Towards Scalable Within-Season Crop Mapping With Phenology Normalization and Deep Learning
Towards Scalable Within-Season Crop Mapping With Phenology Normalization and Deep Learning
复制标题
DOI：
10.1109/jstars.2023.3237500
复制
发表时间：
2023
影响因子：
5.5
通讯作者：
Zi-Ling Yang;C. Diao;F. Gao
中科院分区：
文献类型：
--
作者：
Zi-Ling Yang;C. Diao;F. Gao
利用时间序列遥感数据绘制作物类型图对于广泛的农业应用至关重要。在生长季节进行作物绘图对于及时监测农业系统特别重要。由于难以及时获得当前生长季节的作物类型样本，目前大多数侧重于季节内作物制图的研究利用历史遥感和作物类型参考数据建立模型。然而，考虑到不同年份和地点的作物物候模式不同，可能无法直接使用前几年的作物类型样本，这妨碍了模型的可扩展性和可移植性，无法及时将其转换为当前季节的作物制图。本文提出了一种创新的季节内出苗（WISE）物候归一化深度学习模型，用于可扩展的季节内作物映射。农作物时间序列遥感数据首先被归一化的WISE作物出苗日期之前，被送入一个基于注意力的一维卷积神经网络分类器。与传统的基于植物的方法相比，WISE物候归一化方法大大有助于深度学习作物映射模型适应作物物候动态的时空变化。伊利诺伊州2017年至2020年的结果表明，该模型优于基于分类器的方法，在季末对玉米和大豆进行分类的总体准确率超过90%。在生长季节，该模型可以提供令人满意的性能（85%的整体准确度）1至4周前基于植物的方法。通过WISE物候归一化，所提出的模型在伊利诺伊州表现出更稳定的性能，并且可以转移到不同的年份，具有增强的可扩展性和鲁棒性。
Crop-type mapping using time-series remote sensing data is crucial for a wide range of agricultural applications. Crop mapping during the growing season is particularly critical in timely monitoring of the agricultural system. Most existing studies focusing on within-season crop mapping leverage historical remote sensing and crop type reference data for model building, due to the difficulty in obtaining timely crop type samples for the current growing season. Yet the crop type samples from previous years may not be used directly considering the diverse patterns of crop phenology across years and locations, which hampers the scalability and transferability of the model to the current season for timely crop mapping. This article proposes an innovative within-season emergence (WISE) phenology normalized deep learning model towards scalable within-season crop mapping. The crop time-series remote sensing data are first normalized by the WISE crop emergence dates before being fed into an attention-based one-dimensional convolutional neural network classifier. Compared to conventional calendar-based approaches, the WISE-phenology normalization approach substantially helps the deep learning crop mapping model accommodate the spatiotemporal variations in crop phenological dynamics. Results in Illinois from 2017 to 2020 indicate that the proposed model outperforms calendar-based approaches and yields over 90% overall accuracy for classifying corn and soybeans at the end of season. During the growing season, the proposed model can give satisfactory performance (85% overall accuracy) one to four weeks earlier than calendar-based approaches. With WISE-phenology normalization, the proposed model exhibits more stable performance across Illinois and can be transferred to different years with enhanced scalability and robustness.