Search

Forest fires present significant threats to both natural ecosystems and human communities, highlighting the need for advanced detection systems for early intervention and mitigation. This paper aims to develop a novel forest fire detection system by integrating Internet of Things technology, machine learning algorithms, and real-time data from weather APIs. The proposed system utilizes IoT sensors to gather environmental parameters and weather conditions, enhancing the accuracy of fire detection. A machine learning model trained on this data distinguishes between normal environmental fluctuations and signs of fire. Additionally, an image processing algorithm is employed to analyze images for the presence of smoke or flames. Integration and testing of the system demonstrate its promising results in terms of accuracy and efficiency compared to traditional methods. This paper contributes to technology-driven solutions for forest fire management, with significant implications for environmental conservation and public safety. [ABSTRACT FROM AUTHOR]

The 9th International Conference on Forest Fire Research, organised by the Forest Fire Research Center of the Association for Developmental of Industrial Aerodynamics every 4 years since 1990, was held in November 2022 in Coimbra, Portugal. The conference was held in conjunction with the 17th International Wildland Fire Safety Summit, sponsored by the International Association of Wildland Fire. The number and quality of the submissions for this joint event was very high, and the authors were encouraged to submit a full paper to a special issue of the International Journal of Wildland Fire (IJWF). Given the large number of submissions, the Journal decided to publish the special issue in four parts. Part 1 was published in January 2023, with eight papers, Part 2 in March 2023, with 10 papers and Part 3 in June 2023 with 15 papers. This fourth part presents 10 original papers, in three areas: Decision Support Systems and Tools (3), Risk Assessment & Reduction (3) and the Wildland Urban Interface (4). All the papers in this special issue are published Open Access. Part 4 of the special issue that resulted from the 9th International Conference on Forest Fire Research includes 10 papers on various aspects of wildland fire research. Parts 1, 2 and 3 were published in January, March and June 2023 respectively. All papers in the special issue are published Open Access. [ABSTRACT FROM AUTHOR]

The Special Issue "Impact of climate warming and disturbances on forest ecosystems" underscores the critical importance of understanding how forests respond to these environmental challenges and the legacy of past management practices. Forest ecosystems are facing significant challenges due to ongoing climate change, characterized by rising temperatures and increased frequency of extreme events. The rapid pace of climate change is altering disturbance patterns and the adaptability of forests, which have a direct impact on ecosystem services that contribute to human well-being. This Special Issue features 11 research papers from nine countries. Some key outputs from these research papers include evidence on how climate change is already impacting forest ecosystems. For instance, the climatic envelope of many forest species has shifted due to global warming, making species more vulnerable, especially in lower elevations and at the edges of their distribution. Urgent adaptive measures in forest management are necessary to address this challenge. Climate change also affects vegetation phenology, tree growth, stand productivity, reproduction rates, and stand regeneration. Remote sensing data and ecological modeling techniques play a crucial role in monitoring and understanding these changes, especially in remote regions where field measurements are limited. The rising frequency and intensity of extreme events like droughts, windstorms, and forest fires require enhanced prediction and automatic monitoring. Leveraging machine learning tools and remote sensing data is imperative. This Special Issue provides insights into the intricate relationships among forests, climate change, and human interventions. We provide further research recommendations for the quantification and automated monitoring of forest fires and the management of forests to better withstand storms and increase their resilience to climate change. [ABSTRACT FROM AUTHOR]

Forest fires present a substantial environmental challenge, constituting a dual menace to human life and ecological well-being. The imperative for forest fire prevention and management underscores the indispensability of robust detection, prediction, and behavior analysis systems. This scholarly paper offers a thorough exploration of diverse methodologies and techniques employed in the realms of forest fire detection, prediction, and behavior analysis. Encompassing both ground-based and aerial surveillance systems, as well as remote sensing technologies, machine learning-based approaches, and social media-driven systems, the survey provides a comprehensive overview of the multifaceted landscape of forest fire monitoring. In addition to delineating the current state of the art, the paper critically examines the challenges and limitations inherent in existing systems. Furthermore, it imparts valuable insights into prospective avenues for research and development within this domain. In essence, this paper underscores the significance of amalgamating data from various sources and employing diverse analytical methods to enhance our comprehension of forest fire behavior. The overarching goal is to foster the formulation of efficacious strategies for mitigating the impact of this environmental menace. [ABSTRACT FROM AUTHOR]

