用于森林火灾动态预测的火场状态-燃料参数双估计方法研究

消防科学与技术 ›› 2026, Vol. 45 ›› Issue (5): 132-142.

用于森林火灾动态预测的火场状态-燃料参数双估计方法研究

罗肖龙², 王正¹, 吴昊², 纪杰¹, 丁龙¹

（1.中国科学技术大学火灾安全全国重点实验室，安徽合肥 230026； 2.中国科学技术大学先进技术研究院，安徽合肥 230031）

收稿日期:2025-02-16 修回日期:2025-05-02 出版日期:2026-05-15 发布日期:2026-05-15
作者简介:罗肖龙，中国科学技术大学先进技术研究院硕士研究生，主要从事森林火灾蔓延预测研究，安徽省合肥市望江西路5089号，230026。
基金资助:
国家重点研发计划项目（2023YFC3006900）

Research on the dual estimation method of fire state-fuel parameters for dynamic prediction of wildfires

Luo Xiaolong², Wang Zheng¹, Wu Hao², Ji Jie¹, Ding Long¹

(1. State Key Laboratory of Fire Science, University of Science and Technology of China, Hefei Anhui 230026, China;2. Institute of Advanced Technology, University of Science and Technology of China, Hefei Anhui 230031, China)

Received:2025-02-16 Revised:2025-05-02 Online:2026-05-15 Published:2026-05-15

摘要/Abstract

摘要： 由于林火蔓延预测模型的火线状态和输入参数不可避免地存在误差和不确定性，导致林火蔓延预测结果与实际蔓延结果之间通常会出现较大偏差。基于数据同化的卡尔曼滤波方法在降低模型状态误差方面具有动态估计的优势,本文结合集合转换卡尔曼滤波（Ensemble Transform Kalman Filter，ETKF）算法，提出了基于多层感知器（Multi-Layer Perceptron，MLP）神经网络的火线位置-燃料参数双估计方法。该方法利用连续两次观测到的火线位置数据，通过ETKF和MLP算法分别在不同预测周期和燃料调节因子分辨率下对火线位置状态和燃料参数进行估计，旨在降低模型状态和模型参数的不确定性。本文结合万平方米尺度的计划烧除试验和历史火灾案例，对双估计方法进行了验证。结果表明，双估计算法能够有效降低火线状态和模型参数误差，采用双估计方法预测的火线位置更接近实际观测的火线位置。预测周期对双估计方法降低火蔓延模型误差具有重要影响，预测周期越长，双估计方法相比单估计方法在火线位置预测精度上的提升越大。在历史火灾案例中，双估计算法的火线位置预测结果整体表现良好，验证了本文算法在实际场景下的预测性能。

关键词: 林火蔓延预测, 燃料调节因子, 参数估计, 集合转换卡尔曼滤波算法, FARSITE

Abstract: Since the fireline state and input parameters of wildfire spread prediction models inevitably contain errors and uncertainties, there are usually large deviations between wildfire spread predictions and actual spread results. The Kalman filter method based on data assimilation has the advantage of dynamic estimation in reducing model state errors. In this paper, we propose a dual estimation method for fireline position and fuel parameters based on Multi-Layer Perceptron (MLP) neural network, combined with the Ensemble Transform Kalman Filter (ETKF) algorithm. This method utilizes fireline position data from two consecutive observations and employs ETKF and MLP algorithms to estimate fireline position state and fuel parameters respectively under different prediction periods and fuel adjustment factor resolutions, aiming to reduce the uncertainties in both model state and model parameters. We validated the dual estimation method using a 10 000 m2 prescribed burning experiment and historical wildfire cases. The results demonstrate that the dual estimation algorithm can effectively reduce errors in both fireline state and model parameters, with the predicted fireline positions being to colser actual observations compared to single estimation methods. The prediction period significantly influences the performance of the dual estimation method in reducing fire spread model errors. The longer the prediction period, the greater the improvement in fireline position prediction accuracy compared to single estimation methods. In historical wildfire cases, the dual estimation algorithm shows good overall performance in fireline position prediction, validating the predictive capability of our algorithm in practical scenarios.

Key words: wildfire spread prediction, fuel adjustment factor, parameter estimation, ensemble transform Kalman filter algorithm, FARSITE

罗肖龙, 王正, 吴昊, 纪杰, 丁龙. 用于森林火灾动态预测的火场状态-燃料参数双估计方法研究[J]. 消防科学与技术, 2026, 45(5): 132-142.

Luo Xiaolong, Wang Zheng, Wu Hao, Ji Jie, Ding Long. Research on the dual estimation method of fire state-fuel parameters for dynamic prediction of wildfires[J]. Fire Science and Technology, 2026, 45(5): 132-142.