Crop type classification using satellite observations is an important tool for providing insights about planted area and enabling estimates of crop condition and yield, especially within the growing season when uncertainties around these quantities are highest. As the climate changes and extreme weather events become more frequent, these methods must be resilient to changes in domain shifts that may occur, for example, due to shifts in planting timelines. In this work, we present an approach for within-season crop type classification using moderate spatial resolution (30 m) satellite data that addresses domain shift related to planting timelines by normalizing inputs by crop growth stage. We use a neural network leveraging both convolutional and recurrent layers to predict if a pixel contains corn, soybeans, or another crop or land cover type. We evaluated this method for the 2019 growing season in the midwestern US, during which planting was delayed by as much as 1-2 months due to extreme weather that caused record flooding. We show that our approach using growth stage-normalized time series outperforms fixed-date time series, and achieves overall classification accuracy of 85.4% prior to harvest (September-November) and 82.8% by mid-season (July-September).

中文翻译：

---

使用生长阶段标准化的多光谱卫星观测中的弹性季节性作物类型分类

使用卫星观测进行作物类型分类是一种重要工具，可用于提供有关种植面积的见解并能够估计作物状况和产量，尤其是在这些数量的不确定性最高的生长季节。随着气候变化和极端天气事件变得更加频繁，这些方法必须能够适应可能发生的领域变化的变化，例如，由于种植时间表的变化。在这项工作中，我们提出了一种使用中等空间分辨率 (30 m) 卫星数据进行季节内作物类型分类的方法，该方法通过按作物生长阶段标准化输入来解决与种植时间线相关的领域转移。我们使用神经网络利用卷积层和循环层来预测像素是否包含玉米、大豆或其他作物或土地覆盖类型。我们在美国中西部的 2019 年生长季节评估了这种方法，在此期间，由于极端天气导致创纪录的洪水，种植推迟了 1-2 个月。我们表明，我们使用生长阶段标准化时间序列的方法优于固定日期时间序列，并且在收获前（9 月至 11 月）实现了 85.4% 的总体分类准确率，在季节中期（7 月至 9 月）达到了 82.8%。