Forest fire is a major disturbance in mountainous ecosystems across the world. It impacts the composition, functioning, and structure of the forest ecosystem. Demographic pressure and the related climatic factors are thought to exacerbate the danger of forest fires, although there is a lack of statistical data to support this, particularly in South Asian countries with limited historical records. The study looks at how forest fires interact with their causative variables, such as population, topography, vegetation, and climate regimes, in the forests of Northern India. In order to do so, the paper presents a 15-year trend analysis of forest burn scars. This investigation confirmed the utility of principal component analysis using multisource spatial data and correlation matrices. The findings reveal that the occurrence and intensity of forest fires in mountainous locations are influenced by anthropogenic activities, forests near roads and settlements are extremely vulnerable. Based on the analysis, we emphasize the need for restructuring the existing policies like National Action Plan for forest fires and forest fire prevention and management scheme into more practical science-based policies. These findings may be utilized in planning effective fire control processes in time, and the technique provided in this study may be used to discover potential fire-risk zones in other areas. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs) and quadrotors are being used in an increasing number of applications. The detection and management of forest fires is continually improved by the incorporation of new economical technologies in order to prevent ecological degradation and disasters. Using an inner-outer loop design, this paper discusses an attitude and altitude controller for a quadrotor. As a highly nonlinear system, quadrotor dynamics can be simplified by assuming several assumptions. Quadrotor autopilot is developed using nonlinear feedback linearization technique, LQR, SMC, PD, and PID controllers. Often, these approaches are used to improve control and to reject disturbances. PDPID controllers are also deployed in the tracking and surveillance of smoke or fire by intelligent algorithms. In this paper, the efficiency using a combined PDPID controllers with adjustable parameters have been studied. The performance was assessed by simulation using matlab Simulink. The computational study conducted to assess the proposed approach showed that the PD-PID combination presented in this paper yields promising outcomes. [ABSTRACT FROM AUTHOR]

Forest fires are one of the world's deadliest natural disasters. Early detection of forest fires can help minimize the damage to ecosystems and forest life. In this paper, we propose an improved fire detection method YOLOv5-IFFDM for YOLOv5. Firstly, the fire and smoke detection accuracy and the network perception accuracy of small targets are improved by adding an attention mechanism to the backbone network. Secondly, the loss function is improved and the SoftPool pyramid pooling structure is used to improve the regression accuracy and detection performance of the model and the robustness of the model. In addition, a random mosaic augmentation technique is used to enhance the data to increase the generalization ability of the model, and re-clustering of flame and smoke detection a priori frames are used to improve the accuracy and speed. Finally, the parameters of the convolutional and normalization layers of the trained model are homogeneously merged to further reduce the model processing load and to improve the detection speed. Experimental results on self-built forest-fire and smoke datasets show that this algorithm has high detection accuracy and fast detection speed, with average accuracy of fire up to 90.5% and smoke up to 84.3%, and detection speed up to 75 FPS (frames per second transmission), which can meet the requirements of real-time and efficient fire detection. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Wildland Fire Science is the property of Journal of Wildland Fire Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Canopy fuels determine the characteristics of the entire complex of forest fuels due to their constant changes triggered by the environment; therefore, the development of appropriate strategies for fire management and fire risk reduction requires an accurate description of canopy forest fuels. This paper presents a method for mapping the spatial distribution of canopy fuel loads (CFLs) in alignment with their natural variability and three-dimensional spatial distribution. The approach leverages an object-based machine learning framework with UAV multispectral data and photogrammetric point clouds. The proposed method was developed in the mixed forest of the natural protected area of "Sierra de Quila", Jalisco, Mexico. Structural variables derived from photogrammetric point clouds, along with spectral information, were used in an object-based Random Forest model to accurately estimate CFLs, yielding R2 = 0.75, RMSE = 1.78 Mg, and an average B i a s r e l = 18.62%. Canopy volume was the most significant explanatory variable, achieving a mean decrease in impurity values greater than 80%, while the combination of texture and vegetation indices presented importance values close to 20%. Our modelling approach enables the accurate estimation of CFLs, accounting for the ecological context that governs their dynamics and spatial variability. The high precision achieved, at a relatively low cost, encourages constant updating of forest fuels maps to enable researchers and forest managers to streamline decision making on fuel and forest fire management. [ABSTRACT FROM AUTHOR]

