发表机构
VITO Remote Sensing（VITO遥感公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究将过往预测和BVL掩码纳入模型，提出CTY嵌入编码器，在540万像素的泛欧数据集上使作物F1提升，纠正召回偏差，为地理空间模型提供低成本方案。
AI 中文摘要
机器学习，尤其是深度网络，正越来越多地用于推导更高级的地球观测（EO）产品，如年度土地覆盖和作物类型地图。许多产品已投入业务运行：每年处理新获取的数据，通常使用同一模型，从而扩展多年存档。在此过程中，这些系统会积累两种几乎从未反馈到模型中的有用信号：系统自身的过往预测存档，以及处理联盟中其他合作伙伴生成的辅助图层。这两种信号通常在网络外部使用，作为基于规则的后处理或固定输入掩码。以哥白尼陆地监测服务高分辨率图层（HRL）农田作物类型产品为测试平台，我们表明，将这两种信号纳入模型，可将单年单任务像素分类器转变为能跨年推理的模型。我们引入作物类型（CTY）嵌入编码器，将每个过往预测表示为按置信度缩放、按时间排序的分类标记，并对年份轴进行注意力机制处理，同时研究应如何在模型的输入和输出中表示外部提供的基础植被图层（BVL）掩码。为在重新标记非作物像素时公平比较设计，我们仅对18种作物类别进行评估，并分别报告精确率和召回率。在约540万带标签像素的泛欧数据集上，添加预测历史使仅作物的F1值提升1.6个百分点（pp），更重要的是，纠正了召回率偏向的误差分布，其中多年生作物和木本作物的提升最大（橄榄+4.6，水果+3.7，坚果+3.2 pp）。在历史数据和目标年份中一致表示BVL掩码，使作物类别额外提升约2.5个百分点。该方法适用于任何生成类别地图的重复性地理空间模型或基础模型，是一种低成本方案。
英文摘要
Machine learning, and deep networks in particular, are increasingly used to derive higher-level Earth observation (EO) products such as annual land-cover and crop-type maps. Many are generated operationally: each year a new acquisition is processed, typically with the same model, extending a multi-year archive. In the process these systems accumulate two kinds of useful signal that are almost never fed back into the model: the system's own archive of past predictions, and ancillary layers produced by other partners in a processing consortium. Both are normally used outside the network, as rule-based post-processing or a fixed input mask. Using the Copernicus Land Monitoring Service High Resolution Layer (HRL) Croplands crop-type product as a testbed, we show that bringing both signals inside the model turns a single-year, single-task pixel classifier into one that reasons across years. We introduce a Crop Type (CTY) embedding encoder that represents each past prediction as a confidence-scaled, time-ordered categorical token and attends over the year axis, and we study how the externally provided Base Vegetation Layer (BVL) mask should be represented in the model's inputs and outputs. To compare designs fairly when they relabel non-crop pixels, we evaluate on the 18 crop classes only and report precision and recall separately. On a pan-European dataset of about 5.4M labelled pixels, adding the prediction history raises crop-only F1 by 1.6 percentage points (pp) and, more importantly, corrects a recall-skewed error profile, with the largest gains on perennial and tree crops (olives +4.6, fruits +3.7, nuts +3.2 pp). Representing the BVL mask consistently in both the history and the target year adds about 2.5 pp on the crop classes. The approach is a low-cost recipe for any recurring geospatial or foundation model that emits class maps.
Comments17 pages, 7 figures Updated abstract to match with arxiv submission
