JCSAI | Journal of Computer Science and Artificial Intelligence
← Back to Volume 8, Issue 2

A Combined Prediction Model of Rainfall and Flowering Period Based on GRU and Random Forest for Qingming Festival Tourism

Xingyu Liu, Zige Xu, Xuejiao Lu, Miao Xi
Vol. 8, No. 2, pp. 17-21, 2026 DOI: 10.54097/n7yysv03 August 31, 2026
Download PDF
Abstract.Aiming at the uncertainty of rainfall and flowering period during the Qingming Festival, which directly affects the experience of spring outing and flower viewing activities, this paper proposes a combined prediction framework based on machine learning and phenology models. First, a rainfall discrimination standard for the “continuous drizzle” scenario is defined, and a prediction model based on GRU and SMOTE oversampling is established to forecast the rainfall probability and precipitation of typical cities during the Qingming Festival in 2026. Second, a flowering period prediction model integrating growing degree day (GDD) and random forest regression is constructed to predict the initial, full, and end flowering stages of rapeseed, cherry blossoms, and peony. The proposed method is verified on historical meteorological and phenological datasets. The results show that the rainfall prediction accuracy reaches 87.45%, and the mean absolute error (MAE) of the flowering period prediction is less than 2.5 days. The predicted results match the actual distribution of flowering periods in the middle and lower reaches of the Yangtze River and northern regions. The proposed model can provide reliable data support for tourism route planning, and has practical significance for the development of flower viewing tourism and the extension of cultural tourism industry chains.
Keywords. Qingming Festival Rainfall Prediction Flowering Period Forecast Growing Degree Day Random Forest
APA Citation Xingyu Liu, Zige Xu, Xuejiao Lu, Miao Xi (2026). A Combined Prediction Model of Rainfall and Flowering Period Based on GRU and Random Forest for Qingming Festival Tourism. Journal of Computer Science and Artificial Intelligence, 8(2), 17-21. https://doi.org/10.54097/n7yysv03

References

  1. Wang, Z., Li, C., Liu, B., et al. (2026). Physics informed GRU encoder decoder model for predicting cross scale mechanical behavior of rock. Computers and Geotechnics, 196, 108128.
  2. Bahrom, S., Abu, N., Rahman, A. H. N., et al. (2026). Forecasting of rainfall in Malaysia using time series analysis. Environmental Science and Pollution Research, 1–16.
  3. Fan, H., Ma, Y., Xu, Q., et al. (2026). Multi Feature and Multi Step Monthly Rainfall Forecasting with the Hybrid VMD LSTM CATNet Model in Diverse Climatic Regions. Water Resources Management, 40(5), 198.
  4. Aniley, E., Zemen, A., Belay, M., et al. (2025). Evaluating rainfall forecasting capability of multi source weather (MSWX) product over rainfall regimes of Ethiopia. Geocarto International, 40(1).
  5. Sahu, S., & Verma, P. (2025). Optimizing Irrigation Scheduling with a Hybrid Transformer GRU Model and Reinforcement Learning in Smart Agriculture. Water Resources Management, 40(1), 30.
  6. Zhang, B., Feng, N., Liu, S., et al. (2025). Construction of Flowering Period Prediction Model based on Mathematical Modeling. International Core Journal of Engineering, 11(11), 182–199.
  7. Tadayon, A., Nazari, M., Kerachian, R. (2025). Enhancing long lead rainfall forecasting in data scarce large watersheds using multi model fusion. Journal of Hydrology: Regional Studies, 62, 102936.
  8. Wang, E., Brown, H., Zheng, B., et al. (2025). Molecular physiological model integration revolutionizes cereal flowering prediction. The New Phytologist, 249(3), 1373–1388.
  9. Küllahcı, K., & Altunkaynak, A. (2024). Eigen time series modeling: a breakthrough approach to spatio temporal rainfall forecasting in basins. Neural Computing and Applications, 37(6), 1–22.
  10. Yumkhaibam, S., & Kusre, C. B. (2023). Application of artificial neural networks for time series rainfall forecasting in the Loktak lift irrigation command area of Manipur, India. Irrigation and Drainage, 73(2), 741–756.