Forest fires will do great harm to the ecological environment. At present, the most important research field is the study of the causes of forest fires, and the failure to determine the causes will greatly hinder the prevention, control and safety management of forest fires. In order to solve this problem, this paper constructs a Bayesian network to calculate the state probability and sensitivity after determining the factors related to forest fire. Secondly, on the basis of constructing Bayesian network, the Bow-tie model is constructed according to the consequences of forest fire. The constructed Bow-tie model contains 7 influencing factors and 5 consequences, and 26 corresponding control measures. Finally, through the analysis of Bayesian network and bow tie model, the forest fire prevention system is constructed. According to the calculation results of the Bayesian network, the probability of forest fires being at high risk of occurrence is higher for three factors: agriculture, forestry and water expenditure, rural population density and precipitation. Changes in rural population density and humidity have the greatest impact on the occurrence of forest fires. In combination with the Bow-tie model, human factors are the most important factors leading to the occurrence of forest fires, and the material, environmental, and management factors are the secondary factors. Based on the forest control system, the prevention and management measures are put forward. This research can provide reference for the control of forest fire and reduce the occurrence of similar forest fires. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to highlight the interest of focusing public policies for wildfire management on behavioral changes supported by sustainable development projects dedicated to the Algerian forest heritage. Thus, the Aurès region in the eastern part of Algeria will be used as an example to illustrate the proposed new strategy. Design/methodology/approach: The proposed method, guided by projects' management in sustainable development, consists of developing a responsible citizenship strategy focused on behavioral changes of citizens. Therefore, the title of the proposed method: The Construct of Responsible Citizenship. Findings: In order to cope with forest fires, the proposed approach highlights the interest of promoting responsible citizenship. Likewise, it outlines a tool for sustaining behavioral changes based on the principle of continuous improvement and field follow-up using a multicriteria approach known as "goal programming." Practical implications: The proposed new forest fire protection plan addresses the shortcomings in Algeria's current forest fire management policy, which appears unable to deal with the increasing severity of forests' fire risk that the country has been experiencing in recent decades. Originality/value: The aim is to highlight the interest of investment in forest fires prevention within the framework of the sustainable development of Algerian forest heritage, specifically, to work toward citizen subcontracting of the Algerian forest heritage. [ABSTRACT FROM AUTHOR]

Earth resource and environmental monitoring are essential areas that can be used to investigate the environmental conditions and natural resources supporting sustainable policy development, regulatory measures, and their implementation elevating the environment. Large-scale forest fire is considered a major harmful hazard that affects climate change and life over the globe. Therefore, the early identification of forest fires using automated tools is essential to avoid the spread of fire to a large extent. Therefore, this paper focuses on the design of automated forest fire detection using a fusion-based deep learning (AFFD-FDL) model for environmental monitoring. The AFFDFDL technique involves the design of an entropy-based fusion model for feature extraction. The combination of the handcrafted features using histogram of gradients (HOG) with deep features using SqueezeNet and Inception v3 models. Besides, an optimal extreme learning machine (ELM) based classifier is used to identify the existence of fire or not. In order to properly tune the parameters of the ELM model, the oppositional glowworm swarm optimization (OGSO) algorithm is employed and thereby improves the forest fire detection performance. A wide range of simulation analyses takes place on a benchmark dataset and the results are inspected under several aspects. The experimental results highlighted the betterment of the AFFD-FDL technique over the recent state of art techniques. [ABSTRACT FROM AUTHOR]

