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

arXiv: https://arxiv.org/abs/2603.18626 · HTML: https://mlsanity.com/paper/2603.18626/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 38 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 1 of 1)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)

## Abstract (arXiv)

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 underlineGeography-knowledge underlineEnhanced underlineAnalog underlineRecognition (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 underlineMorphology-integrated underlineSiamese underlineGraph underlineNetwork (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.