近年來許多國家皆提倡公共自行車，其特性不但符合永續運輸的概念，還可以在大眾運輸導向的發展中扮演關鍵角色，決策者為了提升運作效率還有增加租借量必須了解何種因素會影響公共自行車的使用，以往研究大多探討建成環境、社會經濟對自行車使用的影響，然而這兩者較不會在短時間內變動；而天氣帶來的影響較少被關注，天氣是無時無刻在變化的，所以了解天氣如何影響自行車使用對於即時調整或長期規劃都有極大的幫助。利用自行車數據來進行相關研究時，非常規的旅次可能會影響研究結果，而該類資料可嘗試從天氣狀況進行判斷，若是知道天氣因子到達某個數值時就會減少自行車使用，就可定義出不適合騎乘自行車的環境。
國外探討天氣如何影響公共自行車使用的文獻表明不同時段、季節時，各個天氣因子對公共自行車使用會有不同程度的影響，本研究選用溫度、濕度、風速等天氣因子當作自變數，應變數則選擇同站點、同時段租借次數的變化量。本研究欲使用的自變數中包含連續變數與類別變數，且天氣因子與公共自行車租借量之間並非是線性關係，因此選擇了隨機森林作為模型建構的方法，此方法可以有效處理多維而且類型不同的變數，同時又能找出天氣因子和租借量之間的非線性關係，在預測數值方面也普遍優於一般的線性回歸。
研究結果顯示每項天氣因子都有某段區間會使自行車使用增加，某些區段會導致自行車使用減少，且在不同季節各變數會有不同程度的影響，天氣因子對於不同特性的自行車旅次造成的影響也有差異。

In recent years, many countries have advocated public bicycles. Public bicycles' characteristics not only correspond to the concept of sustainable transportation, but also can play a key role in the TOD. In order to improve the operation efficiency and increase the rental, decision makers must understand what factors will affect the use of public bicycles. Previous studies mostly discussed the impact of the built environment and social economy on the use of bicycles; However, they are less likely to change in a short time; Less attention has been paid to the impact of the weather. The weather is changing all the time. Therefore, understanding how the weather affects bicycle use is great help for immediate adjustment or long-term planning. When using bicycle data for research, abnormal trips may affect the research results, and that kind of data can be determined by the weather conditions. If it is known that the use of bicycles will be reduced when the weather factor reaches a certain value, the environment that is not suitable for cycling can be defined.

Foreign literature on how the weather affects the use of public bicycles shows that various weather factors will have different degrees of impact on the use of public bicycles in different periods and seasons. In this study, weather factors such as temperature, humidity and wind speed are selected as independent variables, and the change of rental times at the same station and the same time is selected as the dependent variable. The independent variables to be used in this study include continuous variables and category variables, and the relationship between weather factors and public bicycle rentals is not linear. Therefore, random forest is selected as the model construction method. This method can effectively deal with multi-dimensional and different types of variables, and can find out the nonlinear relationship between weather factors and rentals. It is also generally superior to the general linear regression in the prediction value.

The results show that each factor has a section that will increase bicycle use, and some sections will reduce bicycle use. In different seasons, variables will have different impact, and the impact of weather factors on bicycle trips with different characteristics is also distinct.