The surface fine dead fuel moisture content (FFMC) is an important factor in predicting forest fire risk and is influenced by various meteorological factors. Many prediction methods rely on temperature and humidity as factors, resulting in poor model prediction accuracy under rainfall conditions. At the same time, there is an increasing number of methods based on machine learning, but there is still a lack of comparison with traditional models. Therefore, this paper selected the broad-leaved forest tree species Quercus mongolica and the coniferous forest species Pinus sylvestris var. mongolica in Northeast China. Taking surface dead fine fuel as the research object, we used indoor simulated rainfall experiments to explore the impact of rainfall on the surface dead fuel moisture content. The prediction model for surface dead fuel moisture content was modified by the direct estimation method. Finally, using field data, the direct estimation method and convolution neural network (CNN) model were used in the comparison. The rainfall simulation results showed that the indoor fuel moisture content had a logarithmic increasing trend. Rainfall and previous fuel moisture content had a significant impact on the fuel moisture content prediction model, and both the relational model and nonlinear model performed well in predicting fuel moisture content under indoor rainfall conditions. Under field conditions, humidity, temperature and rainfall played a significant role in fuel moisture content. Compared with the unmodified direct estimation method, the modified direct estimation method significantly improved the prediction accuracy and the goodness of fit (R2) increased from 0.85–0.94 to 0.94–0.96. Mean absolute error (MAE) decreased from 9.18–18.33% to 6.86–10.74%, and mean relative error (MRE) decreased from 3.97–17.18% to 3.53–14.48%. The modified direct estimation method has higher prediction accuracy compared with the convolutional neural network model; the R2 value was above 0.90, MAE was below 8.11%, and MRE was below 8.87%. The modified direct estimation method had the best prediction effect among them. This study has a certain reference value for the prediction model of surface fuel moisture content in post-rainfall fire risk assessment and is also of great significance for forest fire management in Northeast China. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

The fire season of 2023 was record-breaking in Canada given the number, severity, and intensity of wildfires. Factors contributing to the number of fires are likely to get worse in the future because of the interaction and complexity of many factors such as climate change and the legacy of decades of successful wildfire suppression. Further complicating wildfire management is the ever-continuing expansion of the wildland-urban interface and subsequent increases in values at risk. Fire management solutions including prevention and suppression will require novel approaches given rising costs and logistical complications. This paper examines the payment concept for ecosystem services whereby ranchers are paid to graze cattle in targeted high-priority areas in the wildland urban interface. Grazing can be ecologically appropriate and has long been used in fire-prone ecosystems in Europe. With some key considerations, implementing PES (Payments for Ecosystem Services) could reduce fire risk, support agricultural producers, and enhance societal protection. [ABSTRACT FROM AUTHOR]

With the development of the Internet of Things (IoT), the amount of data is growing and becoming more diverse. There are several problems when transferring data to the cloud, such as limitations on network bandwidth and latency. That has generated considerable interest in the study of edge computing, which processes and analyzes data near the network terminals where data is causing. The edge computing can extract insight data from a large number of data and provide fast essential services through simple analysis. The edge computing has a real-time advantage, but also has disadvantages, such as limited edge node capacity. The edge node for edge computing causes overload and delays in completing the task. In this paper, we proposes an efficient offloading model through collaboration between edge nodes for the prevention of overload and response to potential danger quickly in emergencies. In the proposed offloading model, the functions of edge computing are divided into data-centric and task-centric offloading. The offloading model can reduce the edge node overload based on a centralized, inefficient distribution and trade-off occurring in the edge node. That is the leading cause of edge node overload. So, this paper shows a collaborative offloading model in edge computing that guarantees real-time and prevention overload prevention based on data-centric offloading and task-centric offloading. Also, we present an intelligent offloading model based on several scenarios of forest fire ignition. [ABSTRACT FROM AUTHOR]

