A fast Fourier convolutional deep neural network for accurate and explainable discrimination of wheat yellow rust and nitrogen deficiency from Sentinel-2 time series data.
A fast Fourier convolutional deep neural network for accurate and explainable discrimination of wheat yellow rust and nitrogen deficiency from Sentinel-2 time series data.
复制标题
基于Sentinel-2时间序列数据的快速傅里叶卷积深度神经网络用于小麦黄锈病和缺氮的准确和可解释判别。
DOI：
10.3389/fpls.2023.1250844
复制
发表时间：
2023
影响因子：
5.6
通讯作者：
中科院分区：
文献类型：
--
作者：
准确和及时地检测植物胁迫对于保护产量至关重要，从而可以制定更有针对性的干预策略。遥感和深度学习的最新进展显示出以全自动和可重复的方式快速非侵入性检测植物胁迫的巨大潜力。然而，现有的模型总是面临着一些挑战：1）计算效率低，具有相似症状的不同压力之间的错误分类; 2）宿主-压力相互作用的可解释性差。在这项工作中，我们提出了一种新的快速傅立叶卷积神经网络（FFDNN）的准确和可解释的检测两种植物胁迫具有相似的症状（即小麦黄锈病和氮缺乏）。具体而言，与现有的CNN模型不同，所提出的模型的主要组成部分包括：1）快速傅立叶卷积块，一种新的快速傅立叶变换核作为基本感知单元，以取代传统的卷积核来捕获植物在各种时间尺度上对胁迫的局部和全局响应，并在傅立叶域中减少学习参数以提高计算效率; 2）Capsule特征编码器，用于将提取的特征封装成一系列向量特征，以表示特定应力的宿主-应力相互作用的层次结构的部分到整体的关系。此外，为了减轻过度拟合，光化学植被指数为基础的过滤器被放置作为预处理操作员，以消除非光化学噪声从输入的哨兵-2时间序列。所提出的模型进行了评估与地面实况数据控制和自然条件下。结果表明，高层次的矢量特征解释的主机压力的相互作用/响应的影响，所提出的模型实现了竞争优势，在检测和区分的黄锈病和氮缺乏的Sentinel-2时间序列的分类精度，鲁棒性和泛化。
Accurate and timely detection of plant stress is essential for yield protection, allowing better-targeted intervention strategies. Recent advances in remote sensing and deep learning have shown great potential for rapid non-invasive detection of plant stress in a fully automated and reproducible manner. However, the existing models always face several challenges: 1) computational inefficiency and the misclassifications between the different stresses with similar symptoms; and 2) the poor interpretability of the host-stress interaction. In this work, we propose a novel fast Fourier Convolutional Neural Network (FFDNN) for accurate and explainable detection of two plant stresses with similar symptoms (i.e. Wheat Yellow Rust And Nitrogen Deficiency). Specifically, unlike the existing CNN models, the main components of the proposed model include: 1) a fast Fourier convolutional block, a newly fast Fourier transformation kernel as the basic perception unit, to substitute the traditional convolutional kernel to capture both local and global responses to plant stress in various time-scale and improve computing efficiency with reduced learning parameters in Fourier domain; 2) Capsule Feature Encoder to encapsulate the extracted features into a series of vector features to represent part-to-whole relationship with the hierarchical structure of the host-stress interactions of the specific stress. In addition, in order to alleviate over-fitting, a photochemical vegetation indices-based filter is placed as pre-processing operator to remove the non-photochemical noises from the input Sentinel-2 time series. The proposed model has been evaluated with ground truth data under both controlled and natural conditions. The results demonstrate that the high-level vector features interpret the influence of the host-stress interaction/response and the proposed model achieves competitive advantages in the detection and discrimination of yellow rust and nitrogen deficiency on Sentinel-2 time series in terms of classification accuracy, robustness, and generalization.
登录
查看更多内容
DOI：
10.1016/j.isprsjprs.2014.03.016
发表时间：
2014-07-01
影响因子：
12.7
作者：
Behmann, Jan;Steinruecken, Joerg;Pluemer, Lutz
通讯作者：
Pluemer, Lutz
DOI：
10.3390/s17092022
发表时间：
2017-09-04
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Fuentes A;Yoon S;Kim SC;Park DS
通讯作者：
Park DS
DOI：
10.1016/j.jag.2015.03.017
发表时间：
2015-12-01
影响因子：
7.5
作者：
Elarab, Manal;Ticlavilca, Andres M.;Mckee, Mac
通讯作者：
Mckee, Mac
植被指数和光合参数检测小麦热胁迫能力的比较
影响因子：
6.2
作者：
Cao, Zhongsheng;Yao, Xia;Zhu, Yan
通讯作者：
Zhu, Yan
DOI：
10.25165/j.ijabe.20181102.3467
发表时间：
2018-03-01
影响因子：
2.4
作者：
Huang, Wenjiang;Lu, Junjing;Shi, Yue
通讯作者：
Shi, Yue