Plant disease epidemiology in the age of artificial intelligence and machine learning
Crop diseases pose a major threat to global food security, causing substantial yield losses and economic damage each year. Plant disease epidemiology studies the dynamics of plant-pathogen interactions and their impact on disease outcomes, considering environmental influences at a population level....
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Agriculture Communications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2949798125000195 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Crop diseases pose a major threat to global food security, causing substantial yield losses and economic damage each year. Plant disease epidemiology studies the dynamics of plant-pathogen interactions and their impact on disease outcomes, considering environmental influences at a population level. While recent advances in artificial intelligence (AI) and machine learning (ML) have introduced innovative tools for disease prediction and management, most applications have focused on plant disease detection, classification and severity quantification using imaging technologies and sensor-based data. However, their use in plant disease epidemiology, particularly in understanding host-pathogen interactions and the ecology and evolution of the pathosystems remains limited due to the complexity of multi-scale interactions. In this review, we first propose an updated plant disease epidemiology ‘disease pyramid’ model, incorporating ecological and evolutionary components into the traditional ‘disease triangle’ model. Following this, we discuss current ML applications in plant disease epidemiology, while highlighting both challenges and opportunities. We offer insights into potential input datasets that could significantly enhance the predictability and accuracy of ML models, while also outlining future directions for this rapidly evolving field. The aim of this review is to draw the reader's attention to the knowledge gap in the application of ML in plant disease epidemiology and showcase the vast potential for expanding the scope of more in-depth and comprehensive research in this field in the future. |
|---|---|
| ISSN: | 2949-7981 |