Early detection of Fusarium infection in corn using spectral analysis

T. Sandovsky, Y. Edan, S. Gad, A. Etzioni, T. Nacson, V. Alchanatis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This work presents a non-destructive methodology for early detection of Fusarium infection, by spectral analysis in the 350-2,500 nm range. Corn plants in greenhouse conditions were analysed using spectral analysis. The Lasso model was used to differentiate infected from non-infected plants based on the first derivative of leaf spectral reflectance. Fusarium infection was successfully recognized in plants at V2 growth stage with 74% success rate. This result enables infection detection at a stage which currently is not possible without destroying the plant, which can be further applied to map the disease in field scale.

Original languageAmerican English
Title of host publicationPrecision Agriculture 2019 - Papers Presented at the 12th European Conference on Precision Agriculture, ECPA 2019
EditorsJohn V. Stafford
PublisherWageningen Academic Publishers
Pages339-346
Number of pages8
ISBN (Electronic)9789086863372
DOIs
StatePublished - 1 Jan 2019
Event12th European Conference on Precision Agriculture, ECPA 2019 - Montpellier, France
Duration: 8 Jul 201911 Jul 2019

Publication series

NamePrecision Agriculture 2019 - Papers Presented at the 12th European Conference on Precision Agriculture, ECPA 2019

Conference

Conference12th European Conference on Precision Agriculture, ECPA 2019
Country/TerritoryFrance
CityMontpellier
Period8/07/1911/07/19

Keywords

  • Disease detection
  • Fusarium
  • Multispectral
  • Spectral analysis

All Science Journal Classification (ASJC) codes

  • Agronomy and Crop Science
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Early detection of Fusarium infection in corn using spectral analysis'. Together they form a unique fingerprint.

Cite this