Early Disease Detection in Hydroponic Crops Using Hyperspectral Imaging and CNN-Based Classification

Hemant Kumar, Ayan Rajput

Abstract: Hydroponic farming systems require precise and early disease detection mechanisms to ensure optimal crop yield and resource efficiency. Traditional visual inspection and RGB imaging methods are often inadequate for detecting early-stage plant stress and disease symptoms. This paper presents an intelligent Agri-Tech framework for disease detection in hydroponic crops using hyperspectral imaging and convolutional neural networks (CNNs). The proposed system captures spectral signatures beyond the visible range, enabling early identification of physiological changes in plants. A deep learning-based classification model is developed to analyze hyperspectral data and detect crop diseases with high accuracy. Experimental results demonstrate an overall detection accuracy of 94.6%, a 42% reduction in diagnosis time, and a 35% improvement in early disease identification compared to conventional methods. The findings highlight the effectiveness of integrating hyperspectral imaging with deep learning for sustainable and precision hydroponic agriculture.

Keywords: Agri-Tech, Hyperspectral Imaging, Convolutional Neural Networks, Hydroponic Farming, Plant Disease Detection, Deep Learning

How to Cite?: Hemant Kumar, Ayan Rajput, "Early Disease Detection in Hydroponic Crops Using Hyperspectral Imaging and CNN-Based Classification", Volume 14 Issue 12, December 2025, International Journal of Science and Research (IJSR), Pages: 2265-2268, https://www.ijsr.net/getabstract.php?paperid=SR251227223927, DOI: https://dx.doi.org/10.21275/SR251227223927