Salvato in:
Dettagli Bibliografici
Autori principali: Rui, Yicheng, Duan, Xiao-Wei, Deng, Licai, Yang, Fan, Dang, Zhengming, Du, Zhengjun, Peng, Junhao, Chu, Wenhao, Mahmut, Umut, Li, Kexin, Wu, Yiyun, Feng, Fabo
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.16429
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915869820452864
author Rui, Yicheng
Duan, Xiao-Wei
Deng, Licai
Yang, Fan
Dang, Zhengming
Du, Zhengjun
Peng, Junhao
Chu, Wenhao
Mahmut, Umut
Li, Kexin
Wu, Yiyun
Feng, Fabo
author_facet Rui, Yicheng
Duan, Xiao-Wei
Deng, Licai
Yang, Fan
Dang, Zhengming
Du, Zhengjun
Peng, Junhao
Chu, Wenhao
Mahmut, Umut
Li, Kexin
Wu, Yiyun
Feng, Fabo
contents Ground-based time-domain observatories require minute-by-minute, site-scale awareness of cloud cover, yet existing all-sky datasets are short, daylight-biased, or lack astrometric calibration. We present LenghuSky-8, an eight-year (2018-2025) all-sky imaging dataset from a premier astronomical site, comprising 429,620 $512 \times 512$ frames with 81.2% night-time coverage, star-aware cloud masks, background masks, and per-pixel altitude-azimuth (Alt-Az) calibration. For robust cloud segmentation across day, night, and lunar phases, we train a linear probe on DINOv3 local features and obtain 93.3% $\pm$ 1.1% overall accuracy on a balanced, manually labeled set of 1,111 images. Using stellar astrometry, we map each pixel to local alt-az coordinates and measure calibration uncertainties of approximately 0.37 deg at zenith and approximately 1.34 deg at 30 deg altitude, sufficient for integration with telescope schedulers. Beyond segmentation, we introduce a short-horizon nowcasting benchmark over per-pixel three-class logits (sky/cloud/contamination) with four baselines: persistence (copying the last frame), optical flow, ConvLSTM, and VideoGPT. ConvLSTM performs best but yields only limited gains over persistence, underscoring the difficulty of near-term cloud evolution. We release the dataset, calibrations, and an open-source toolkit for loading, evaluation, and scheduler-ready alt-az maps to boost research in segmentation, nowcasting, and autonomous observatory operations.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16429
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LenghuSky-8: An 8-Year All-Sky Cloud Dataset with Star-Aware Masks and Alt-Az Calibration for Segmentation and Nowcasting
Rui, Yicheng
Duan, Xiao-Wei
Deng, Licai
Yang, Fan
Dang, Zhengming
Du, Zhengjun
Peng, Junhao
Chu, Wenhao
Mahmut, Umut
Li, Kexin
Wu, Yiyun
Feng, Fabo
Instrumentation and Methods for Astrophysics
Artificial Intelligence
Computer Vision and Pattern Recognition
I.4.6; I.2.10
Ground-based time-domain observatories require minute-by-minute, site-scale awareness of cloud cover, yet existing all-sky datasets are short, daylight-biased, or lack astrometric calibration. We present LenghuSky-8, an eight-year (2018-2025) all-sky imaging dataset from a premier astronomical site, comprising 429,620 $512 \times 512$ frames with 81.2% night-time coverage, star-aware cloud masks, background masks, and per-pixel altitude-azimuth (Alt-Az) calibration. For robust cloud segmentation across day, night, and lunar phases, we train a linear probe on DINOv3 local features and obtain 93.3% $\pm$ 1.1% overall accuracy on a balanced, manually labeled set of 1,111 images. Using stellar astrometry, we map each pixel to local alt-az coordinates and measure calibration uncertainties of approximately 0.37 deg at zenith and approximately 1.34 deg at 30 deg altitude, sufficient for integration with telescope schedulers. Beyond segmentation, we introduce a short-horizon nowcasting benchmark over per-pixel three-class logits (sky/cloud/contamination) with four baselines: persistence (copying the last frame), optical flow, ConvLSTM, and VideoGPT. ConvLSTM performs best but yields only limited gains over persistence, underscoring the difficulty of near-term cloud evolution. We release the dataset, calibrations, and an open-source toolkit for loading, evaluation, and scheduler-ready alt-az maps to boost research in segmentation, nowcasting, and autonomous observatory operations.
title LenghuSky-8: An 8-Year All-Sky Cloud Dataset with Star-Aware Masks and Alt-Az Calibration for Segmentation and Nowcasting
topic Instrumentation and Methods for Astrophysics
Artificial Intelligence
Computer Vision and Pattern Recognition
I.4.6; I.2.10
url https://arxiv.org/abs/2603.16429