From Surface Forecasting to Observability Forecasting: A Latent World Model for Cloud-Aware EO Monitoring
作者: Mohanad Albughdadi
分类: cs.CV
发布日期: 2026-07-15
💡 一句话要点
提出云监测的可观测性预测模型以提升地球观测效率
🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)
关键词: 地球观测 可观测性预测 云监测 多光谱图像 气象驱动
📋 核心要点
- 现有地球观测方法在图像到达时无法有效判断表面是否可见,导致数据利用率低。
- 本文提出了一种改进的LeWorldModel模型,专注于云监测序列的可观测性预测,旨在提高图像采集的有效性。
- 实验结果表明,LeWorldModel在可用性预测和准确性方面显著优于传统的持久性基线,准确率提升幅度明显。
📝 摘要(中文)
地球观测处理链的瓶颈在于图像到达时表面是否可见。本文将此问题视为可观测性预测问题,基于EarthNet2021数据集,利用多光谱图像和气象驱动因素预测下一次采集是否可用,并预测可用视图的返回时间。我们改进了LeWorldModel模型,使其适应云监测序列,最终模型在23904个训练集上训练,具有1800万可训练参数,并在多个评估基准上表现优异。
🔬 方法详解
问题定义:本文解决的是地球观测图像到达时表面可见性的问题,现有方法在此方面存在较大不足,导致图像数据的有效利用率低下。
核心思路:论文提出了一种基于云监测的可观测性预测模型,利用多光谱图像和气象数据,预测下一次图像采集的可用性及其返回时间。
技术框架:整体架构包括数据预处理、模型训练和评估三个主要阶段。数据预处理将原始图像转换为包含五个图像通道和多个气象变量的序列,随后使用改进的LeWorldModel进行训练和评估。
关键创新:最重要的创新在于将LeWorldModel适配于云监测序列,显著提升了对可观测性预测的准确性,与传统方法相比,提供了更为精确的可用性预测。
关键设计:模型具有1800万可训练参数,采用特定的损失函数和网络结构,确保在训练过程中能够有效捕捉气象因素对图像可用性的影响。
🖼️ 关键图片
📊 实验亮点
实验结果显示,LeWorldModel在可用性预测的平衡准确率范围为0.769至0.887,而持久性基线仅为0.493至0.556。在首次可用预测的准确率方面,LeWorldModel的表现也显著优于持久性基线,准确率范围为0.602至0.806。
🎯 应用场景
该研究在地球观测领域具有广泛的应用潜力,尤其是在气象监测、环境监控和灾害响应等方面。通过提高图像采集的可用性,能够有效支持决策制定和资源管理,未来可能推动相关技术的进一步发展。
📄 摘要(原文)
The bottleneck of Earth Observation processing chains is not the arrival of new imagery but whether the surface is actually visible when the image arrives. We study this as an observability forecasting problem on EarthNet2021. Given recent multispectral imagery and exogenous weather drivers, the goal is to predict whether the next acquisition will be usable and, if not, when a usable view is likely to return. To do this, we adapt LeWorldModel, a joint-embedding predictive architecture world model, to cloud-aware Earth Observation sequences. The final pipeline converts raw minicubes into episodic HDF5 sequences with five image channels (blue, green, red, near-infrared, cloud mask) and eight meteorological and calendar covariates. The resulting model has 18.0M trainable parameters and is trained from scratch on 23,904 training episodes. The trained leWorldModel is evaluated under a locked protocol: linear probes are fit on train only, calibration choices are set on an internal validation split, and the fitted heads are then frozen for valsplit, IID, OOD, and extreme evaluation. On the full frozen-bundle observability benchmark, LeWorldModel consistently outperforms persistence. For next-step usability, balanced accuracy ranges from 0.769 to 0.887, compared with 0.493 to 0.556 for persistence. For exact first-usable-horizon prediction, accuracy ranges from 0.602 to 0.806, compared with 0.120 to 0.369 for persistence. Against a frozen LightGBM baseline fit on the same training windows, LeWorldModel is better on continuous clear/cloud regression and on exact recovery timing on valsplit, IID, and extreme, while LightGBM is stronger on the simpler binary any-usable-within-six task and is more robust on OOD. In separate sampled diagnostic analyses, LeWM also produces strong ranking-based anomaly signals under synthetic temporal inconsistencies.