Author(s)

JiaLe Zhang, TiLiang Zhang^*

Affiliation(s)

School of mathematics and statistics, Hubei University of Education, Wuhan 430205, Hubei, China.

Corresponding Author

TiLiang Zhang

ABSTRACT

Qingming Festival is an important traditional festival in China that combines cultural and economic value. The unpredictable weather in spring, especially the heavy rain, affects travel and flower viewing experiences. This article explores how to optimize Qingming flower viewing tourism under such weather conditions to improve economic benefits. This article proposes a quantitative analysis method based on the "rain shower" weather, which combines precipitation probability and precipitation amount to construct "rain shower" label data, and uses GRU recurrent neural network for weather classification prediction. In order to improve the accuracy of predictions, the SMOTE oversampling method was introduced, and the final model achieved an accuracy of 87.45% on the test set, providing a scientific basis for predicting the probability of rainfall during the Qingming Festival in 2026. Then, this article used a combination of deep modeling (GDD) and random forest regression to establish a flowering prediction model. The model simulates the flowering period based on temperature changes and integrates monitoring data from various regions to accurately predict the flowering periods of rapeseed flowers, cherry blossoms, and peonies. In the Qingming Festival of 2026, rapeseed flowers are the best viewing period in Wuyuan and Wuhan, peonies are in Luoyang and Xi'an, and cherry blossoms are approaching the end period, providing a basis for tourism planning. Finally, this article establishes a multi-objective path planning model aimed at optimizing the flower viewing experience. The model considers flowering period, weather, scenic spot rating, and transportation to construct a rating function. Under the three-day travel restriction, the best route was selected as "Luoyang Xi'an Turpan", which is suitable for the flowering period, comfortable in weather, and diverse in tourism. Adjustments can be made according to the actual situation.

KEYWORDS

Optimization algorithm; Quantitative analysis method; Weather modeling; Random forest regression; GRU Recurrent neural network

CITE THIS PAPER

JiaLe Zhang, TiLiang Zhang. Analysis of the flower appreciation route and economic promotion strategy for the "rain scene" during the Qingming Festival. World Journal of Economics and Business Research. 2025, 3(4): 40-46. DOI: https://doi.org/10.61784/wjebr3066.

REFERENCES

[1] Sun Linxuan, Deng Longsheng, Tang Dong, et al. Deformation patterns and stability prediction of Dongjiatun landslide in Yan'an area, Shaanxi Province under different recurrence periods of rainfall. Journal of Earth Science and Environment, 2025, 47(03): 331-343.

[2] Shen Haojun, Luo Yong, Zhao Zongci, et al. Research on Summer Rainfall Prediction in China Based on LSTM Network Progress in Climate Change Research, 2020, 16(3): 263.

[3] Liu Dong, Ru Wenchao, Zhang Liangliang, et al. Application of Fishhawk Optimization Algorithm to Improve the Safety Evaluation of Regional Water Energy Grain Linkage System Using Random Forest Model. Journal of Northeast Agricultural University, 2025, 56(04): 64-74.

[4] Li Hengchang, Zhou Qing, Shi Lijuan, et al. Research on the joint inversion of cloud base height using FY-4B and millimeter wave radar based on random forest algorithm//Chinese Meteorological Society Summary of the 36th Annual Meeting of the Chinese Meteorological Society - S4 Atmospheric Detection Shandong Meteorological Engineering Technology Center; Meteorological Observation Center of China Meteorological Administration, 2025: 127-129.

[5] Wang Yanxiao. The impact of climate change on the flowering period of peonies in Luoyang in the past 50 years Research on Agricultural Disasters, 2022, 12(08): 88-90.

[6] Zhao F, Wang L, Xu S. Identification of QTL-by-environment interaction by controlling polygenic background effect. Journal of Genetics and Genomics, 2025, 52(07): 915-926.

[7] Li Dongmei, Li Wenquan. Calculation Method for Road Capacity. Journal of Henan University, 2002, 6: 24-27.

[8] Li Xin, Jifeng Dai, Jianxin Lin, et al. A review of research on vulnerability assessment indicators for urban road networks. Highway Transportation Technology, 2016: 155-157.

[9] Qi Ruizhen. Vulnerability Assessment of Xiamen Road Network Based on Complex Networks and Topological Potential. Huaqiao University, 2023.

[10] Dailisa, He Zhengguang, He Meng, et al. Meta analysis of the Impact of OSAHS on Traffic Accident Risk. Modern Medicine and Health, 2025, 41(07): 1699-1705+1710.