Creative Commons source reading · Machine learning for performance
Artificial intelligence–Driven detection and decision support system for precision management of maize downy mildew
G J; Dhole A; D D
Originally published in PLoS One · 2026-03-09
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
AbstractArtificial intelligence (AI) enables rapid and precise plant disease detection, offering transformative potential for crop protection. Maize downy mildew (MDM), a destructive disease, causes substantial yield losses, making early detection critical. In this study, we evaluated the performance of thirteen machine-learning (ML) and deep-learning (DL) algorithms for classifying healthy and infected maize leaves using a curated field dataset. Model performance was assessed using multiple metrics, including accuracy, precision, recall, F1-score, and AUC-ROC. Among the tested models, VGG16 achieved the highest performance, with 97% accuracy, 0.98 precision, 0.95 recall, 0.97 F1-score, and an AUC-ROC of 0.99. Training and validation curves indicated minimal overfitting, demonstrating robust generalization. Feature visualization using…
Discussion
Maize (Zea mays L.) is a globally important cereal crop with major contributions to food security, livestock feed, and agro-industrial uses [5,6,21]. However, its productivity is severely constrained by downy mildew, caused by Peronosclerospora spp., particularly in tropical and subtropical regions [22,23]. Yield losses are often substantial, underscoring the need for reliable diagnostic and management strategies. Conventional diagnostic methods, including field-based scoring and laboratory confirmation, are limited by subjectivity, cost, and scalability [24,25]. In recent years, machine-learning and deep-learning approaches have emerged as powerful alternatives for plant disease detection, providing rapid, accurate, and scalable solutions [11,26]. Our study compared thirteen ML and DL algorithms for classifying maize downy mildew and…
Conclusion
This study demonstrates the potential of deep-learning–based approaches, particularly VGG16, for accurate and interpretable detection of maize downy mildew, achieving superior performance over conventional ML models. Integration of AI-driven disease classification with decision support system–guided fungicide advisories resulted in substantial reductions in disease severity, significant yield gains, and enhanced economic returns. By combining advanced diagnostic tools with practical management strategies, the work provides a scalable framework for sustainable maize health management. While further validation under diverse agro-climatic conditions and development of lightweight models for field deployment are necessary, the findings highlight a transformative pathway toward reducing crop losses, improving farmer profitability, and…
Editorial reading guide
- What data created and tested the model, and was evaluation independent?
- What is the cost of a false positive, false negative or out-of-distribution decision?
