Mitigating class imbalance in forest fire prediction with GAN-Augmented data fusion

Based on the automatic machine learning framework, combined with the characteristics of forest fire meteorological data and the adaptive requirements of forest fire prediction, this paper optimizes the data preprocessing, parameter learning, loss function and other links of auto-sklearn, builds a forest fire risk prediction framework with regional adaptive characteristics. Based on the forest meteorological fire risk data, a forest fire risk prediction model with regional characteristics and self-learning characteristics is constructed to solve the problems of low compatibility of the existing machine learning methods with binary unbalanced forest fire data, improve the accuracy of forest fire prediction and provide decision-making basis for forestry risk management. The comparative analysis results show that the prediction accuracy of the improved framework in different test sets is improved by 13% on average. Compared with the existing machine learning model for forest fire prediction, the prediction accuracy of the framework proposed in this paper is comprehensively better than the existing methods in terms of real forest fire data.

Forest fires have major impact on ecosystems and greatly impact the amount of greenhouse gases and aerosols in the atmosphere. This paper presents an overview in the forest fire detection, emission estimation, and fire risk prediction in China using satellite imagery, climate data, and various simulation models over the past three decades. Since the 1980s, remotely-sensed data acquired by many satellites, such as NOAA/AVHRR, FY-series, MODIS, CBERS, and ENVISAT, have been widely utilized for detecting forest fire hot spots and burned areas in China. Some developed algorithms have been utilized for detecting the forest fire hot spots at a sub-pixel level. With respect to modeling the forest burning emission, a remote sensing data-driven Net Primary productivity (NPP) estimation model was developed for estimating forest biomass and fuel. In order to improve the forest fire risk modeling in China, real-time meteorological data, such as surface temperature, relative humidity, wind speed and direction, have been used as the model input for improving prediction of forest fire occurrence and its behavior. Shortwave infrared (SWIR) and near infrared (NIR) channels of satellite sensors have been employed for detecting live fuel moisture content (FMC), and the Normalized Difference Water Index (NDWI) was used for evaluating the forest vegetation condition and its moisture status.

Forest fires pose a potential threat to the ecological and environmental systems and natural resources, impacting human lives. However, automated surveillance system for early forest fire detection can mitigate such calamities and protect the environment. Therefore, we propose a UAV-based forest fire fighting system with integrated artificial intelligence (AI) capabilities for continuous forest surveillance and fire detection. The major contributions of the proposed research are fourfold. Firstly, we explain the detailed working mechanism along with the key steps involved in executing the UAV-based forest fire fighting system. Besides, a robust forest fire detection system requires precise and efficient classification of forest fire imagery against no-fire. Moreover, we have curated a novel dataset (DeepFire) containing diversified real-world forest imagery with and without fire to assist future research in this domain. The DeepFire dataset consists of 1900 colored images with 950 each for fire and no-fire classes. Next, we investigate the performance of various supervised machine learning classifiers for the binary classification problem of detecting forest fire. Furthermore, we propose a VGG19-based transfer learning solution to achieve improved prediction accuracy. We assess and compare the performance of several machine learning approaches such as k -nearest neighbors, random forest, naive Bayes, support vector machine, logistic regression, and the proposed approach for accurately identifying fire and no-fire images in the DeepFire dataset. The simulation results demonstrate the efficacy of the proposed approach in terms of accurate classification, where it achieves the mean accuracy of 95% with 95.7% precision and 94.2% recall.