A new physical and mathematical formulation for the extinguishing of a forest fire with an inhibitor solution distributed using an explosive charge is proposed in this paper. It is assumed that the water and inhibitor are in the liquid-dispersion state and move together with the medium. The inhibitor allows the disruption of exothermic reactions, while being partially consumed. The results of numerical simulations have shown that the presence of an inhibitor makes it possible to reduce the required mass of the extinguishing composition for the successful suppression of a forest fire. It is shown that these results are in good agreement with known experimental data on the efficiency of replacing pure water with an inhibitor solution. [ABSTRACT FROM AUTHOR]

Forest fires are becoming a more significant problem in Central Europe, but their danger is not as high as that in Southern Europe. The exception, however, is forest fires occurring in disturbed areas (windthrow and bark beetle outbreak areas), which are comparable in severity and danger to the most serious forest fires. In this study, we describe the current situation in Central European countries in terms of fire protection for disturbed areas in managed forests and forest stands left to spontaneously develop (secondary succession). If a country has regulations and strategies in this area, they are often only published in the local language. In this review, we combine information from all Central European countries and summarize it in a unified international language, provide an opportunity for local authorities to express their own experiences, and integrate data from worldwide scientific research. Thus, this paper may be considered a universal guide for managing fire protection and preparedness in disturbed areas and can serve as a reference for the establishment of strict legislative rules at the state level. These laws must be obligatory for all stakeholders in individual countries. The motivation for this study was two large forest fires in an area left to spontaneously develop in the Bohemian Switzerland National Park in the Czech Republic and Harz Mountains in Germany in the summer of 2022. These incidents revealed that fire prevention legislation was inadequate or nonexistent in these areas. The strategy of the European Union is to increase the size of protected areas and spontaneous development areas. Therefore, we consider it necessary to provide governments with relevant information on this topic to create conditions for better management of these destructive events. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Wildland Fire Science is the property of Journal of Wildland Fire Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Form@re is the property of Firenze University Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Nowadays, forests play an important role in stabilizing the ecological balance, being one of the most important components of the biosphere. Due to the vital activity of forests, the gas composition of the atmosphere is normalized. Mass forest fires have the opposite effect. They cause irreparable damage to flora and fauna, contribute to the melting of Arctic ice, an increase in the Earth's temperature, and destabilization of the carbon balance. The purpose of this study is to develop an algorithm for calculating the moisture content and time of forest fire maturation of forest combustible materials. To achieve this goal, the main factors determining a forest fire hazard have been studied, as well as a review of existing methods for assessing forest fire danger and scientific papers on forest pyrology. As a result of the analysis of the research aimed at studying the rate of drying of forest combustible materials (FCM), depending on the physical properties and environmental parameters, a dependency of changes in moisture content over time was obtained. With its help, knowing the initial moisture content of FCM, it is possible to calculate the periods of fire maturation for each component of the forest plantation. Cooperative use of the resulting algorithm with a digital twin of a forest stand makes it possible to identify the most fire-hazard forest areas and estimate the period of their fire-prone maturation. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Wildland Fire Science is the property of Journal of Wildland Fire Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Wildfire is one of the most significant disturbances responsible for reshaping the terrain and changing the ecosystem of a particular region. Its detrimental effects on environ-ment as well as human lives and properties, and growing trend in terms of frequency and intensity of wildfires over the last decade have necessitated the development of efficient forest fire management techniques. During the last three decades, Forest Fire Decision Support Systems (FFDSS) have been developed to help in the decision-making processes during forest fires by providing necessary information on fire detection, their status and behavior, and other aspects of forest fires. However, most of these decision support sys-tems lack the capability of developing intelligent fire suppression strategies based upon current status and predicted behavior of forest fire. This paper presents an approach for development of efficient fireline building strategies via intelligent resource allocation. A Genetic Algorithm based approach has been proposed in this paper for resource allo-cation and optimum fireline building that minimizes the total damage due to wildland fires. The approach is based on a simulation-optimization technique in which the Genetic Algorithm uses advanced forest fire propagation models based upon Huygens principles for evaluation of cost index of its solutions. Both homogeneous and heterogeneous envi-ronmental conditions have been considered. Uncertainties in weather conditions as well as imperfect knowledge about exact vegetation and topographical conditions make exact prediction of wildfires very difficult. The paper incorporates Monte-Carlo simulations to develop robust strategies in uncertain conditions. Extensive simulations demonstrate the effectiveness of the proposed approach in efficient resource allocation for fighting complex wildfires in uncertain and dynamic conditions. [ABSTRACT FROM AUTHOR]

