Canopy anomaly classification using hybrid machine learning

B. Maestrini; J.M. Michielsen; S. Boersma; S. Wan; A. Beniers; G. Kessel; F. Hollewand; M. Shamsi; M. Afonso

Jump to Content

Canopy anomaly classification using hybrid machine learning

In: Precision agriculture '25

Authors:

B. Maestrini

B. Maestrini
Bernardo.maestrini@wur.nl

Search for other papers by B. Maestrini in
Current site
Google Scholar
PubMed

J.M. Michielsen

J.M. Michielsen

Search for other papers by J.M. Michielsen in
Current site
Google Scholar
PubMed

S. Boersma

S. Boersma

Search for other papers by S. Boersma in
Current site
Google Scholar
PubMed

S. Wan

S. Wan

Search for other papers by S. Wan in
Current site
Google Scholar
PubMed

A. Beniers

A. Beniers

Search for other papers by A. Beniers in
Current site
Google Scholar
PubMed

G. Kessel

G. Kessel

Search for other papers by G. Kessel in
Current site
Google Scholar
PubMed

F. Hollewand

F. Hollewand

Search for other papers by F. Hollewand in
Current site
Google Scholar
PubMed

M. Shamsi

M. Shamsi

Search for other papers by M. Shamsi in
Current site
Google Scholar
PubMed

, and

M. Afonso

M. Afonso

Search for other papers by M. Afonso in
Current site
Google Scholar
PubMed

Type:: Chapter

Pages:: 730–736

DOI:: https://doi.org/10.1163/9789004725232_096

Access via:

Dar Hadith al Hassania

Download PDF

An hybrid machine learning model that detects anomalies in canopy reflectance and identifies their cause in potato crops was developed. The model was created by training a long-short-term-memory neural network on synthetic crop NDVI data generated by coupling a potato growth model (Tipstar) and a canopy reflectance model (PROSAIL). The following stress factors were considered: no stress (control), N deficiency, presence of weeds, poor potato emergence. The model was validated against field experimental data – collected for two years – where the different stresses were imposed. The balanced model accuracy on the experimental dataset ranged between 50 and 100%, depending on the year and the stress factor.

Citation Info

Save
Cite
Email this content

Share link with colleague or librarian

You can email a link to this page to a colleague or librarian:
Email this content
or copy the link directly:

https://brill.edhh.ma/edcollchap-oa/book/9789004725232/BP000096.xml
The link was not copied. Your current browser may not support copying via this button.

Link copied successfully

Collapse
Expand

Precision agriculture '25

E-Book ISBN:: 9789004725232

Publisher:: Wageningen Academic

Print Publication Date:: 18 Jun 2025

Subjects
- Life Sciences
  - General
  - Agriculture & Environment

Metrics

	All Time	Past 365 days	Past 30 Days
Abstract Views	0	0	0
Full Text Views	78	65	4
PDF Views & Downloads	109	86	4

African Studies	Education	Media Studies
American Studies	History	Middle East and Islamic Studies
Ancient Near East and Egypt	Human Rights and Humanitarian Law	Musicology
Art History	International Law	Philosophy
Asian Studies	International Relations	Religious Studies
Biblical Studies	Jewish Studies	Slavic and Eurasian Studies
Biology	Languages and Linguistics	Social Sciences
Book History and Cartography	Life Sciences	Theology and World Christianity
Classical Studies	Literature and Cultural Studies

Subjects

Authors

Open Access

Product Information

Company

Contact

Canopy anomaly classification using hybrid machine learning

Citation Info

Share link with colleague or librarian

Precision agriculture '25

Table of Contents

Metrics

Metrics