Abstract
Earth observation machine learning pipelines differ fundamentally from standard computer vision workflows. Imagery is typically delivered as large, georeferenced scenes, labels may be raster masks or vector geometries in distinct coordinate reference systems, and both training and evaluation often require spatially aware sampling and splitting strategies. TorchGeo is a PyTorch-based domain library that provides datasets, samplers, transforms and pre-trained models with the goal of making it easy to use geospatial data in machine learning pipelines. In this paper, we introduce a tutorial that demonstrates 1.) the core TorchGeo abstractions through code examples, and 2.) an end-to-end case study on multispectral water segmentation from Sentinel-2 imagery using the Earth Surface Water dataset. This demonstrates how to train a semantic segmentation model using TorchGeo datasets, apply the model to a Sentinel-2 scene over Rio de Janeiro, Brazil, and save the resulting predictions as a GeoTIFF for further geospatial analysis. The tutorial code itself is distributed as two Python notebooks: this https URL and this https URL.
Abstract (translated)
地球观测机器学习管道与标准计算机视觉工作流程在根本上有所不同。图像通常以大型、地理参考的场景形式提供，标签可能是不同的坐标参考系统中的栅格掩码或向量几何图形，并且训练和评估过程常常需要空间感知采样和分割策略。TorchGeo 是一个基于 PyTorch 的领域库，它提供了数据集、采样器、转换以及预训练模型，旨在简化在机器学习管道中使用地理空间数据的过程。 在这篇论文中，我们介绍了一个教程，该教程通过代码示例展示了1.) TorchGeo的核心抽象，并2.) 使用Sentinel-2影像进行多光谱水域分割的端到端案例研究。本案例基于地球表面水体数据集（Earth Surface Water dataset），演示了如何使用TorchGeo的数据集训练语义分割模型，将该模型应用于巴西里约热内卢地区的Sentinel-2场景，并保存预测结果为GeoTIFF文件以供进一步的地理空间分析。 教程代码本身以两个Python笔记本的形式分发：[此链接](https://this.https.URL) 和 [此链接](https://this.https.URL)。
URL
https://arxiv.org/abs/2603.02386
