Developing a Non-Destructive Chlorophyll Content Estimation in Mungbean Leaves Using Deep Learning

This study develops a deep learning-based tool for non-destructive chlorophyll content estimation in mungbean leaves, designed to supplement traditional measurement methods. Convolutional Neural Networks extract relevant leaf features from digital images, enhanced by image processing and data augmentation. The model achieved a 92% validation accuracy and a 0.15 mg/cm<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> mean absolute error, demonstrating its potential for precise estimation. A mobile application facilitates real-time, onsite assessment, offering a practical alternative to resourceintensive laboratory techniques. Future research will explore advanced deep learning architectures and refine measurement techniques to improve accuracy and enable widespread adoption in precision agriculture, ultimately providing a complementary approach to traditional chlorophyll analysis