Accurate and efficient assessment of plant photosynthetic pigment contents is crucial for monitoring plant health, growth, and stress responses. Traditional methods for pigment analysis require time-consuming laboratory procedures and specialized equipment, limiting their practicality for real-time monitoring in the field. In this study, we present a novel approach that utilizes artificial intelligence (AI) techniques within a mobile application for real-time assessment of plant photosynthetic pigment contents. The application integrates image analysis algorithms based on deep learning models to analyze plant leaf images captured by a mobile device's camera. The AI model accurately identifies and quantifies various photosynthetic pigments, including chlorophylls and carotenoids, providing instant information about plant physiological status. Experimental evaluations demonstrated the application's robustness and accuracy in estimating pigment contents across different plant species and growth stages. This mobile-based AI approach offers a convenient and rapid tool for on-site monitoring of plant health and can facilitate precision agriculture practices.

Plant photosynthetic pigments, artificial intelligence, deep learning

Huang, W., Jia, Z., & Li, H. (2020). Plant stress identification and classification using deep learning-based hyperspectral imaging. Remote Sensing, 12(3), 382.

Negin, B., & Alchanatis, V. (2020). Hyperspectral remote sensing for plant stress detection: current status and future perspectives. Journal of Applied Remote Sensing, 14(4), 042801.

Hu, P., Dong, W., Hu, X., & Deng, Y. (2021). Monitoring crop growth and health using unmanned aerial vehicles and artificial intelligence: A review. Remote Sensing, 13(10), 1904.

Fang, L., Zhang, Y., Liu, Y., Wang, X., & Yu, Z. (2020). Plant leaf chlorophyll content estimation from hyperspectral data using machine learning approaches. Remote Sensing, 12(7), 1087.

Li, F., Zhang, W., Zhang, Z., & Guo, W. (2019). Development of a mobile application for plant disease diagnosis using deep learning. Computers and Electronics in Agriculture, 161, 272-280.

Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.

Yang, G., Liu, Y., Tang, R., Xu, B., Xu, G., & Li, M. (2019). Application of deep learning in agriculture. Computers and Electronics in Agriculture, 163, 104859.

Liakos, K. G., Busato, P., Moshou, D., Pearson, S., & Bochtis, D. (2018). Machine learning in agriculture: A review. Sensors, 18(8), 2674.

Feng, X., Liu, H., Wang, M., & Liu, J. (2021). Estimating chlorophyll content of rice leaves based on machine learning algorithms using hyperspectral data. Computers and Electronics in Agriculture, 182, 106006.

Selvaraj, M. G., & Jayas, D. S. (2017). Artificial intelligence techniques for hyperspectral image analysis: A review. Biosystems Engineering, 163, 80-99.