Predictive Modeling of Forest Fires in Yunnan Province: An Integration of ARIMA and Stepwise Regression Analysis

Abstract

As global warming progresses, forest fires have become more frequent, leading to the destruction of forest biodiversity and consequently affecting Earth’s ecosystems and human living conditions. The ability to predict the long-term trend of forest fires holds significant value for fire prevention and management. In Yunnan Province, China, a region rich in forest resources, this study utilized temperature, average annual rainfall, relative humidity, and wind speed data from 1991 to 2021. We forecasted forest fires using the stepwise regression and autoregressive integrated moving average (ARIMA) model, incorporating the collected forest fire data. The findings reveal a negative correlation between rainfall and forest fire incidence, whereas wind speed exhibited a positive correlation. The ARIMA model forecasts a cyclical trend in fires from 2022 to 2033, with considerable fluctuations in the number of fires, notably in 2027 and 2033. The projected affected area is anticipated to show a marked increase from 2028 onwards. This research not only provides a novel methodology for forecasting forest fires but also lays a scientific foundation for the development of future fire prevention and mitigation strategies.

Keywords

• ARIMA model
• fire prediction
• stepwise regression model
• time series analysis