DVTXAI: A Novel Deep Vision Transformer with an Explainable AI-based Framework and its Application in Agriculture

Abstract

Abstract Agriculture is one of the fundamental components of human civilization, contributing not only to food production but also to economic growth. Early identification of diseases in plants presents a significant challenge, as timely detection is crucial to increasing agricultural production. Incorporating the latest technology, such as artificial intelligence (AI) techniques, in fields can reduce major losses for farmers and also improve productivity. In this paper, we have proposed a Deep Vision transformer and an Explainable AI-based technique to overcome the various diseases in plants. Here, we have used the dataset "Plant Village," as a case study that focuses on two majorly grown crops like: potatoes and tomatoes. Further, we have analyzed nine diseases that affect these crops around the globe, with tomatoes showing six different conditions and potatoes affected by three bacterial diseases. The proposed DVTXAI framework incorporates the Deep vision transforms to detect plant diseases at an early stage. In the experiments, the proposed model achieves an accuracy of 93. 56% for tomatoes and 99.95% for potatoes. Additionally, the model is Explainable AI (XAI), which reveals the transparency mechanism that helps the farmer to make the right decision at an early stage of the crop.

Plant phenotyping relevance

植物画像から病害を推定する深層学習・説明可能AIフレームワークが研究の中心であり、植物病害状態の表現型推定手法として評価されている。

Code and data availability

植物フェノタイピング解析を再現する公開資産であることを、入力本文と直接リンクから確認できなかったため保留しました。

No evidence-backed public reproduction asset is currently recorded.