Wheat yield and grain protein content (GPC) are two main optimization targets for breeding and cultivation. Remote sensing provides nondestructive and early predictions of yield and GPC, respectively. However, whether it is possible to simultaneously predict yield and GPC in one model and the accuracy and influencing factors are still unclear. In this study, we made a systematic comparison of different deep learning models in terms of data fusion, time-series feature extraction, and multitask learning. The results showed that time-series data fusion significantly improved yield and GPC prediction accuracy with R2 values of 0.817 and 0.809. Multitask learning achieved simultaneous prediction of yield and GPC with comparable accuracy to the single-task model. We further proposed a two-to-two model that combines data fusion (two kinds of data sources for input) and multitask learning (two outputs) and compared different feature extraction layers, including RNN (recurrent neural network), LSTM (long short-term memory), CNN (convolutional neural network), and attention module. The two-to-two model with the attention module achieved the best prediction accuracy for yield (R2=0.833) and GPC (R2=0.846). The temporal distribution of feature importance was visualized based on the attention feature values. Although the temporal patterns of structural traits and spectral traits were inconsistent, the overall importance of both structural traits and spectral traits at the postanthesis stage was more important than that at the preanthesis stage. This study provides new insights into the simultaneous prediction of yield and GPC using deep learning from time-series proximal sensing, which may contribute to the accurate and efficient predictions of agricultural production.
Patchy stomata are a common and characteristic phenomenon in plants. Understanding and studying the regulation mechanism of patchy stomata are of great significance to further supplement and improve the stomatal theory. Currently, the common methods for stomatal behavior observation are based on static images, which makes it difficult to reflect dynamic changes of stomata. With the rapid development of portable microscopes and computer vision algorithms, it brings new chances for stomatal movement observation. In this study, a stomatal behavior observation system (SBOS) was proposed for real-time observation and automatic analysis of each single stoma in wheat leaf using object tracking and semantic segmentation methods. The SBOS includes two modules: the real-time observation module and the automatic analysis module. The real-time observation module can shoot videos of stomatal dynamic changes. In the automatic analysis module, object tracking locates every single stoma accurately to obtain stomatal pictures arranged in time-series; semantic segmentation can precisely quantify the stomatal opening area (SOA), with a mean pixel accuracy (MPA) of 0.8305 and a mean intersection over union (MIoU) of 0.5590 in the testing set. Moreover, we designed a graphical user interface (GUI) so that researchers could use this automatic analysis module smoothly. To verify the performance of the SBOS, the dynamic changes of stomata were observed and analyzed under chilling. Finally, we analyzed the correlation between gas exchange and SOA under drought stress, and the correlation coefficients between mean SOA and net photosynthetic rate (Pn), intercellular CO2 concentration (Ci), stomatal conductance (Gs), and transpiration rate (Tr) are 0.93, 0.96, 0.96, and 0.97.
Recently, deep learning has been highly successful in image classification. Labeling the PolSAR data, however, is time-consuming and laborious and in response semi-supervised deep learning has been increasingly investigated in PolSAR image classification. Semi-supervised deep learning methods for PolSAR image classification can be broadly divided into two categories, namely pixels-based methods and superpixels-based methods. Pixels-based semi-supervised methods are liable to be affected by speckle noises and have a relatively high computational complexity. Superpixels-based methods focus on the superpixels and ignore tiny detail-preserving represented by pixels. In this paper, a Fuzzy superpixels based Semi-supervised Similarity-constrained CNN (FS-SCNN) is proposed. To reduce the effect of speckle noises and preserve the details, FS-SCNN uses a fuzzy superpixels algorithm to segment an image into two parts, superpixels and undetermined pixels. Moreover, the fuzzy superpixels algorithm can also reduce the number of mixed superpixels and improve classification performance. To exploit unlabeled data effectively, we also propose a Similarity-constrained Convolutional Neural Network (SCNN) model to assign pseudo labels to unlabeled data. The final training set consists of the initial labeled data and these pseudo labeled data. Three PolSAR images are used to demonstrate the excellent classification performance of the FS-SCNN method with data of limited labels.
The increasing applications of Polarimetric SAR (PolSAR) image classification demand for effective superpixels algorithms. Fuzzy superpixels algorithms reduce the misclassification rate by dividing pixels into superpixels, which are groups of pixels of homogenous appearance, and undetermined pixels. However, two key issues remain to be addressed in designing a fuzzy superpixel algorithm for PolSAR image classification. Firstly, the polarimetric scattering information, which is unique in PolSAR images, is not effectively used. Such information can be utilized to generate superpixels more suitable for PolSAR images. Secondly, the ratio of undetermined pixels is fixed for each image in the existing techniques, ignoring the fact that the difficulty of classifying different objects varies in an image. To address these two issues, we propose a polarimetric scattering information based adaptive fuzzy superpixels (AFS) algorithm for PolSAR images classification. In AFS, the correlation between pixels' polarimetric scattering information, for the first time, is considered to generate superpixels. This correlation is further used to dynamically and adaptively update the ratio of undetermined pixels. AFS is evaluated extensively against different evaluation metrics and compared with the state-of-the-art superpixels algorithms on three PolSAR images. The experimental results demonstrate the superiority of AFS on PolSAR image classification problems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.