The escalating issue of forest fires poses severe risks to ecosystems and human habitats, primarily due to the greenhouse effect and sudden climate changes. These fires, mostly occurring naturally, necessitate prompt detection and control. Addressing this, the authors introduce the Forest Fire Detection, Prediction, and Behaviour Analysis (FDPA) system, an innovative Internet of Things (IoT) solution. The FDPA system leverages a wireless sensor network to efficiently detect and analyse fire behaviour, providing real‐time data on fire spread, speed, and direction. Uniquely, it can anticipate natural fires hours before they occur by monitoring ecological parameters such as humidity, temperature, and using the Chandler Burning Index (CBI) for quantifying fire danger. Designed for the challenging forest environment, the FDPA system prioritises minimal power usage and simple components, crucial in areas with limited power resources. Its resilient design ensures the wireless sensor network and sensor nodes withstand harsh weather and fire conditions, maintaining functionality and reliability. Field tests of the FDPA system in various Jordanian forest locations, including Burgish–Ajloun, have demonstrated its effectiveness. The trials revealed the system's capability in early fire detection, low latency response, predicting fire behaviour, and determining fire spread direction. Continuous monitoring of the forest ecosystem and rapid detection allow authorities to act swiftly, preventing potential fires from escalating. Furthermore, the system tracks ecological changes within the forest, offering insights into imminent natural fires. This feature enables proactive measures to mitigate fire spread, safeguarding the environment and nearby communities. The strategic placement of sensor nodes and the use of durable yet straightforward components reduce the risk of system damage due to environmental extremities. Overall, the FDPA system emerges as a promising tool for forest fire management. Its ability to detect, predict, and analyse forest fires in real‐time positions it as a vital asset in minimising the detrimental impacts of forest fires on the environment and human settlements.

Forest fires are a major threat to ecosystems and human lives. Early detection of forest fires can greatly reduce their impact and detection is crucial in minimizing their damage. In recent years, the application of unmanned aerial vehicles (UAVs) with cameras with high resolution has become an effective tool for forest fire detection. However, manual detection and analysis of these images can be time-consuming and errorprone. In this study, we propose a forest fire detection method that uses Convolution Neural Networks (CNNs) to automatically analyze UAV imagery. The proposed method involves preprocessing the images to enhance the features of interest and then feeding them into the CNN for classification. We trained & tested our model using a dataset of UAV images and obtained a classification precision of 95%. The results indicate that our proposed method is effective in detecting forest fires using UAV imagery and can provide a fast and accurate means of early detection, which is critical in preventing the spread of wildfires. Forests are critical components of biosphere protection all around the planet. They provide significant contributions to the carbon cycle worldwide and support a diverse range of the animal and plant kingdoms. Fires in forests are among the most serious risks to living organisms in many parts of the world; they jeopardise the environment, including people, plants, and animals. Wildfires ravaged the regions of North Africa and the Mediterranean last year. Early detection of forest fires is critical for saving lives and property. The detection and prediction of forest fires are challenging undertakings given that wildfires begin tiny and are difficult to spo tin the distance. Fires can start small and spread swiftly to become enormous and dangerous. The combination of drones and high accuracy wildfire detection can be achieved by deep learning utilizing photos. UAVs can be used to help determine the fire’s location and the extent of its spread region, even though deep learning can be utilised to determine the fire’s qualities. This pairing is a critical building block for developing a system capable of more precise detection of wildfires. The recent published state-ofthe-art research publications on employing drones and deep learning to identify forest fires are examined in this paper.

Affected by global warming and increased extreme weather, Hunan Province saw a phased and concentrated outbreak of forest fires in 2022, causing significant damage and impact. Predicting the occurrence of forest fires can enhance the ability to make early predictions and strengthen early warning and responses. Currently, fire prevention and extinguishing in China’s forests and grasslands face severe challenges due to the overlapping of natural and social factors. Existing forest fire occurrence prediction models mostly take into account vegetation, topographic, meteorological and human activity factors; however, the occurrence of forest fires is closely related to the forest fuel moisture content. In this study, the traditional driving factors of forest fire such as satellite hotspots, vegetation, meteorology, topography and human activities from 2004 to 2021 were introduced along with forest fuel factors (vegetation canopy water content and evapotranspiration from the top of the vegetation canopy), and a database of factors for predicting forest fire occurrence was constructed. And a forest fire occurrence prediction model was built using machine learning methods such as the Random Forest model (RF), the Gradient Boosting Decision Tree model (GBDT) and the Adaptive Augmentation Model (AdaBoost). The accuracy of the models was verified using Area Under Curve (AUC) and four other metrics. The RF model with an AUC value of 0.981 was more accurate than all other models in predicting the probability of forest fire occurrence, followed by the GBDT (AUC = 0.978) and AdaBoost (AUC = 0.891) models. The RF model, which has the best accuracy, was selected to predict the monthly forest fire probability in Changsha in 2022 and combined with the Inverse Distance Weight Interpolation method to plot the monthly forest fire probability in Changsha. We found that the monthly spatial and temporal distribution of forest fire probability in Changsha varied significantly, with March, April, May, September, October, November and December being the months with higher forest fire probability. The highest probability of forest fires occurred in the central and northern regions. In this study, the core drivers affecting the occurrence of forest fires in Changsha City were found to be vegetation canopy evapotranspiration and vegetation canopy water content. The RF model was identified as a more suitable forest fire occurrence probability prediction model for Changsha City. Meanwhile, this study found that vegetation characteristics and combustible factors have more influence on forest fire occurrence in Changsha City than meteorological factors, and surface temperature has less influence on forest fire occurrence in Changsha City.

