Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Geospatial-based mapping and monitoring of pest and disease outbreaks utilizing machine learning

Goenka, Deep Kumar and Pal, Mahendra LU (2025) p.213-255
Abstract

For this project, machine learning and cutting-edge remote sensing technologies are used to create a geospatial mapping and monitoring system for agricultural pest and disease outbreaks. By combining satellite data, unmanned aerial vehicle hyperspectral evaluation, and environmental factors, the system can identify the spread of pests and diseases in real time. Data evaluation and outbreak prediction activities are carried out by three machine learning algorithms: random forest, support vector machine, and neural networks. The system’s architecture helps regulate resources for greater environmental preservation while producing targeted pest-management suggestions. By using geographic data and predictive methods to carry out focused... (More)

For this project, machine learning and cutting-edge remote sensing technologies are used to create a geospatial mapping and monitoring system for agricultural pest and disease outbreaks. By combining satellite data, unmanned aerial vehicle hyperspectral evaluation, and environmental factors, the system can identify the spread of pests and diseases in real time. Data evaluation and outbreak prediction activities are carried out by three machine learning algorithms: random forest, support vector machine, and neural networks. The system’s architecture helps regulate resources for greater environmental preservation while producing targeted pest-management suggestions. By using geographic data and predictive methods to carry out focused interventions and facilitate sustainable agriculture management practices, the system improves the identification of possible hazards. Because the project developers are always working on system refinement through field verification and user input, problems with data quality, model correctness, and real-time monitoring require constant attention. Researchers are currently looking at how blockchain technology and Internet of Things device integration might improve system scalability and guarantee data integrity. The created system represents a significant advancement in the management of pests and diseases via the use of machine learning and geospatial technology applications, which offer scalable solutions for global agricultural problems and increase the resilience of the food chain.

(Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Geospatial mapping, hyperspectral imaging, machine learning, pest and disease monitoring, remote sensing
host publication
Agricultural Insights from Space : Machine Learning Applications in Satellite Data Analysis - Machine Learning Applications in Satellite Data Analysis
pages
43 pages
publisher
Elsevier
external identifiers
  • scopus:105026964040
ISBN
9780443341144
9780443341137
DOI
10.1016/B978-0-443-34113-7.00009-2
language
English
LU publication?
yes
id
7bff6166-332d-439a-803d-c7e9ea988e3a
date added to LUP
2026-02-16 09:33:30
date last changed
2026-02-16 09:34:46
@inbook{7bff6166-332d-439a-803d-c7e9ea988e3a,
  abstract     = {{<p>For this project, machine learning and cutting-edge remote sensing technologies are used to create a geospatial mapping and monitoring system for agricultural pest and disease outbreaks. By combining satellite data, unmanned aerial vehicle hyperspectral evaluation, and environmental factors, the system can identify the spread of pests and diseases in real time. Data evaluation and outbreak prediction activities are carried out by three machine learning algorithms: random forest, support vector machine, and neural networks. The system’s architecture helps regulate resources for greater environmental preservation while producing targeted pest-management suggestions. By using geographic data and predictive methods to carry out focused interventions and facilitate sustainable agriculture management practices, the system improves the identification of possible hazards. Because the project developers are always working on system refinement through field verification and user input, problems with data quality, model correctness, and real-time monitoring require constant attention. Researchers are currently looking at how blockchain technology and Internet of Things device integration might improve system scalability and guarantee data integrity. The created system represents a significant advancement in the management of pests and diseases via the use of machine learning and geospatial technology applications, which offer scalable solutions for global agricultural problems and increase the resilience of the food chain.</p>}},
  author       = {{Goenka, Deep Kumar and Pal, Mahendra}},
  booktitle    = {{Agricultural Insights from Space : Machine Learning Applications in Satellite Data Analysis}},
  isbn         = {{9780443341144}},
  keywords     = {{Geospatial mapping; hyperspectral imaging; machine learning; pest and disease monitoring; remote sensing}},
  language     = {{eng}},
  pages        = {{213--255}},
  publisher    = {{Elsevier}},
  title        = {{Geospatial-based mapping and monitoring of pest and disease outbreaks utilizing machine learning}},
  url          = {{http://dx.doi.org/10.1016/B978-0-443-34113-7.00009-2}},
  doi          = {{10.1016/B978-0-443-34113-7.00009-2}},
  year         = {{2025}},
}