TorchGeo: deep learning with geospatial data

Adam J Stewart, Caleb Robinson, Isaac A Corley, Anthony Ortiz, Juan M Lavista Ferres, Arindam Banerjee

Keywords: deep learning, remote sensing, geospatial data

Abstract: Remotely sensed geospatial data are critical for earth observation applications including precision agriculture, urban planning, disaster monitoring and response, and climate change research, among others. Deep learning methods are particularly promising for modeling many earth observation tasks given the success of deep neural networks in similar computer vision tasks and the sheer volume of remotely sensed imagery available. However, the variance in data collection methods and handling of geospatial metadata make the application of deep learning methodology to remotely sensed data nontrivial. For example, satellite imagery often includes additional spectral bands beyond red, green, and blue and must be joined to other geospatial data sources that can have differing coordinate systems, bounds, and resolutions. To help realize the potential of deep learning for remote sensing applications, we introduce TorchGeo, a Python library for integrating geospatial data into the PyTorch deep learning ecosystem. TorchGeo provides data loaders for a variety of benchmark datasets, composable datasets for generic geospatial data sources, samplers for geospatial data, and transforms that work with multispectral imagery. TorchGeo is also the first library to provide pre-trained models for multispectral satellite imagery, allowing for advances in transfer learning on downstream earth observation tasks with limited labeled data. We use TorchGeo to create reproducible benchmark results on existing datasets, benchmark our proposed method for preprocessing geospatial imagery on-the-fly, and investigate the differences between ImageNet pre-training and in-domain self-supervised pre-training on model performance across several datasets. We aim for TorchGeo to become a new standard for reproducibility and for driving progress at the intersection of deep learning and remotely sensed geospatial data.

One-sentence Summary: We introduce TorchGeo, a PyTorch domain library providing datasets, samplers, transforms, and models for geospatial data

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2111.08872/code)