[论文解读] Early- and in-season crop type mapping without current-year ground truth: generating labels from historical information via a topology-based approach

Chenxi Lin, Liheng Zhong+4 more|arXiv (Cornell University)|Oct 19, 2021

Remote Sensing in Agriculture被引用 9

一句话总结

本文提出一种基于拓扑结构的方法，通过从历史数据中转移跨年度光谱特征空间的拓扑关系，无需当年的实地验证数据即可生成作物类型早期及在季标签。利用Landsat-8和Sentinel-2数据，该方法在玉米的抽丝期和大豆的开花期即可实现玉米F1值0.887、大豆F1值0.851，从而以极低的标注成本实现及时且高精度的作物制图。

ABSTRACT

Land cover classification in remote sensing is often faced with the challenge of limited ground truth. Incorporating historical information has the potential to significantly lower the expensive cost associated with collecting ground truth and, more importantly, enable early- and in-season mapping that is helpful to many pre-harvest decisions. In this study, we propose a new approach that can effectively transfer knowledge about the topology (i.e. relative position) of different crop types in the spectral feature space (e.g. the histogram of SWIR1 vs RDEG1 bands) to generate labels, thereby support crop classification in a different year. Importantly, our approach does not attempt to transfer classification decision boundaries that are susceptible to inter-annual variations of weather and management, but relies on the more robust and shift-invariant topology information. We tested this approach for mapping corn/soybeans in the US Midwest and paddy rice/corn/soybeans in Northeast China using Landsat-8 and Sentinel-2 data. Results show that our approach automatically generates high-quality labels for crops in the target year immediately after each image becomes available. Based on these generated labels from our approach, the subsequent crop type mapping using a random forest classifier reach the F1 score as high as 0.887 for corn as early as the silking stage and 0.851 for soybean as early as the flowering stage and the overall accuracy of 0.873 in Iowa. In Northeast China, F1 scores of paddy rice, corn and soybeans and the overall accuracy can exceed 0.85 two and half months ahead of harvest. Overall, these results highlight unique advantages of our approach in transferring historical knowledge and maximizing the timeliness of crop maps. Our approach supports a general paradigm shift towards learning transferrable and generalizable knowledge to facilitate land cover classification.

研究动机与目标

• 为解决遥感作物分类中地面验证数据有限的挑战。
• 实现在不依赖当年田间数据的前提下，实现作物类型早期及在季制图。
• 在光谱特征空间中跨年度转移作物类型之间稳健且对位移不变的拓扑关系。
• 在保持高分类精度的同时，降低地面验证数据收集的成本与延迟。
• 通过及时、准确的作物图支持收获前决策制定。

提出的方法

• 该方法识别并转移作物类型在光谱特征空间中的相对空间排列（即拓扑结构），例如SWIR1与RDEG1波段的直方图。
• 其重点在于拓扑关系——如作物簇之间的相对位置——而非随天气和管理措施变化的固定决策边界。
• 从历史Landsat-8和Sentinel-2数据中提取拓扑特征，用于源年度的训练。
• 随后将这些拓扑模式直接应用于目标年度影像获取后的第一时间，生成无需地面验证的伪标签。
• 使用生成的标签训练随机森林分类器，实现实时作物类型制图。
• 该方法在北美中西部的玉米/大豆系统以及中国东北地区的水稻/玉米/大豆系统中进行了验证。

实验结果

研究问题

• RQ1 光谱特征空间中的拓扑关系是否可跨年度可靠转移，以在无当年地面验证数据的情况下生成作物标签？
• RQ2 仅依赖历史拓扑知识与当年影像，能否实现早期准确的作物类型制图？
• RQ3 基于拓扑的标签生成方法在早期分类中相比传统方法具有多大优势？
• RQ4 该方法对天气和农业实践的年度间变化具有多强的鲁棒性？
• RQ5 该方法是否能在如北美中西部和中国东北地区等多样化的农业生态区实现高精度？

主要发现

• 该方法在北美中西部地区为玉米和大豆生成了高质量的伪标签，F1值分别达到0.887和0.851，最早可至抽丝期和开花期。
• 在爱荷华州，利用生成标签的作物图总体准确率达到0.873，展现出极低标注成本下的优异性能。
• 在东北中国，水稻、玉米和大豆的F1值均超过0.85，且在收获前约两个半月即实现。
• 该方法无需当年地面验证数据即可实现高精度，显著降低了数据采集成本。
• 基于拓扑的迁移方法对天气和管理措施的年度间变化表现出强鲁棒性。
• 结果凸显了拓扑作为遥感土地覆盖分类中稳定且可迁移信号的巨大潜力。