从地表预测到可观测性预测：用于云感知地球观测监测的潜在世界模型

中文摘要 AI 辅助

地球观测处理链的瓶颈不在于新图像的到来，而在于图像到达时地表是否实际可见。我们将此作为EarthNet2021上的可观测性预测问题进行研究。给定近期多光谱图像和外部天气驱动因素，目标是预测下一次采集是否可用，若不可用，可用视图可能何时返回。为此，我们将联合嵌入预测架构世界模型LeWorldModel应用于云感知地球观测序列。最终管道将原始小立方体转换为具有五个图像通道（蓝、绿、红、近红外、云掩码）和八个气象及日历协变量的情节性HDF5序列。所得模型有1800万个可训练参数，在23904个训练情节上从头开始训练。训练后的LeWorldModel在锁定协议下评估：线性探测器仅在训练集上拟合，校准选择在内部验证分割上设置，然后冻结拟合的头部进行验证分割、独立同分布、非独立同分布和极端评估。在完整的冻结捆绑可观测性基准上，LeWorldModel始终优于持久性方法。对于下一步可用性，平衡准确率在0.769至0.887之间，而持久性方法为0.493至0.556。对于精确的首次可用时间预测，准确率在0.602至0.806之间，而持久性方法为0.120至0.369。与在相同训练窗口上拟合的冻结LightGBM基线相比，LeWorldModel在连续的晴/云回归以及验证分割、独立同分布和极端情况下的精确恢复时间方面表现更好，而LightGBM在更简单的六小时内任何可用的二元任务上更强，在非独立同分布情况下更稳健。在单独的采样诊断分析中，LeWM在合成时间不一致下也产生强大的基于排名的异常信号。

英文摘要

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.

发表机构

• European Centre for Medium-Range Weather Forecasts（欧洲中期天气预报中心）

机构由 AI 辅助整理，请以论文原文为准。