AnySat：一個適用於任何解析度、比例尺和模式的地球觀測模型

AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities

December 18, 2024

作者: Guillaume Astruc, Nicolas Gonthier, Clement Mallet, Loic Landrieu

cs.AI

摘要

地理空間模型必須適應地球觀測數據在解析度、尺度和模式方面的多樣性。然而，現有方法期望固定的輸入配置，這限制了它們的實際應用性。我們提出了AnySat，這是一個基於聯合嵌入預測架構（JEPA）和分辨率自適應空間編碼器的多模型，使我們能夠以自監督方式在高度異質數據上訓練單一模型。為了展示這一統一方法的優勢，我們編制了GeoPlex，這是一個包含5個具有不同特徵和11個不同傳感器的多模數據集的集合。然後，我們同時在這些多樣數據集上訓練一個強大的單一模型。經過微調後，我們在GeoPlex數據集和另外4個環境監測任務的數據集上取得了更好或接近最先進的結果：土地覆蓋映射、樹木種類識別、農作物類型分類、變化檢測和洪水分割。代碼和模型可在https://github.com/gastruc/AnySat找到。

English

Geospatial models must adapt to the diversity of Earth observation data in terms of resolutions, scales, and modalities. However, existing approaches expect fixed input configurations, which limits their practical applicability. We propose AnySat, a multimodal model based on joint embedding predictive architecture (JEPA) and resolution-adaptive spatial encoders, allowing us to train a single model on highly heterogeneous data in a self-supervised manner. To demonstrate the advantages of this unified approach, we compile GeoPlex, a collection of 5 multimodal datasets with varying characteristics and 11 distinct sensors. We then train a single powerful model on these diverse datasets simultaneously. Once fine-tuned, we achieve better or near state-of-the-art results on the datasets of GeoPlex and 4 additional ones for 5 environment monitoring tasks: land cover mapping, tree species identification, crop type classification, change detection, and flood segmentation. The code and models are available at https://github.com/gastruc/AnySat.