The existing YOLOv5‐based framework has achieved great success in the field of target detection. However, in forest fire detection tasks, there are few high‐quality forest fire images available, and the performance of the YOLO model has suffered a serious decline in detecting small‐scale forest fires. Making full use of context information can effectively improve the performance of small target detection. To this end, this paper proposes a new graph‐embedded YOLOv5 forest fire detection framework, which can improve the performance of small‐scale forest fire detection using different scales of context information. To mine local context information, we design a spatial graph convolution operation based on the message passing neural network (MPNN) mechanism. To utilize global context information, we introduce a multi‐head self‐attention (MSA) module before each YOLO head. The experimental results on FLAME and our self‐built fire dataset show that our proposed model improves the accuracy of small‐scale forest fire detection. The proposed model achieves high performance in real‐time performance by fully utilizing the advantages of the YOLOv5 framework. [ABSTRACT FROM AUTHOR]

The magnitude of the recent forest fires, the time required to extinguish them, and the damage they caused have attracted the attention of all humanity. If the current trend continues, it will cause great irreversible losses. There is a great need for scientific studies to prevent or reduce the damages of these fires. In this context, this paper proposes algorithms and mathematical models for generating the routes of unmanned aerial vehicles to detect forest fires that may occur especially in regions far from residential areas. A novel heuristic dispatching rule and a simulation-based optimization algorithm are proposed. The striking features of the proposed algorithms are that the routes are created with a focus on minimizing the fire probabilities. The uncertainties and dynamics of real-life are also considered. Various scenarios have experimented on a realistic case. Experimental results and findings are promising. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have driven the recent advances in fire detection. However, existing methods require large-scale labeled samples to train data-hungry networks, which are difficult to collect and even more laborious to label. This paper applies unsupervised domain adaptation (UDA) to transfer knowledge from a labeled public fire dataset to another unlabeled one in practical application scenarios for the first time. Then, a transfer learning benchmark dataset called Fire-DA is built from public datasets for fire recognition. Next, the Deep Subdomain Adaptation Network (DSAN) and the Dynamic Adversarial Adaptation Network (DAAN) are experimented on Fire-DA to provide a benchmark result for future transfer learning research in fire recognition. Finally, two transfer tasks are built from Fire-DA to two public forest fire datasets, the aerial forest fire dataset FLAME and the large-scale fire dataset FD-dataset containing forest fire scenarios. Compared with traditional handcrafted feature-based methods and supervised CNNs, DSAN reaches 82.5% performance of the optimal supervised CNN on the testing set of FLAME. In addition, DSAN achieves 95.8% and 83.5% recognition accuracy on the testing set and challenging testing set of FD-dataset, which outperform the optimal supervised CNN by 0.5% and 2.6%, respectively. The experimental results demonstrate that DSAN achieves an impressive performance on FLAME and a new state of the art on FD-dataset without accessing their labels during training, a fundamental step toward unsupervised forest fire recognition for industrial applications. [ABSTRACT FROM AUTHOR]

