting its potential as a robust and scalable framework for deep-sea ecological assessment.
Paper Structure (14 sections, 6 equations, 9 figures, 2 tables)

This paper contains 14 sections, 6 equations, 9 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Preliminary
  3. Knowledge-Enhanced Cold Seep Stage Classificatio
  4. Habitat Map Construction and Macrofauna Detection
  5. Microbial Relative Abundance Analysis
  6. Graph-Regularized Multinomial Logistic Regression
  7. Experiments
  8. Experimental Environment
  9. Performance Comparison (RQ1)
  10. Ablation Study (RQ2)
  11. Sensitivity Analysis (RQ3)
  12. Interpretability Analysis (RQ4)
  13. Related Work
  14. Conclusion

Figures (9)

  • Figure 1: Methane bubbling observed in the cold seep area.
  • Figure 2: Rich biological assemblages around a cold seep.
  • Figure 3: Motivation: Cold seep development stage recognition requires robust learning from complex microbial data, since macrofaunal observations are expensive and challenging to acquire.
  • Figure 4: Framework of GRMLR and data flow. Macrofauna counts and CLR-transformed microbial features are integrated through an ecological knowledge graph during training, while inference uses only microbial data for stage classification.
  • Figure 5: A representative raw submersible frame ($1920\times1080$) used as input to the mapping pipeline.
  • ...and 4 more figures