Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GEAR: Geography-knowledge Enhanced Analog Recognition Framework in Extreme Environments

Zelin Liu, Bocheng Li, Yuling Zhou, Xuanting Li, Yixuan Yang, Jing Wang, Weishu Zhao, Xiaofeng Gao

Abstract

The Mariana Trench and the Qinghai-Tibet Plateau exhibit significant similarities in geological origins and microbial metabolic functions. Given that deep-sea biological sampling faces prohibitive costs, recognizing structurally homologous terrestrial analogs of the Mariana Trench on the Qinghai-Tibet Plateau is of great significance. Yet, no existing model adequately addresses cross-domain topographic similarity retrieval, either neglecting geographical knowledge or sacrificing computational efficiency. To address these challenges, we present \underline{\textbf{G}}eography-knowledge \underline{\textbf{E}}nhanced \underline{\textbf{A}}nalog \underline{\textbf{R}}ecognition (\textbf{GEAR}) Framework, a three-stage pipeline designed to efficiently retrieve analogs from 2.5 million square kilometers of the Qinghai-Tibet Plateau: (1) Skeleton guided Screening and Clipping: Recognition of candidate valleys and initial screening based on size and linear morphological criteria. (2) Physics aware Filtering: The Topographic Waveform Comparator (TWC) and Morphological Texture Module (MTM) evaluate the waveform and texture and filter out inconsistent candidate valleys. (3) Graph based Fine Recognition: We design a \underline{\textbf{M}}orphology-integrated \underline{\textbf{S}}iamese \underline{\textbf{G}}raph \underline{\textbf{N}}etwork (\textbf{MSG-Net}) based on geomorphological metrics. Correspondingly, we release an expert-annotated topographic similarity dataset targeting tectonic collision zones. Experiments demonstrate the effectiveness of every stage. Besides, MSG-Net achieved an F1-Score 1.38 percentage points higher than the SOTA baseline. Using features extracted by MSG-Net, we discovered a significant correlation with biological data, providing evidence for future biological analysis.

GEAR: Geography-knowledge Enhanced Analog Recognition Framework in Extreme Environments

Abstract

The Mariana Trench and the Qinghai-Tibet Plateau exhibit significant similarities in geological origins and microbial metabolic functions. Given that deep-sea biological sampling faces prohibitive costs, recognizing structurally homologous terrestrial analogs of the Mariana Trench on the Qinghai-Tibet Plateau is of great significance. Yet, no existing model adequately addresses cross-domain topographic similarity retrieval, either neglecting geographical knowledge or sacrificing computational efficiency. To address these challenges, we present \underline{\textbf{G}}eography-knowledge \underline{\textbf{E}}nhanced \underline{\textbf{A}}nalog \underline{\textbf{R}}ecognition (\textbf{GEAR}) Framework, a three-stage pipeline designed to efficiently retrieve analogs from 2.5 million square kilometers of the Qinghai-Tibet Plateau: (1) Skeleton guided Screening and Clipping: Recognition of candidate valleys and initial screening based on size and linear morphological criteria. (2) Physics aware Filtering: The Topographic Waveform Comparator (TWC) and Morphological Texture Module (MTM) evaluate the waveform and texture and filter out inconsistent candidate valleys. (3) Graph based Fine Recognition: We design a \underline{\textbf{M}}orphology-integrated \underline{\textbf{S}}iamese \underline{\textbf{G}}raph \underline{\textbf{N}}etwork (\textbf{MSG-Net}) based on geomorphological metrics. Correspondingly, we release an expert-annotated topographic similarity dataset targeting tectonic collision zones. Experiments demonstrate the effectiveness of every stage. Besides, MSG-Net achieved an F1-Score 1.38 percentage points higher than the SOTA baseline. Using features extracted by MSG-Net, we discovered a significant correlation with biological data, providing evidence for future biological analysis.
Paper Structure (20 sections, 9 equations, 6 figures, 2 tables, 1 algorithm)

This paper contains 20 sections, 9 equations, 6 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Problem Formulation
  3. Geographical Analysis and Data Processing
  4. Qinghai-Tibet Plateau (QTP).
  5. Mariana Trench (MT).
  6. Expert-Annotated Dataset.
  7. Problem Definition
  8. GEAR Framework
  9. Seleton-guided Screening and Clipping (SSC)
  10. Topographic Waveform Comparator (TWC)
  11. Morphological Texture Module (MTM)
  12. Morphology-integrated Siamese Graph Network (MSG-Net)
  13. Experiments
  14. Implementation Details
  15. Baseline Setting
  16. ...and 5 more sections

Figures (6)

  • Figure 1: Topology and microbial comparison between the Tibetan Plateau (TP) and the Mariana Trench (MT).(a) V-shaped topographic profile comparison.(b) Location and DEM grids of the TP.(c) Location of the MT and sampling sites.
  • Figure 2: The reference trench $\mathcal{T}_{\text{ref}}$ (2D (a) and 3D (b) versions)
  • Figure 3: The pipeline of GEAR
  • Figure 4: Topological similarity distributions of candidate valleys discarded during the coarse screening phase. (a) Separate distributions for the TWC and MTM stages. (b) The combined overall distribution.
  • Figure 5: Bray-Curtis Dissimilarity heatmap and correlation between terrain and BC dissimilarity
  • ...and 1 more figures

Theorems & Definitions (2)

  • definition 1: Similarity Learning Model
  • definition 2: Analog Recognition Retriever