Planning the analyses of the spatial distribution and driving factors of forest fires and regionalizing fire risks is an important part of forest fire management. Based on the Landsat-8 active fire dataset of the Liangshan Yi Autonomous Prefecture from 2014 to 2021, this paper proposes an optimal parameter logistic regression (OPLR) model, conducts forest fire risk zoning research under the optimal spatial analysis scale and model parameters, and establishes a forest fire risk prediction model. The results showed that the spatial unit of the optimal spatial analysis scale in the study area was 5 km and that the prediction accuracy of the OPLR was about 81%. The climate was the main driving factor of forest fires, while temperature had the greatest influence on the probability of forest fires. According to the forest fire prediction model, mapping the fire risk zoning, in which the medium- and high-risk area was 6021.13 km2, accounted for 9.99% of the study area. The results contribute to a better understanding of forest fire management based on the local environmental characteristics of the Liangshan Yi Autonomous Prefecture and provide a reference for related forest fire prevention and control management.

Forest fires can destroy forest and inflict great damage to the ecosystem. Fortunately, forest fire detection with video has achieved remarkable results in enabling timely and accurate fire warnings. However, the traditional forest fire detection method relies heavily on artificially designed features; CNN-based methods require a large number of parameters. In addition, forest fire detection is easily disturbed by fog. To solve these issues, a lightweight YOLOX-L and defogging algorithm-based forest fire detection method, GXLD, is proposed. GXLD uses the dark channel prior to defog the image to obtain a fog-free image. After the lightweight improvement of YOLOX-L by GhostNet, depth separable convolution, and SENet, we obtain the YOLOX-L-Light and use it to detect the forest fire in the fog-free image. To evaluate the performance of YOLOX-L-Light and GXLD, mean average precision (mAP) was used to evaluate the detection accuracy, and network parameters were used to evaluate the lightweight effect. Experiments on our forest fire dataset show that the number of the parameters of YOLOX-L-Light decreased by 92.6%, and the mAP increased by 1.96%. The mAP of GXLD is 87.47%, which is 2.46% higher than that of YOLOX-L; and the average fps of GXLD is 26.33 when the input image size is 1280 × 720. Even in a foggy environment, the GXLD can detect a forest fire in real time with a high accuracy, target confidence, and target integrity. This research proposes a lightweight forest fire detection method (GXLD) with fog removal. Therefore, GXLD can detect a forest fire with a high accuracy in real time. The proposed GXLD has the advantages of defogging, a high target confidence, and a high target integrity, which makes it more suitable for the development of a modern forest fire video detection system.

