article · Expert Systems with Applications
Early detection of crop diseases is vital for safeguarding food security and minimising environmental harm caused by excessive chemical treatments. While deep learning offers effective automated disease classification, it often struggles to provide clear explanations to non-expert farmers or integrate essential domain and contextual knowledge, such as soil or plant data. Conversely, semantic web systems hold rich domain information but lack robust pattern-learning capabilities. To overcome these limitations, deep learning was combined with ontologies and knowledge graphs for cassava disease classification. The resulting framework achieved a 90.5 percent prediction accuracy on a large noisy dataset, alongside an average processing latency of approximately 3.85 seconds per sample. Crucially, the hybrid model delivers user-level explanations that integrate contextual agricultural insights, providing practical diagnostic support tailored for non-specialist end users.
Plant diseases threaten food yields and drive over-reliance on chemical interventions. Providing farmers with fast, accurate disease diagnosis alongside clear, understandable explanations helps non-experts make informed crop management decisions quickly. Integrating contextual agricultural knowledge directly into artificial intelligence tools bridges the gap between complex machine learning outputs and everyday farm management.
The system represents an applied and tested technology evaluated on a noisy dataset of over 5,000 samples. It could enable crop diagnostic mobile tools and decision-support services for farmers and agricultural advisors. With an average response time under four seconds and strong user validation, the method appears close to real-world pilot deployment, although the abstract does not describe an explicit path to commercial production.
AI-generated from the published abstract. Always read the original work before citing.
Food security is currently a major concern due to the growing global population, the exponential increase in food demand, the deterioration of soil quality, the occurrence of numerous diseases, and the effects of climate change on crop yield. Sustainable agriculture is necessary to solve this food security challenge. Disruptive technologies, such as of artificial intelligence, especially, deep learning techniques can contribute to agricultural sustainability. For example, applying deep learning techniques for early disease classification allows us to take timely action, thereby helping to increase the yield without inflicting unnecessary environmental damage, such as excessive use of fertilisers or pesticides. Several studies have been conducted on agricultural sustainability using deep learning techniques and also semantic web technologies such as ontologies and knowledge graphs. However, the three major challenges remain: (i) the lack of explainability of deep learning-based systems (e.g. disease information), especially to non-experts like farmers; (ii) a lack of contextual information (e.g. soil or plant information) and domain-expert knowledge in deep learning-based systems; and (iii) the lack of pattern learning ability of systems based on the semantic web, despite their ability to incorporate domain knowledge. Therefore, this paper presents the work on disease classification, addressing the challenges as mentioned earlier by combining deep learning and semantic web technologies, namely ontologies and knowledge graphs. The findings are: (i) 0.905 (90.5%) prediction accuracy on large noisy dataset; (ii) ability to generate user-level explanations about disease and incorporate contextual and domain knowledge; (iii) the average prediction latency of 3.8514 s on 5268 samples; (iv) 95% of users finding the explanation of the proposed method useful; and (v) 85% of users being able to understand generated explanations easily–show that the proposed method is superior to the state-of-the-art in terms of performance and explainability and is also suitable for real-world scenarios.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.eswa.2023.120955
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
