Title

Early Drought Plant Stress Detection with Bi-Directional Long-Term Memory Networks

Abstract

Early drought stress detection is a promising strategy that enables us to move from a reactive to a more proactive approach to manage drought risks and impacts. In this work, we apply for the first time the Bidirectional Long Short-Term Memory (BLSTM) networks to RGB images for accurate drought plant stress detection in the early stage. In addition, an optimal data collection strategy (ODCS) is investigated to use less time and manpower for the purpose of accurate early drought stress condition detection. The proposed method is validated on two independently collected RGB image datasets. In both datasets, the BLSTM method achieves competitive classification performances compared to three other deep learning methods. By using the proposed ODCS, our method can use only 2/3 of the entire dataset to achieve 74.6 percent F-score for the patch sequence classification and 72.0 percent F-score for the image sequence classification.

Department(s)

Computer Science

Second Department

Civil, Architectural and Environmental Engineering

Comments

This work is supported by NSF CAREER award IIS-1351049, NSF EPSCoR Grant IIA-1355406, Intelligent System Center and Center of Biomedical Science and Engineering at Missouri University of Science and Technology.

Keywords and Phrases

Deep learning; Drought; Stresses; Bi-directional; Classification performance; Drought stress; Drought stress conditions; Learning methods; Long term memory; Pro-active approach; Sequence classification; Classification (of information); Data acquisition; Data set; Detection method; Image analysis; Learning; Memory; Model validation

International Standard Serial Number (ISSN)

0099-1112

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2018 American Society for Photogrammetry and Remote Sensing, All rights reserved.

Share

 
COinS