基于IWOA-BP的红松人工林枯落针叶层火蔓延速率预测模型

打开文本图片集

中图分类号：S762 文献标志码：A 文章编号：1000-2006（2026）02-0029-08

Abstract：【Objective】Pinus horaiensis needes exhibitasignificant forestfireriskdue totheir highoil content，and surfacefire spread is the main fire spread mode.Developing a predictive modelfor surface fire spread rates can provide scientificbasisandvaluable insights for firepreventionandcontrol inPinus horaiensis plantations.【Method】The dead coniferous layerof Pinus koraiensis plantation inLiangshuiareaof Heilongjiang provincewasusedasthe material，360 sets of indoor point burning tests were conducted with water content of 0 ， 5% ， 10% ， 15% ， 20% ，slope of 0∘ ， 5∘ ， 10∘ ， （204 15∘ and wind speed of 0 ，1， 2 ，3，4 and 5m/s . Based on the fire spread rate measured by thermocouple method，an improved WOA（IWOA）-BP neural network model was constructed to predict the firespread rate，and the prediction results were compared with those of three models （WOA-BP neural network，GA-BP neural network and PSO-BP neural network）.【Result】Slope，wind speed and fire spread rate were significantly positively correlated（ P<0.01 ），while water content exhibited a negative correlation with fire spread rate （ P<0.05 ）.The fire spreadrate decreased with an increasein fuel water content，and increasedwith theincreaseof wind speedand slope.When the windspeed was 4m/s ，the fire spread growth rate reached the maximum.The improved whale optimization algorithm （IWOA） included Tent chaotic mapping，improved nonlinear convergence factor，adaptive weighting and Levy flight motion.These enhancements increased the algorithm'srandomnessand diversity，therebyimproving itsconvergencespeedandreducing thelikelihoodof becoming trapped in localoptima，with high predictionaccuracyandrobustness.Theaccuracyand stabilityofthe BPneural network model optimized bythe IWOAdemonstrated significantimprovementscompared to three other models，exhibiting thehighestmodelfitness to the measured data.【Conclusion】The IWOA-BP neural networkmodelcanefectivelypredictthefirespreadrateof thedeadconiferouslayerof the Pinus horaiensis plantation， andproviding scientific gudance for forest fire preventionandcontroland forest liter firespreadrate predictionmodel. Keywords：Pinuskoraiensisplantation；firespreadrate；point firetest；improvedwhaleoptimizationalgorithm （IWOA）；BP neural network

森林火灾具备传播速度快和破坏力大的特点[1-2]，对森林资源、地球生态和经济产生严重的影响[3-6]。（剩余14332字）