PlumX Metrics
Embed PlumX Metrics

Monitoring plant diseases and pests through remote sensing technology: A review

Computers and Electronics in Agriculture, ISSN: 0168-1699, Vol: 165, Page: 104943
2019
  • 397
    Citations
  • 587
    Usage
  • 769
    Captures
  • 0
    Mentions
  • 5
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

  • Citations
    397
    • Citation Indexes
      394
    • Policy Citations
      3
      • Policy Citation
        3
  • Usage
    587
  • Captures
    769
  • Social Media
    5
    • Shares, Likes & Comments
      5
      • Facebook
        5

Review Description

Plant diseases and pests endanger agriculture and forestry significantly around the world. The implementation of non-contact, highly-efficient, and affordable methods for detecting and monitoring plant diseases and pests over vast areas could greatly facilitate plant protection. In this respect, different forms of remote sensing methods have been introduced for detecting and monitoring plant diseases and pests in many ways. This review outlines the state-of-the-art research achievements in relation to sensing technologies, feature extraction, and monitoring algorithms that have been conducted at multiple scales. Based on their characteristics and maturity in detecting and monitoring plant diseases and pests, sensing systems are classified into groups that include: visible & near-infrared spectral sensors (VIS-NIR); fluorescence and thermal sensors; and synthetic aperture radar (SAR) and light detection and ranging (Lidar) systems. Based on the data acquired from these remote sensing systems and sensitivity analysis, a variety of remote sensing features are proposed and identified as surrogates in the detection and monitoring processes. They include (1) optical, fluorescence, and thermal parameters; (2) image-based landscape features; and (3) features associated with habitat suitability. We also review the algorithms that link the remote sensing features with the occurrence of plant diseases and pests for identifying, differentiating and determining severity of diseases and pests over large areas. The algorithms including statistical discriminant analyses, machine learning algorithms, regression-based models and spectral unmixing algorithms using data collected at a single time or multiple times. Finally, according to the review, we provide a general framework to facilitate the monitoring of an unknown disease or pest highlighting future challenges and trends.

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know