首页  >  科学研究  >  科研成果  >  正文
科研成果
博士生冯璐玮的论文在 IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 刊出
发布时间:2022-01-05 10:22:22     发布者:易真     浏览次数:

标题: Multitask Learning of Alfalfa Nutritive Value From UAV-Based Hyperspectral Images

作者: Feng, LW (Feng, Luwei); Zhang, Z (Zhang, Zhou); Ma, YC (Ma, Yuchi); Sun, YZ (Sun, Yazhou); Du, QY (Du, Qingyun); Williams, P (Williams, Parker); Drewry, J (Drewry, Jessica); Luck, B (Luck, Brian)

来源出版物: IEEE GEOSCIENCE AND REMOTE SENSING LETTERS DOI: 10.1109/LGRS.2021.3079317 提前访问日期: MAY 2021

摘要: Alfalfa is a valuable and widely adapted forage crop, and its nutritive value directly affects animal performance and ultimately affects the profitability of livestock production. Traditional nutritive value measurement method is labor-intensive and time-consuming and thus hinders the determination of alfalfa nutritive values over large fields. The adoption of unmanned aerial vehicles (UAVs) facilitates the generation of images with high spatial and temporal resolutions for field-level agricultural research. Additionally, compared with other imaging modalities, hyperspectral data usually consist of hundreds of narrow spectral bands and allow the accurate detection, identification, and quantification of crop quality. Although various machine-learning methods have been developed for alfalfa quality prediction, they were all single-task models that learned independently for each quality trait and failed to utilize the underlying relatedness between each task. Inspired by the idea of multitask learning (MTL), this study aims to develop an approach that simultaneously predicts multiple quality traits. The algorithm first extracts shared information through a long short-term memory (LSTM)-based common hidden layer. To enhance the model flexibility, it is then divided into multiple branches, each containing the same or different number of task-specific fully connected hidden layers. Through comparison with multiple mainstream single-task machine-learning models, the effectiveness of the model is illustrated based on the measured alfalfa quality data and multitemporal UAV-based hyperspectral imagery.

作者关键词: Task analysis; Hyperspectral imaging; Mathematical model; Agriculture; Predictive models; Computer architecture; Logic gates; Alfalfa; hyperspectral imagery; multitask learning; nutritive value; unmanned aerial vehicle (UAV)

地址: [Feng, Luwei; Du, Qingyun] Wuhan Univ, Sch Resources & Environm Sci, Wuhan 430079, Peoples R China.

[Zhang, Zhou; Ma, Yuchi; Sun, Yazhou; Williams, Parker; Drewry, Jessica; Luck, Brian] Univ Wisconsin, Dept Biol Syst Engn, Madison, WI 53706 USA.

通讯作者地址: Zhang, Z (通讯作者)Univ Wisconsin, Dept Biol Syst Engn, Madison, WI 53706 USA.

电子邮件地址: zzhang347@wisc.edu

影响因子:3.966

 

信息服务
学院网站教师登录 学院办公电话 学校信息门户登录

版权所有 © 武汉大学资源与环境科学学院
地址:湖北省武汉市珞喻路129号 邮编:430079 
电话:027-68778381,68778284,68778296 传真:027-68778893    邮箱:sres@whu.edu.cn