中国农业科学

• • 上一篇    

最新录用:基于Bi-LSTM模型的时间序列遥感作物分类研究

黄翀1,3※,侯相君1,2 #br#   

  1. 1中国科学院地理科学与资源研究所/资源与环境信息系统国家重点实验室,北京 1001012中国科学院大学,北京 1000493中国科学院地理科学与资源研究所/中国科学院黄河三角洲现代农业工程实验室,北京 100101
  • 出版日期:2022-05-11 发布日期:2022-05-11

Crop Classification with Time Series Remote Sensing based on Bi-LSTM Model

HUANG Chong1,3HOU XiangJun1,2 #br#   

  1. 1Institute of Geographical Sciences and Natural Resources, Chinese Academy of Sciences/State Key Laboratory of Resource and Environmental Information Systems, Beijing 100101; 2University of Chinese Academy of Sciences,Beijing 100049; 3CAS Engineering Laboratory for Yellow River Delta Modern Agriculture, Institute of Geographical Sciences and Natural Resources, Chinese Academy of Sciences,Beijing 100101
  • Published:2022-05-11 Online:2022-05-11

摘要: 【目的】及时、准确地作物分类制图是农情监测的重要依据。随着卫星遥感数据获取的时空分辨率显著提高,基于密集时间序列遥感数据的作物分类与早期识别成为可能。同时,以深度学习为前沿的机器学习方法快速发展,为作物遥感分类提供了新的技术支撑。【方法】本文以黄河三角洲地区为例,以哨兵2号全年可用卫星影像为数据源,构建年时间序列NDVI数据集;采用循环神经网络构架,搭建针对结构化时序数据的双向长短期记忆网络模型(bidirectional long short-term memoryBi-LSTM),探究结合时间序列遥感的深度学习模型在作物精细分类与生长季早期制图中的应用潜力。【结果】作物年生长时序特征对于大多数作物遥感分类识别都具有较好的区分能力,基于年时间序列NDVI数据的Bi-LSTM模型作物分类总体准确率达90.9%Kappa系数达到0.892。通过测试不同时间序列长度对作物分类的影响,确定了在满足一定制图精度情况下典型作物的最早可识别时间以实现对作物的早期制图。【结论】卫星影像时间序列蕴含的结构化特征信息可以有效地降低特定时段的作物光谱混淆;双向循环神经网络模型能够同时考虑前向和后向的时间状态信息,可以学习作物不同阶段的光谱变化特征,在水稻、棉花、春玉米等易混淆作物的识别上表现优异;模型能够有效地把握样本总体上的变化趋势,在农作物多分类任务中表现出较好的泛化能力和鲁棒性。对大多数作物来说,其分类精度随着数据时间序列长度增加而不断提高,冬小麦、水稻等作物在生长季早期即具有较为独特的分类特征,因而利用生长季早期的时间序列影像即可获得较高的制图精度,而棉花、春玉米等作物需要完整生长序列影像才能更好地保证分类精度。本研究通过集成深度学习和遥感时间序列,为及时、快速的区域作物高精度制图提供了可行的思路。

关键词: 作物分类 , 早期识别, 时序遥感, Bi-LSTM, 模型泛化

Abstract: ObjectiveTimely and accurate crop classification mapping is an important basis for agricultural situation monitoring. With the significant increase in spatial and temporal resolution of satellite remote sensing data acquisition, crop classification and early identification based on intensive time series remote sensing data have become possible. Meanwhile, the rapid development of machine learning methods with deep learning has provided new technical support for crop remote sensing classification.Method】In this paper, we take the Yellow River Delta region as an example and construct a time-series NDVI dataset using Sentinel-2 year-round available satellite images as the data source. Based on a recurrent neural network architecture, a Bidirectional Long Short-Term Memory (Bi-LSTM) network model is built to explore its potential application in crop classification using its feature learning capability for structured time series data. Result】Winter-wheat-summer-maize is the main crop cultivation pattern in the region, and the overall accuracy of the Bi-LSTM model reached 90.9% with a Kappa coefficient of 0.892. Crop accuracy improves with the increase of time series data length. The accuracy of crops such as winter-wheat and rice will improve significantly after the emergence of unique characteristics. Crops such as cotton and spring-maize require complete growth sequences to ensure classification accuracy. Conclusion】Structured feature information embedded in satellite image time series can effectively reduce crop spectral confusion at specific time periods. The Bi-LSTM model is able to consider both forward and backward temporal state information and can learn the spectral change characteristics of crops, which is excellent in the identification of confusing crops such as rice, cotton and spring corn. By testing the effect of different time series length on crop classification, the earliest identifiable time of typical crops was obtained for early mapping of crops under certain mapping accuracy. In addition, the deep learning model can effectively capture the variation trend on the sample in general, and shows better generalization ability and robustness in the crop multi-classification task. This study provides a feasible idea for regional crop mapping with high accuracy by integrating deep learning and remote sensing time series.


Key words: crop classification, early identification, time-series remote sensing, Bi-LSTM model, model generalization