Lightweight, Pre-trained Transformers for Remote Sensing Timeseries

TL;DR

Presto is a lightweight, pre-trained transformer model tailored for remote sensing time series data, enabling effective transfer learning and feature extraction with less computational resources.

Contribution

The paper introduces Presto, a novel pre-trained transformer specifically designed for remote sensing time series data, improving efficiency and performance over larger models.

Findings

Presto performs competitively on various remote sensing tasks.

Presto requires significantly less compute than larger models.

Presto is effective for transfer learning and feature extraction.

Abstract

Machine learning methods for satellite data have a range of societally relevant applications, but labels used to train models can be difficult or impossible to acquire. Self-supervision is a natural solution in settings with limited labeled data, but current self-supervised models for satellite data fail to take advantage of the characteristics of that data, including the temporal dimension (which is critical for many applications, such as monitoring crop growth) and availability of data from many complementary sensors (which can significantly improve a model's predictive performance). We present Presto (the Pretrained Remote Sensing Transformer), a model pre-trained on remote sensing pixel-timeseries data. By designing Presto specifically for remote sensing data, we can create a significantly smaller but performant model. Presto excels at a wide variety of globally distributed remote sensing tasks and performs competitively with much larger models while requiring far less compute. Presto can be used for transfer learning or as a feature extractor for simple models, enabling efficient deployment at scale.