Ahmed, F., Rose, G., & Jakob, C. (2013). Commuter cyclist travel behavior examination of the impact of changes in weather. Transportation Research Record(2387), 76-82.
Ashqar, H. I., Elhenawy, M., & Rakha, H. A. (2019). Modeling bike counts in a bike-sharing system considering the effect of weather conditions. Case Studies on Transport Policy, 7(2), 261-268.
Bao, J., Yu, H., & Wu, J. M. (2019). Short-term FFBS demand prediction with multi-source data in a hybrid deep learning framework. Iet Intelligent Transport Systems, 13(9), 1340-1347.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
Campbell, A. A., Cherry, C. R., Ryerson, M. S., & Yang, X. (2016). Factors influencing the choice of shared bicycles and shared electric bikes in Beijing. Transportation Research Part C: Emerging Technologies, 67, 399-414.
El-Assi, W., Salah Mahmoud, M., & Nurul Habib, K. (2015). Effects of built environment and weather on bike sharing demand: a station level analysis of commercial bike sharing in Toronto. Transportation, 44(3), 589-613.
Faghih-Imani, A., & Eluru, N. (2016). Determining the role of bicycle sharing system infrastructure installation decision on usage: Case study of montreal BIXI system. Transportation Research Part A: Policy and Practice, 94, 685-698.
Fournier, N., Christofa, E., & Knodler, M. A. (2017). A sinusoidal model for seasonal bicycle demand estimation. Transportation Research Part D-Transport and Environment, 50, 154-169.
Gao, K., Yang, Y., Li, A. Y., & Qu, X. B. (2021). Spatial heterogeneity in distance decay of using bike sharing: An empirical large-scale analysis in Shanghai. Transportation Research Part D-Transport and Environment, 94, 102814.
Gebhart, K., & Noland, R. B. (2014). The impact of weather conditions on bikeshare trips in Washington, DC. Transportation, 41(6), 1205-1225.
He, Y., Song, Z., Liu, Z., & Sze, N. N. (2019). Factors influencing electric bike share ridership: analysis of park city, Utah. Transportation Research Record: Journal of the Transportation Research Board, 2673(5), 12-22.
Kim, H. (2020). Seasonal impacts of particulate matter levels on bike sharing in Seoul, South Korea. International journal of environmental research and public health, 17(11), 3999.
Kim, K. (2018). Investigation on the effects of weather and calendar events on bike-sharing according to the trip patterns of bike rentals of stations. Journal of Transport Geography, 66, 309-320.
Kumar, D. (2021). Meteorological barriers to bike rental demands: A case of Washington D.C. using NCA approach. Case Studies on Transport Policy, 9(2), 830-841.
Li, S., Zhuang, C., Tan, Z., Gao, F., Lai, Z., & Wu, Z. (2021). Inferring the trip purposes and uncovering spatio-temporal activity patterns from dockless shared bike dataset in Shenzhen, China. Journal of Transport Geography, 91, 102974.
Lin, P. F., Weng, J. C., Liang, Q., Alivanistos, D., & Ma, S. Y. (2020). Impact of weather conditions and built environment on public bikesharing trips in Beijing. Networks & Spatial Economics, 20(1), 1-17.
Lund, H. (2006). Reasons for living in a transit-oriented development, and associated transit use. Journal of the American Planning Association, 72(3), 357-366.
Médard de Chardon, C., Caruso, G., & Thomas, I. (2017). Bicycle sharing system ‘success’ determinants. Transportation Research Part A: Policy and Practice, 100, 202-214.
Maas, S., Nikolaou, P., Attard, M., & Dimitriou, L. (2021). Heat, hills and the high season: A model-based comparative analysis of spatio-temporal factors affecting shared bicycle use in three Southern European islands. Sustainability, 13(6), 3274.
Mattson, J., & Godavarthy, R. (2017). Bike share in Fargo, North Dakota: Keys to success and factors affecting ridership. Sustainable Cities and Society, 34, 174-182.
Morton, C. (2020). The demand for cycle sharing: Examining the links between weather conditions, air quality levels, and cycling demand for regular and casual users. Journal of Transport Geography, 88, 102854.
Noland, R. B., Smart, M. J., & Guo, Z. (2016). Bikeshare trip generation in New York City. Transportation Research Part A: Policy and Practice, 94, 164-181.
Nosal, T., & Miranda-Moreno, L. F. (2014). The effect of weather on the use of North American bicycle facilities: A multi-city analysis using automatic counts. Transportation Research Part A: Policy and Practice, 66, 213-225.
Probst, P., Boulesteix, A. L., & Bischl, B. (2019). Tunability: Importance of hyperparameters of machine learning algorithms. Journal of Machine Learning Research, 20, 1934–1965.
Sathishkumar, V. E., & Cho, Y. (2020). A rule-based model for Seoul Bike sharing demand prediction using weather data. European Journal of Remote Sensing, 53, 166-183.
Sathishkumar, V. E., Park, J., & Cho, Y. (2020). Using data mining techniques for bike sharing demand prediction in metropolitan city. Computer Communications, 153, 353-366.
Scott, D. M., & Ciuro, C. (2019). What factors influence bike share ridership? An investigation of Hamilton, Ontario’s bike share hubs. Travel Behaviour and Society, 16, 50-58.
Spencer, P., Watts, R., Vivanco, L., & Flynn, B. (2013). The effect of environmental factors on bicycle commuters in Vermont: Influences of a northern climate. Journal of Transport Geography, 31, 11-17.
Torti, A., Pini, A., & Vantini, S. (2020). Modelling time‐varying mobility flows using function‐on‐function regression: Analysis of a bike sharing system in the city of Milan. Journal of the Royal Statistical Society: Series C (Applied Statistics), 70(1), 226-247.
Wang, Y., Zhan, Z., Mi, Y., Sobhani, A., & Zhou, H. (2022). Nonlinear effects of factors on dockless bike-sharing usage considering grid-based spatiotemporal heterogeneity. Transportation Research Part D: Transport and Environment, 104, 103194.
Wessel, J. (2020). Using weather forecasts to forecast whether bikes are used. Transportation Research Part a-Policy and Practice, 138, 537-559.
Wiechert, W. (2003). The role of modeling in computational science education. Future Generation Computer Systems, 19(8), 1363-1374.
Yang, Z., Hu, J., Shu, Y., Cheng, P., Chen, J., & Moscibroda, T. (2016). Mobility modeling and prediction in bike-sharing systems. Paper presented at the Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services, Singapore, Singapore.
Zhao, J., Wang, J., Xing, Z., Luan, X., & Jiang, Y. (2018). Weather and cycling: Mining big data to have an in-depth understanding of the association of weather variability with cycling on an off-road trail and an on-road bike lane. Transportation Research Part A: Policy and Practice, 111, 119-135.
Zhou, X., Wang, M., & Li, D. (2019). Bike-sharing or taxi? Modeling the choices of travel mode in Chicago using machine learning. Journal of Transport Geography, 79, 102479.