Applicability analysis of flame height estimation based on Byram's fireline intensity model under flat and windless conditions

Forest fire have a serious impact on forest ecosystems, the safety of people's lives and property, and social stability. The height of surface flames, as the main indicator of forest fire behavior, which is an important parameter for forest fire management. The relationship between fireline intensity and flame height proposed by Byram has been widely used in estimating flame height; however, its applicability to the surface fuel of typical forest stands in the Yunnan-Guizhou Plateau of China has not yet been analyzed. In this study, the surface fuel in the area was taken as the research object, and the flame height of different fuel bed characteristics was measured through an indoor burning experiment. The applicability of three methods-the directly used Byram's model, corrected model, and re-established prediction model-was analyzed to estimate the flame height in the Yunnan-Guizhou Plateau. We found that the flame height of the typical forest stands in the Yunnan-Guizhou Plateau ranged from 0.05 to 1.2 m and was significantly affected by the moisture content, load, and height of the fuel bed. Although the fireline intensity exhibited a significant linear relationship with the flame height, directly using Byram's method to predict the flame height of surface fires was impractical, as its mean prediction error exceeded 150%. The mean relative errors of the prediction model obtained by modifying Byram's method and that based on the characteristics of the fuel bed were both within 15%, which is significantly lower than that of the original Byram's method. Based on the results of this study, we propose two methods that are suitable for predicting the flame height of surface fires in the typical forests of the Yunnan-Guizhou Plateau in China, which is of great significance for further understanding the relationship between flame height, fireline intensity, and scientific forest fire management.