Algae classification algorithm based on chlorophyll fluorescence dynamics

Abstract This study presents a rapid and accurate algorithm for classifying algae based on chlorophyll fluorescence dynamics. A comprehensive dataset of five representative algal species was collected using a photosynthesis meter. A Bayesian-optimized extreme gradient boosting (XGBoost)-based prediction model was developed and evaluated against three machine-learning methods. The experimental results demonstrate that the proposed method achieves the highest overall classification performance, with an accuracy rate of 0.96. The feature importance analysis further indicated that fluorescence wavelengths contributed significantly to classification, with the highest importance at 440 nm and the lowest at 563 nm. These findings indicate that fluorescence dynamics can effectively capture species-specific spectral characteristics and provide a robust framework for rapid identification of diverse algal taxa. This work contributes to a better understanding of marine ecosystem dynamics. It provides technical support for marine environmental monitoring and the early detection of ecological events, such as harmful algal blooms.