Related Experiment Video
Updated: Jul 19, 2026
07:36
Visualizing Early Infection Sites of Rice Blast Disease (Magnaporthe oryzae) on Barley (Hordeum vulgare) Using a Basic Microscope and a Smartphone
Published on: March 17, 2023
Machine learning techniques in disease forecasting: a case study on rice blast prediction.
Rakesh Kaundal1, Amar S Kapoor, Gajendra P S Raghava
1Bioinformatics Centre, Institute of Microbial Technology, Sector 39-A, Chandigarh 160036, India. rakesh@imtech.res.in <rakesh@imtech.res.in>
BMC Bioinformatics
|November 7, 2006
Summary
Support Vector Machines (SVM) offer superior plant disease forecasting compared to traditional methods. A new SVM-based web server aids researchers and farmers in timely disease management decisions.
Area of Science:
- Plant pathology
- Computational biology
- Agricultural science
Background:
- Existing plant disease prediction models, including neural networks and multiple regression, have limitations in predicting unknown data and require long training times.
- There is a need for advanced prediction software to better understand plant-pathogen-environment interactions.
- An accessible online tool for timely disease prediction is lacking for researchers and farmers.
Purpose of the Study:
- To introduce a novel prediction approach using Support Vector Machines (SVM) for developing weather-based plant disease models.
- To address the limitations of existing modeling techniques in plant disease forecasting.
- To provide a practical tool for early detection and management of plant diseases.
Main Methods:
- Developed and validated weather-based prediction models using a five-fold cross-validation procedure.
- Compared Support Vector Machines (SVM) against conventional multiple regression (REG) and back-propagation neural network (BPNN), and generalized regression neural network (GRNN).
- Selected six significant weather variables as predictor variables for model development.
Main Results:
- SVM-based models demonstrated superior performance in both cross-year and cross-location validation compared to REG, BPNN, and GRNN.
- For cross-year models, SVM achieved a correlation coefficient (r) of 0.77 and percent mean absolute error (%MAE) of 36.66.
- For cross-location models, SVM achieved an r of 0.74 and %MAE of 44.12, outperforming other methods.
Conclusions:
- Support Vector Machines (SVM) significantly outperform existing machine learning techniques and conventional regression approaches for plant disease forecasting.
- A novel SVM-based web server for rice blast prediction has been developed, offering a unique resource for the plant science community and farmers.
- The developed web server is freely available online, facilitating informed decision-making for disease management.
Related Concept Videos
01:18Steps in Outbreak Investigation
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
01:59Plant Breeding and Biotechnology
Crop cultivation has a long history in human civilization, with records showing the cultivation of cereal plants beginning at around 8000 BC. This early plant breeding was developed primarily to provide a steady supply of food.