Multimodal AI model improves tomato leaf disease diagnosis accuracy
A Multi-Modal Generative Model for Tomato Disease Leaves Understanding
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Tomato plants can get diseases that make their leaves look sick, and understanding these problems is important for farmers. The authors created a new computer program called SOLAR that can look at pictures of tomato leaves and answer different questions about the disease, like what it is and how bad it is. SOLAR uses both images and language together to give better and more complete answers than previous tools. This means it can help explain the disease symptoms more clearly and support better decisions for plant care.
What this means in practice
- •For precision agriculture teams: Provide a single multimodal model for assessing tomato leaf diseases including symptoms, severity, and diagnostic questions to support field decision-making.
- •For plant pathology extension services: Use a unified AI tool to generate detailed and explainable responses to farmer inquiries about tomato leaf disease diagnosis.
- •For remote plant monitoring providers: Integrate a generative visual question answering system for diverse disease diagnosis tasks beyond simple label prediction in crop leaf images.$Commercial implications: Enables development of AI-powered precision crop monitoring platforms that deliver richer diagnostic insights to agricultural customers.
Authors
Khang Nguyen Quoc, Minh-Phuoc Tran, Gia-Han Truong, Luyl-Da Quach
Abstract
Artificial intelligence for plant disease analysis has advanced from task-specific classifiers to multi-modal models capable of jointly interpreting visual and textual information. However, practical deployment in precision agriculture remains limited because most existing approaches treat disease understanding as isolated prediction tasks, failing to capture the complementary relationships among symptom recognition, severity assessment, and question-driven diagnostic reasoning. In tomato pathology, accurate interpretation of diseased leaves requires more than label prediction; it demands integrating visual symptoms with semantic context to support a comprehensive and explainable understanding. Here, we present SOLAR, a multimodal generative model that understands tomato disease spanning six question-answering tasks. SOLAR learns to align visual features with task-aware language representations by Fusion Expert module based on mixture-of-expert, enabling it to generate contextually relevant answers across diverse diagnostic tasks. By formulating tomato disease analysis as a generative Visual Question Answering (VQA) task, SOLAR provides a flexible framework that supports multi-task inference within a single model while improving performance and cross-task knowledge sharing. We evaluate SOLAR on $41,677$ images, including $216,209$ Question-Answering (QA) pairs to understand tomato leaf disease under both closed and open-ended QA settings. Experimental results show that SOLAR consistently outperforms state-of-the-art vision-only, vision-language, and task-specific models across all tasks, demonstrating superior accuracy, robustness, and multimodal reasoning. These findings highlight the potential of generative multimodal modeling as an effective direction for understanding of plant disease. The code for this study is available at https://github.com/EnalisUs/SOLAR.