Soybean is an important crop for food and animal feed. Production and area both continue to increase and expand into new areas and countries. Spatially explicit information on soybean cultivation is essential to crop monitoring, production estimation, and national accounting systems. However, its cultivation in diverse climate conditions, landscapes, and agricultural systems poses challenges to accurately map soybean across different regions and years. We propose an innovative soybean mapping method combining phenological alignment with machine learning (named here RF-DTW), which can be applied to diverse geographies and years by aligning phenological shifts and using distinctive features from Sentinel-2 time-series. The method first uses the dynamic time warping (DTW) algorithm to align the growing season between pixels across different sites. Then, based on the harmonized time-series, a set of distinctive features was identified and used to build random forest (RF) models to classify soybean across ten globally distributed sites and multiple years. Results show that the green chlorophyll vegetation index (GCVI), greenness and water content composite index (GWCCI), normalized difference senescent vegetation index (NDSVI), red edge position (REP), and short-wave infrared bands are important inputs for distinguishing soybean from other crops. Spectral-phenological features, particularly the curve slope metrics of GCVI and GWCCI during the peak to late growing season, rank as the most important features for mapping soybean. RF-DTW demonstrates good generalizability across ten study sites, achieving an overall accuracy (OA) of 0.92 and an F1-score of 0.84. F1-scores for eight out of ten sites ranged between 0.82 and 0.98, outperforming a benchmark method, although they were lower (F1-score < 0.60) for the two sites in Sub-Saharan Africa. Additionally, RF-DTW performs robustly when transferred to untrained regions and years, with most cases showing an F1-score higher than 0.70. Our proposed method, as a combination of phenological alignment and machine learning, can be used to map soybean accurately and efficiently across different regions and years, to provide crucial information for understanding the rapid dynamics of soybean cultivation and its global-scale impacts.

中文翻译：

---

一种通过 Sentinel-2 时间序列物候比对绘制大豆图谱的可靠方法


大豆是重要的食品和动物饲料作物。产量和面积都继续增加并扩展到新的地区和国家。关于大豆种植的空间明确信息对于作物监测、产量估算和国家核算系统至关重要。然而，它在不同的气候条件、景观和农业系统中的种植对准确绘制不同地区和年份的大豆构成了挑战。我们提出了一种创新的大豆绘图方法，将物候对齐与机器学习相结合（此处命名为 RF-DTW），该方法可以通过对齐物候变化和使用来自 Sentinel-2 时间序列的独特特征来应用于不同的地理和年份。该方法首先使用动态时间扭曲 （DTW） 算法来调整不同站点像素之间的生长季节。然后，根据协调的时间序列，确定了一组独特的特征，并用于构建随机森林 （RF） 模型，以将大豆分类到全球分布的 10 个地点和多年。结果表明：绿色叶绿素植被指数 （GCVI）、绿化含水量综合指数 （GWCCI） 、归一化差异衰老植被指数 （NDSVI） 、红边位置 （REP） 和短波红外波段是区分大豆与其他作物的重要输入。光谱物候特征，特别是 GCVI 和 GWCCI 在生长高峰到后期的曲线斜率指标，是绘制大豆图的最重要特征。RF-DTW 在 10 个研究地点中表现出良好的泛化性，总体准确率 （OA） 为 0.92，F1 分数为 0.84。10 个站点中有 8 个站点的 F1 分数在 0.82 到 0 之间。98 分，优于基准方法，尽管它们在撒哈拉以南非洲的两个地点的表现较低（F1 分数 < 0.60）。此外，RF-DTW 在转移到未训练的地区和年份时表现稳健，大多数情况下显示 F1 分数高于 0.70。我们提出的方法作为物候对齐和机器学习的结合，可用于准确有效地绘制不同地区和年份的大豆图，为理解大豆种植的快速动态及其全球规模的影响提供关键信息。