Fire was a serious natural disturbance to forest ecosystems. In this study, a national-scale forest fire risk model (RF_NTL) was proposed in mainland China by incorporating a new human activity factor (NTL) from nighttime light data. For objective verification of model's performance, the logistic regression model (LR) and random forest model (RF) were also built in this paper. Results showed that the RF_NTL model fitted with an AUC value up to 0.95, which was superior to the conventional LR model and RF model. The RF_NTL model also had good generalization ability and stability on annual and monthly scales, helping to accurately forecast forest fire risk. Moreover, the spatial distribution of forest fire risk based on RF_NTL model was detailed and reasonable on a national scale. Forest fire high-risk areas in China were mainly concentrated in the northeast and southwest regions. This study could provide references for future relevant research. [ABSTRACT FROM AUTHOR]

The scale and intensity of bushfire activity in Australia is likely to increase as a result of climate change. Effective bushfire management policy measures are therefore essential to minimise the interrelated social, environmental and economic impacts of fire in the landscape. This paper presents a historical review of bushfire management in the South West of Australia (SW): a bushfire prone and biodiverse region. Using a worldview framework to analyse key policy documents and literature, the paper demonstrates that the evolution of complex policy sectors such as bushfire management, is influenced not only by scientific and technical developments but also as a result of changing worldviews. Adapting the Integrative Worldview Framework (IWF), seven worldview categories that dominated particular periods of history in Australia are presented. These worldview categories are then used to examine the evolution of bushfire management practice, policy and institutional arrangements relevant to the SW. The argument presented herein is that a better understanding of worldviews and how they influence complex and contentious policy fields such as bushfire management, is useful for policy analysis, reflexive practice and research. The paper suggests an integrative worldview approach, which enables opportunities for exchanges and constructive conflict between stakeholders and agencies with diverse worldviews, could contribute to creating more sustainable bushfire management. Finally, it is argued that opportunities for Indigenous and Western worldview exchanges in the bushfire management sector, through collaborative knowledge partnerships could assist the sector in both management practice and policy formulation. [ABSTRACT FROM AUTHOR]

Copyright of Canadian Journal of Remote Sensing is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Indonesian Journal of Forestry Research is the property of Indonesian Journal of Forestry Research and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Early prediction of a forest fire is one of the critical research challenges of the wireless sensor network (WSN) to save our ecosystem. In WSN based forest fire detection system, sensor nodes are deployed in the remote forest area for transmitting the sensed data to the base station, which is accessible by the forest department. Though sensor nodes in the forest are localized through GPS connection, the high deployment cost for it motivates the authors of this paper to design a novel localization technique applying the Support Vector Machine. Forest fire prediction in an energy efficient way is another concern of this paper. The semi-supervised classification model is proposed to address this problem by dividing the forest area into different zones [High Active (HA), Medium Active (MA), and Low Active (LA)]. It is designed in such a way that it can be able to predict the state of the (HA, MA, LA) fire zone with 90% accuracy when only one parameter is sensed by sensor nodes due to energy constraints. The greedy forwarding technique is used to transmit the packets from the HA zone to the base station continuously, and the MA zone transmits packets periodically, whereas, LA zone avoids transmitting the sensed data to the base station. This technique of data forwarding enhances network lifetime and reduces congestion during data transmission from the forest area to the base station. [ABSTRACT FROM AUTHOR]