Forest fires have frequently occurred and caused great harm to people’s lives. Many researchers use machine learning techniques to predict forest fires by considering spatio-temporal data features. However, it is difficult to efficiently obtain the features from large-scale, multi-source, heterogeneous data. There is a lack of a method that can effectively extract features required by machine learning-based forest fire predictions from multi-source spatio-temporal data. This paper proposes a forest fire prediction method that integrates spatio-temporal knowledge graphs and machine learning models. This method can fuse multi-source heterogeneous spatio-temporal forest fire data by constructing a forest fire semantic ontology and a knowledge graph-based spatio-temporal framework. This paper defines the domain expertise of forest fire analysis as the semantic rules of the knowledge graph. This paper proposes a rule-based reasoning method to obtain the corresponding data for the specific machine learning-based forest fire prediction methods, which are dedicated to tackling the problem with real-time prediction scenarios. This paper performs experiments regarding forest fire predictions based on real-world data in the experimental areas Xichang and Yanyuan in Sichuan province. The results show that the proposed method is beneficial for the fusion of multi-source spatio-temporal data and highly improves the prediction performance in real forest fire prediction scenarios.

The study of forest fire prediction is of great environmental and scientific significance. China’s Guangxi Autonomous Region has a high incidence rate of forest fires. At present, there is little research on forest fires in this area. The application of the artificial neural network and support vector machines (SVM) in forest fire prediction in this area can provide data for forest fire prevention and control in Guangxi. In this paper, based on Guangxi’s 2010–2018 satellite monitoring hotspot data, meteorology, terrain, vegetation, infrastructure, and socioeconomic data, the researchers determined the main forest fire driving factors in Guangxi. They used feature selection and backpropagation neural networks and radial basis SVM to build forest fire prediction models. Finally, the researchers use the accuracy, precision, and area under the characteristic curve (ROC-AUC) and other indicators to evaluate the predictive performance of the two models. The results showed that the prediction accuracy of the BP neural network and SVM is 92.16% and 89.89%, respectively. As both results are over 85%, the requirements of prediction accuracy is met. These results can be used for forest fire prediction in the Guangxi Autonomous Region. Specifically, the accuracy of the BP neural network was 0.93, which was higher than that of the SVM model (0.89); the recall of the SVM model was 0.84, which was lower than the BANN model (0.92), and the AUC value of the SVM model was 0.95, which was lower than the BP neural network model. The obtained results confirm that the BP neural network model can provide more prediction accuracy than support vector machines and is therefore more suitable for forest fire prediction in Guangxi, China. This research provides the necessary theoretical basis and data support for application in the field of forestry of the Guangxi Autonomous Region, China.

IntroductionForest fires seriously threaten the safety of forest resources and human beings. Establishing an accurate forest fire forecasting model is crucial for forest fire management.MethodsWe used different meteorological and vegetation factors as predictors to construct forest fire prediction models for different fire prevention periods in Heilongjiang Province in northeast China. The logistic regression (LR) model, mixed-effect logistic (mixed LR) model, and geographically weighted logistic regression (GWLR) model were developed and evaluated respectively.ResultsThe results showed that (1) the validation accuracies of the LR model were 77.25 and 81.76% in spring and autumn fire prevention periods, respectively. Compared with the LR model, both the mixed LR and GWLR models had significantly improved the fit and validated results, and the GWLR model performed best with an increase of 6.27 and 10.98%, respectively. (2) The three models were ranked as LR model < mixed LR model < GWLR model in predicting forest fire occurrence of Heilongjiang Province. The medium-and high-risk areas of forest fire predicted by the GWLR model were distributed in western and eastern parts of Heilongjiang Province in spring, and western part in autumn, which was consistent with the observed data. (3) Driving factors had strong temporal and spatial heterogeneities; different factors had different effects on forest fire occurrence in different time periods. The relationship between driving factors and forest fire occurrence varied from positive to negative correlations, whether it’s spring or autumn fire prevention period.DiscussionThe GWLR model has advantages in explaining the spatial variation of different factors and can provide more reliable forest fire predictions.

