This paper proposes a comprehensive experiment scheme that uses PredRNN technology to design a cyanobacterial spatio-temporal sequence prediction system. This experiment can provide effective reference for the treatment of cyanobacteria in lakes. The experiment uses Python language to build a cyanobacterial spatiotemporal sequence prediction system based on the PredRNN algorithm. The whole experimental program includes five modules: Pre-processing of cyanobacterial NDVI (normalized difference vegetation index) image data, segmentation of cyanobacterial dataset, training of spatial-temporal prediction model, testing of prediction model and colorized display. Through comparative experiments, the feasibility and practicality of using the PredRNN algorithm for cyanobacterial spatio-temporal sequence prediction are demonstrated. The experimental scheme is designed to help students master Python programming skills, help improve students’ comprehensive application of image processing and computer vision knowledge, realize the extension of teaching theory to practice in computer vision courses, strengthen the organic combination of teaching and research, enhance students’ research literacy, and promote the development of computer vision courses.