Detailed maps on the spatial and temporal distribution of crops are key for a better understanding of agricultural practices and for food security management. Multi-temporal remote sensing data and deep learning (DL) have been extensively studied for deriving accurate crop maps. However, strategies to solve the problem of transferring crop classification models over time, e.g., training the model with data for a recent year and mapping back to the past, have not been fully explored. This is due to the lack of a generalized method for aggregating optical data with regard to the irregularity in annual clear sky observations and the scarcity of multi-annual crop reference data to support a more generalized DL model. In this study, we tackled these challenges by introducing a method namely Temporal Encoding (TE) to capture the irregular phenological information. Subsequently, we adapted and integrated two methods, i.e., Random Observations Selection (ROS) and Random Day Shifting (RDS) to simulate the variability of temporal sparsity as well as the shifts of crop phenology over different years. We tested this approach with a 1-dimensional Convolutional Neural Network (1D-CNN) and a Transformer Network models. Our results for both classifiers showed that models trained with crop reference data from 2018 and a dense time series of Landsat 7/8 and Sentinel-2 A/B data can be transferred with little decreases in accuracy to map 12 consecutive years from 2010 to 2021. The Transformer Network was slightly more accurate, while the 1D-CNN was much three times faster. Furthermore, the proposed models could achieve similar performances in the same years with and without fully available satellite information. The TE with ROS and RDS appears well suited for improving temporal transferability to support long term historic crop mapping.

中文翻译：

---

具有时间编码和深度学习增强功能的时间可转移作物映射


关于农作物时空分布的详细地图是更好地了解农业实践和粮食安全管理的关键。多时相遥感数据和深度学习（DL）已被广泛研究以获取准确的农作物地图。然而，解决作物分类模型随时间迁移问题的策略（例如，用最近一年的数据训练模型并映射回过去）尚未得到充分探索。这是由于缺乏一种通用的方法来聚合关于年度晴空观测不规则性的光学数据，并且缺乏支持更通用的深度学习模型的多年作物参考数据。在这项研究中，我们通过引入一种称为时间编码（TE）的方法来捕获不规则的物候信息来应对这些挑战。随后，我们采用并集成了随机观测选择（ROS）和随机日移（RDS）两种方法来模拟时间稀疏性的变化以及不同年份作物物候的变化。我们使用一维卷积神经网络 (1D-CNN) 和 Transformer 网络模型测试了这种方法。我们对这两个分类器的结果表明，使用 2018 年作物参考数据以及 Landsat 7/8 和 Sentinel-2 A/B 数据的密集时间序列训练的模型可以在精度几乎没有降低的情况下转移到 2010 年至 2021 年连续 12 年的地图上Transformer 网络稍微准确一些，而 1D-CNN 速度快三倍。此外，无论有没有完全可用的卫星信息，所提出的模型都可以在相同的年份内实现类似的性能。 具有 ROS 和 RDS 的 TE 似乎非常适合提高时间可转移性，以支持长期历史作物绘图。