Smart intercropping system to detect leaf disease using hyperspectral imaging and hybrid deep learning for precision agriculture.

Abstract

Introduction The rapid growth of the global population and intensive agricultural activities has posed serious environmental challenges. In response, there is an increasing demand for sustainable agricultural solutions that ensure efficient resource utilization while maintaining ecological balance. Among these, intercropping has gained prominence as a viable method, promoting enhanced land use efficiency and fostering environment for crop development. However, disease management in intercropping systems remains complex due to the potential for cross-infection and overlapping disease symptoms among crops. Early and precise illness recognition is, therefore, critical for sustaining crop condition and efficiency. Methods This study introduces an intelligent intercropping framework for early leaf disease detection, utilizing hyperspectral imaging and hybrid deep learning models for precision agriculture. Hyperspectral imaging captures intricate biochemical and structural variations in crops like maize, soybean, pea, and cucumber-subtle markers of disease that are otherwise imperceptible. These images enable accurate identification of diseases such as rust, leaf spot, and complex co-infections. To refine disease region segmentation and improve detection accuracy, the proposed model employs the synergistic swarm optimization (SSO) algorithm. A phase attention fusion network (PANet) is utilized for deep feature extraction, minimizing false detection rates. Furthermore, a dual-stage Kepler optimization (DSKO) algorithm addresses the challenge of high-dimensional data by choosing the most applicable landscapes. The disease classification is performed using a random deep convolutional neural network (R-DCNN). Results and discussion Experimental evaluations were conducted using publicly available hyperspectral datasets for maize-soybean and pea-cucumber intercropping systems. The suggested ideal attained remarkable organization accuracies of 99.676% and 99.538% for the respective intercropping systems, demonstrating its potential as a robust, non-invasive tool for smart, sustainable agriculture.

Plant phenotyping relevance

植物の葉の病徴をハイパースペクトル画像から検出・分類する画像解析手法が研究の中心であり、病害状態という植物表現型を直接推定しているため含める。

Code and data availability

The supplied blocks describe a hyperspectral leaf-disease detection pipeline, but the only dataset mentioned is a publicly available hyperspectral dataset curated by Liu et al. (2024) — cited prior work, not a paper-specific deposit by these authors. No data availability statement, code repository, model checkpoint, or

No evidence-backed public reproduction asset is currently recorded.