用卫星图像生成的特征图找金矿，准确率提升明显。
Gold Exploration using Representations from a Multispectral Autoencoder
- 用多光谱自编码器学习卫星图像特征，生成可迁移的地质模式表示。
- 在63张已知金矿与非金矿影像上，地块级准确率达68%，图像级达73%。
- 适合缺乏实地数据的全球性矿产勘探，尤其适合快速筛查区域。
由于现场矿产勘查数据成本高且获取受限，遥感影像被广泛用于大范围成矿潜力制图。本文提出一个概念验证框架，利用来自多光谱Sentinel-2影像的生成式表征，从太空识别含金区域。基于FalconSpace-S2 v1.0大规模数据集预训练的自编码器基础模型Isometric，生成信息密集的光谱-空间表征，并输入轻量级XGBoost分类器。在包含63张已知金矿与非金矿位置的影像数据集上，与原始光谱输入基线相比，该方法将地块级准确率从0.51提升至0.68，图像级准确率从0.55提升至0.73，证明生成嵌入能捕捉即使在标注数据有限情况下也具有可迁移性的矿物学模式。结果表明，基础模型表征有望使矿产勘探更高效、可扩展且适用于全球场景。
原文摘要 · Abstract (English)
Satellite imagery is employed for large-scale prospectivity mapping due to the high cost and typically limited availability of on-site mineral exploration data. In this work, we present a proof-of-concept framework that leverages generative representations learned from multispectral Sentinel-2 imagery to identify gold-bearing regions from space. An autoencoder foundation model, called Isometric, which is pretrained on the large-scale FalconSpace-S2 v1.0 dataset, produces information-dense spectral-spatial representations that serve as inputs to a lightweight XGBoost classifier. We compare this representation-based approach with a raw spectral input baseline using a dataset of 63 Sentinel-2 images from known gold and non-gold locations. The proposed method improves patch-level accuracy from 0.51 to 0.68 and image-level accuracy from 0.55 to 0.73, demonstrating that generative embeddings capture transferable mineralogical patterns even with limited labeled data. These results highlight the potential of foundation-model representations to make mineral exploration more efficient, scalable, and globally applicable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。