The frequent occurrence of forest fires causes irreparable damage to the environment and the economy. Therefore, the accurate detection of forest fires is particularly important. Due to the various shapes and textures of flames and the large variation in the target scales, traditional forest fire detection methods have high false alarm rates and poor adaptability, which results in severe limitations. To address the problem of the low detection accuracy caused by the multi-scale characteristics and changeable morphology of forest fires, this paper proposes YOLOv5s-CCAB, an improved multi-scale forest fire detection model based on YOLOv5s. Firstly, coordinate attention (CA) was added to YOLOv5s in order to adjust the network to focus more on the forest fire features. Secondly, Contextual Transformer (CoT) was introduced into the backbone network, and a CoT3 module was built to reduce the number of parameters while improving the detection of forest fires and the ability to capture global dependencies in forest fire images. Then, changes were made to Complete-Intersection-Over-Union (CIoU) Loss function to improve the network’s detection accuracy for forest fire targets. Finally, the Bi-directional Feature Pyramid Network (BiFPN) was constructed at the neck to provide the model with a more effective fusion capability for the extracted forest fire features. The experimental results based on the constructed multi-scale forest fire dataset show that YOLOv5s-CCAB increases AP@0.5 by 6.2% to 87.7%, and the FPS reaches 36.6. This indicates that YOLOv5s-CCAB has a high detection accuracy and speed. The method can provide a reference for the real-time, accurate detection of multi-scale forest fires.

Forest fires, severe natural disasters causing substantial damage, necessitate accurate predictive modeling to guide preventative measures effectively. This study introduces an enhanced window-based Transformer time series forecasting model aimed at improving the precision of forest fire predictions. Leveraging time series data from 2020 to 2021 in Chongli, a myriad of forest fire influencing factors were ascertained using remote sensing satellite and GIS technologies, with their interrelationships estimated through a multicollinearity test. Given the intricate nature of real-world forest fire prediction tasks, we propose a novel window-based Transformer architecture complemented by a dual time series input strategy premised on 13 influential factors. Subsequently, time series data were incorporated into the model to generate a forest fire risk prediction map in Chongli District. The model’s effectiveness was then evaluated using various metrics, including accuracy (ACC), root mean square error (RMSE), and mean absolute error (MAE), and compared with traditional deep learning methods. Our model demonstrated superior predictive performance (ACC = 91.56%, RMSE = 0.37, MAE = 0.05), harnessing spatial background information efficiently and effectively utilizing the periodicity of forest fire factors. Consequently, the study proves this method to be a novel and potent approach for time series fire prediction.

Abstract: Forest fires or wildfires are major catastrophes that occur in forests, grasslands, or prairies (Grassland areas). Wildfires mostly occur either due to natural factors or human activities such as smoking cigarettes, campfires, or arson, etc. Forest fire has become one of the most drastic problems that cause damage to several forests around the globe. To prevent forest fires, analysis, and predictions should be made on land that is affected by forest fires based on temperature, wind, humidity, etc. Depending upon the above factors, analysis, and prediction are done, which region has a high possibility of wildfires’ dangerous effects. Fire detection will help in finding and controlling an extreme problem in forests, this will help in reducing the forest fire in the future. Many Algorithms are available for the detection of the fire, Based on the use of Algorithms analysis and prediction of the forest fires are made.

Monitoring and early warning technology for forest fires is crucial. An early warning/monitoring system for forest fires was constructed based on deep learning and the internet of things. Forest fire recognition was improved by combining the size, color, and shape characteristics of the flame, smoke, and area. Complex upper-layer fire-image features were extracted, improving the input conversion by building a forest fire risk prediction model based on an improved dynamic convolutional neural network. The proposed back propagation neural network fire (BPNNFire) algorithm calculated the image processing speed and delay rate, and data were preprocessed to remove noise. The model recognized forest fire images, and the classifier classified them to distinguish images with and without fire. Fire images were classified locally for feature extraction. Forest fire images were stored on a remote server. Existing algorithms were compared, and BPNNFire provided real-time accurate forest fire recognition at a low frame rate with 84.37% accuracy, indicating superior recognition. The maximum relative error between the measured and actual values for real-time online monitoring of forest environment indicators, such as air temperature and humidity, was 5.75%. The packet loss rate of the forest fire monitoring network was 5.99% at Longshan Forest Farm and 2.22% at Longyandong Forest Farm.