The simulation of forest fire spread is a key problem for the management of fire, and Cellular Automata (CA) has been used to simulate the complex mechanism of the fire spread for a long time. The simulation of CA is driven by the rate of fire spread (ROS), which is hard to estimate, because some input parameters of the current ROS model cannot be provided with a high precision, so the CA approach has not been well applied yet in the forest fire management system to date. The forest fire spread simulation model LSTM-CA using CA with LSTM is proposed in this paper. Based on the interaction between wind and fire, S-LSTM is proposed, which takes full advantage of the time dependency of the ROS. The ROS estimated by the S-LSTM is satisfactory, even though the input parameters are not perfect. Fifteen kinds of ROS models with the same structure are trained for different cases of slope direction and wind direction, and the model with the closest case is selected to drive the transmission between the adjacent cells. In order to simulate the actual spread of forest fire, the LSTM-based models are trained based on the data captured, and three correction rules are added to the CA model. Finally, the prediction accuracy of forest fire spread is verified though the KAPPA coefficient, Hausdorff distance, and horizontal comparison experiments based on remote sensing images of wildfires. The LSTM-CA model has good practicality in simulating the spread of forest fires.

Modeling forest fire spread is a very complex problem, and the existing models usually need some input parameters which are hard to get. How to predict the time series of forest fire spread rate based on passed series may be a key problem to break through the current technical bottleneck. In the process of forest fire spreading, spread rate and wind speed would affect each other. In this paper, three kinds of network models based on Long Short-Term Memory (LSTM) are designed to predict fire spread rate, exploring the interaction between fire and wind. In order to train these LSTM-based models and validate their effectiveness of prediction, several outdoor combustion experiments are designed and carried out. Process data sets of forest fire spreading are collected with an infrared camera mounted on a UAV, and wind data sets are recorded using a anemometer simultaneously. According to the close relationship between wind and fire, three progressive LSTM based models are constructed, which are called CSG-LSTM, MDG-LSTM and FNU-LSTM, respectively. A Cross-Entropy Loss equation is employed to measure the model training quality, and then prediction accuracy is computed and analyzed by comparing with the true fire spread rate and wind speed. According to the performance of training and prediction stage, FNU-LSTM is determined as the best model for the general case. The advantage of FNU-LSTM is further demonstrated by doing comparison experiments with the normal LSTM and other LSTM based models which predict both fire spread rate and wind speed separately. The experiment has also demonstrated the ability of the model to the real fire prediction on the basis of two historical wildland fires.

Fuel moisture content is one of the important factors that determine ignition probability and fire behaviour in forest ecosystems. In this study, ignition and fire spread moisture content thresholds of 40 dead fuel were performed in laboratory experiments, with a focus on the source of ignition and wind speed. Variability in fuel moisture content at time of ignition and during fire spread was observed for different fuels. Matches were more efficient to result in ignition and spread fire with high values of fuel moisture content compared to the use of cigarette butts. Some fuels did not ignite at 15% moisture content, whereas others ignited at 40% moisture content and fire spread at 38% moisture content in the case of matches, or ignited at 27% moisture content and spread fire at 25% moisture content using cigarette butts. A two-way ANOVA showed that both the source of ignition and the wind speed affected ignition and fire spread threshold significantly, but there was no interaction between these factors. The relationship between ignition and fire spread was strong, with R² = 98% for cigarette butts, and 92% for matches. Further information is needed, especially on the density of fuels, fuel proportion (case of mixed fuels), fuel age, and fuel combustibility.

Preventing and suppressing forest fires is one of the main tasks of forestry agencies to reduce resource loss and requires a thorough understanding of the importance of factors affecting their occurrence. This study was carried out in forest plantations on Maoer Mountain in order to develop models for predicting the moisture content of dead fine fuel using meteorological and soil variables. Models by Nelson (Can J For Res 14:597–600, 1984) and Van Wagner and Pickett (Can For Service 33, 1985) describing the equilibrium moisture content as a function of relative humidity and temperature were evaluated. A random forest and generalized additive models were built to select the most important meteorological variables affecting fuel moisture content. Nelson's (Can J For Res 14:597–600, 1984) model was accurate for Pinus koraiensis, Pinus sylvestris, Larix gmelinii and mixed Larix gmelinii—Ulmus propinqua fuels. The random forest model showed that temperature and relative humidity were the most important factors affecting fuel moisture content. The generalized additive regression model showed that temperature, relative humidity and rain were the main drivers affecting fuel moisture content. In addition to the combined effects of temperature, rainfall and relative humidity, solar radiation or wind speed were also significant on some sites. In P. koraiensis and P. sylvestris plantations, where soil parameters were measured, rain, soil moisture and temperature were the main factors of fuel moisture content. The accuracies of the random forest model and generalized additive model were similar, however, the random forest model was more accurate but underestimated the effect of rain on fuel moisture.

Massive wildfires have become more frequent, seriously threatening the Earth’s ecosystems and human societies. Recognizing smoke from forest fires is critical to extinguishing them at an early stage. However, edge devices have low computational accuracy and suboptimal real-time performance. This limits model inference and deployment. In this paper, we establish a forest smoke database and propose a model for efficient and lightweight forest smoke detection based on YOLOv8. Firstly, to improve the feature fusion capability in forest smoke detection, we fuse a simple yet efficient weighted feature fusion network into the neck of YOLOv8. This also greatly optimizes the number of parameters and computational load of the model. Then, the simple and parametric-free attention mechanism (SimAM) is introduced to address the problem of forest smoke dataset images that may contain complex background and environmental disturbances. The detection accuracy of the model is improved, and no additional parameters are introduced. Finally, we introduce focal modulation to increase the attention to the hard-to-detect smoke and improve the running speed of the model. The experimental results show that the mean average precision of the improved model is 90.1%, which is 3% higher than the original model. The number of parameters and the computational complexity of the model are 7.79 MB and 25.6 GFLOPs (giga floating-point operations per second), respectively, which are 30.07% and 10.49% less than those of the unimproved YOLOv8s. This model is significantly better than other mainstream models in the self-built forest smoke detection dataset, and it also has great potential in practical application scenarios.