中文
相关论文

相关论文: EarthPT: a time series foundation model for Earth …

200 篇论文

Recent progress in self-supervision has shown that pre-training large neural networks on vast amounts of unsupervised data can lead to substantial increases in generalization to downstream tasks. Such models, recently coined foundation…

Earth observation (EO) foundation models have emerged as an effective approach to derive latent representations of the Earth system from various remote sensing sensors. These models produce embeddings that can be used as analysis-ready…

机器学习 · 计算机科学 2025-11-21 Julia Peters , Karin Mora , Miguel D. Mahecha , Chaonan Ji , David Montero , Clemens Mosig , Guido Kraemer

The AiTLAS toolbox (Artificial Intelligence Toolbox for Earth Observation) includes state-of-the-art machine learning methods for exploratory and predictive analysis of satellite imagery as well as repository of AI-ready Earth Observation…

计算机视觉与模式识别 · 计算机科学 2022-01-24 Ivica Dimitrovski , Ivan Kitanovski , Panče Panov , Nikola Simidjievski , Dragi Kocev

Geospatial foundation models provide precomputed embeddings that serve as compact feature vectors for large-scale satellite remote sensing data. While these embeddings can reduce data-transfer bottlenecks and computational costs, Earth…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Erik Scheurer , Rocco Sedona , Stefan Kesselheim , Gabriele Cavallaro

Carefully curated and annotated datasets are the foundation of machine learning, with particularly data-hungry deep neural networks forming the core of what is often called Artificial Intelligence (AI). Due to the massive success of deep…

计算机视觉与模式识别 · 计算机科学 2023-10-31 Michael Schmitt , Seyed Ali Ahmadi , Yonghao Xu , Gulsen Taskin , Ujjwal Verma , Francescopaolo Sica , Ronny Hansch

Accurate mapping of column-averaged CO2 (XCO2) over agricultural landscapes is essential for guiding emission mitigation strategies. We present a Spatiotemporal Vision Transformer with Wavelets (ST-ViWT) framework that reconstructs…

We introduce \textit{SeismoGPT}, a transformer-based model for forecasting three-component seismic waveforms in the context of future gravitational wave detectors like the Einstein Telescope. The model is trained in an autoregressive…

机器学习 · 计算机科学 2025-09-29 Waleed Esmail , Alexander Kappes , Stuart Russell , Christine Thomas

Earth observation (EO) foundation models (FMs) are increasingly trained on multisensor data, spanning multispectral imagery (MSI), synthetic aperture radar (SAR), and derived geospatial layers, but hyperspectral imagery (HSI) remains…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Nassim Ait Ali Braham , Aaron Banze , Conrad M. Albrecht , Julien Mairal , Jocelyn Chanussot , Xiao Xiang Zhu

Satellite images are snapshots of the Earth surface. We propose to forecast them. We frame Earth surface forecasting as the task of predicting satellite imagery conditioned on future weather. EarthNet2021 is a large dataset suitable for…

机器学习 · 计算机科学 2021-04-21 Christian Requena-Mesa , Vitus Benson , Markus Reichstein , Jakob Runge , Joachim Denzler

Satellite Earth-observation (EO) time series in the optical and microwave ranges of the electromagnetic spectrum are often irregular due to orbital patterns and cloud obstruction. Compositing addresses these issues but loses information…

Earth observation (EO) satellites produce massive streams of multispectral image time series, posing pressing challenges for storage and transmission. Yet, learned EO compression remains fragmented and lacks publicly available, large-scale…

计算机视觉与模式识别 · 计算机科学 2026-03-06 Julen Costa-Watanabe , Isabelle Wittmann , Benedikt Blumenstiel , Konrad Schindler

The framework of the seventeen sustainable development goals is a challenge for developers and researchers applying artificial intelligence (AI). AI and earth observations (EO) can provide reliable and disaggregated data for better…

计算机视觉与模式识别 · 计算机科学 2019-07-08 Natalia Efremova , Dennis West , Dmitry Zausaev

Earth Observation (EO) is essential for perceiving dynamic land surface changes, yet deploying autonomous EO in open environments is hindered by the immense diversity of multi-source data and heterogeneous tasks. While remote sensing agents…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Sijie Zhao , Feng Liu , Xueliang Zhang , Hao Chen , Xinyu Gu , Zhe Jiang , Fenghua Ling , Ben Fei , Wenlong Zhang , Junjue Wang , Weihao Xuan , Pengfeng Xiao , Naoto Yokoya , Lei Bai

Accurate estimation of global terrestrial evapotranspiration (ET) is essential to understanding changes in the water cycle, which are expected to intensify in the context of climate change. Current global ET products are derived from…

大气与海洋物理 · 物理学 2023-09-14 Haiyang Shi

Estimating historical evapotranspiration (ET) is essential for understanding the effects of climate change and human activities on the water cycle. This study used historical weather station data to reconstruct ET trends over the past 300…

大气与海洋物理 · 物理学 2024-07-25 Haiyang Shi

The value of Earth observation foundation models for high-impact ecological applications remains insufficiently characterized. This study is one of the first to systematically evaluate the performance, limitations and practical…

计算机视觉与模式识别 · 计算机科学 2026-02-25 Craig Mahlasi , Gciniwe S. Baloyi , Zaheed Gaffoor , Levente Klein , Anne Jones , Etienne Vos , Michal Muszynski , Geoffrey Dawson , Campbell Watson

Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present OlmoEarth: a multimodal, spatio-temporal foundation model that employs a novel self-supervised…

This work presents AstroPT, an autoregressive pretrained transformer developed with astronomical use-cases in mind. The AstroPT models presented here have been pretrained on 8.6 million $512 \times 512$ pixel $grz$-band galaxy postage stamp…

天体物理仪器与方法 · 物理学 2024-05-27 Michael J. Smith , Ryan J. Roberts , Eirini Angeloudi , Marc Huertas-Company

The growing availability of Earth Observation (EO) data and recent advances in Computer Vision have driven rapid progress in machine learning for EO, producing domain-specific models at ever-increasing scales. Yet this progress risks…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Tasos Papazafeiropoulos , Nikolaos Ioannis Bountos , Nikolas Papadopoulos , Ioannis Papoutsis

Transformer-based foundation models have achieved remarkable progress in tasks such as time-series forecasting and image segmentation. However, they frequently suffer from error accumulation in multivariate long-sequence prediction and…

机器学习 · 计算机科学 2026-02-04 Hua Wang , Jinghao Lu , Fan Zhang