Copyright of Fire Ecology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Indonesia is a tropical country that experiences forest fires every year. Forest fires occur due to a prolonged summer season. A major effect of forest fires that commonly occurred in Indonesia is the respiratory disorder and the visual impairment caused by the thick smoke that can experienced by the people who lives around the forest. The effects of forest fire fumes when the forest fire spread across the bigger land or area are also experienced by neighboring countries such as Malaysia, Singapore and Brunei Darussalam. Forest is a habitat for many animals, one of which is a bird. Birds are able to communicate with their colonies through sound. The bird sound during communication to the group can be in the form of calls, marriage invitations, and warnings of danger or threat of forest fires. This paper presents bird sounds classification study using one of Deep Learning (DL) algorithms i.e. Convolutional Neural Network (CNN) method. The CNN method is used to classify bird sounds in the two conditions: (1) under normal circumstances or conditions, and (2) under threated or panic condition. The bird sound data used in this study were collected from the local birds in Indonesia. The classification result of two bird sounds based on CNN method achieved up to 96.45%. This paper is a preliminary study for bio inspired early warning of forest fires based on the sound of birds. [ABSTRACT FROM AUTHOR]

This paper shows the relevance of the problem of fire hazard in the forests of the Volga Federal District (VFD) of European Russia. The Nesterov index and the Selyaninov hydrothermal coefficient (HTC) are considered as indicators of fire hazard. The changes in climatic conditions in the VFD during 1955–2018 are shown; a trend towards warming and an increase in aridity in the study region were revealed. The repeatability of various fire hazard classes from May to September was calculated using the Nesterov method. It is shown that in July, the most dangerous situation was in the south of the VFD, where the repeatability of class IV fire hazard reached 27%. Using the HTC index, the degree of aridity of the district in the summer period was estimated. The frequency of the most arid conditions (HTC < 0.5) increases from the north to the south of the district, from 6% (Kirov Region) to 47% (Orenburg Region). Using the TT index, the potential thunderstorm danger in the VFD was assessed. With the help of the constructed maps, the hotspots of the most probable occurrence of thunderstorms were detected. The use of Rosstat data on the number of forest fires from 1992 to 2020 made it possible to consider the spatiotemporal distribution of forest fires in 14 administrative regions of the VFD. The distribution of the number of fires by the regions is shown depending on their forest cover and season. The peak of the number of fires was revealed in 2010, when the entire territory of the study region was covered by a severe drought, as a result of which the area of forests covered by fire increased many times over. In recent years (since 2017), there has been an increase in the area of burned forest due to the active phase of climate warming. [ABSTRACT FROM AUTHOR]

In this paper, the occurrence of large forest fires in the management area of ŠPD "Srednjobosanska šume" in 2020 was analyzed with regard to forest types and management classes. The period of April-May 2020 was characterized as a period with a particularly high occurrence of forest fires, where the burnt area was 1,030.36 ha, and the material damage was 1,893,559.15 KM. The causes of the fires are unknown, as are the instigators. In most cases, the human factor was found to be the cause, and in three cases it was determined that the fire was caused intentionally. The danger of certain categories of forests (and forest land) from fire is different. The biggest financial damage was caused by the burning of areas under young cultures, i.e. due to damage to seedlings. The aim of the research was to assess the number, frequency and damage caused by fires, as well as the risk of certain categories of forests from fires. Such research is essential for assessing the degree of threat to forests and forest land from fire. [ABSTRACT FROM AUTHOR]

In recent years, forest-fire monitoring methods represented by deep learning have been developed rapidly. The use of drone technology and optimization of existing models to improve forest-fire recognition accuracy and segmentation quality are of great significance for understanding the spatial distribution of forest fires and protecting forest resources. Due to the spreading and irregular nature of fire, it is extremely tough to detect fire accurately in a complex environment. Based on the aerial imagery dataset FLAME, this paper focuses on the analysis of methods to two deep-learning problems: (1) the video frames are classified as two classes (fire, no-fire) according to the presence or absence of fire. A novel image classification method based on channel domain attention mechanism was developed, which achieved a classification accuracy of 93.65%. (2) We propose a novel instance segmentation method (MaskSU R-CNN) for incipient forest-fire detection and segmentation based on MS R-CNN model. For the optimized model, the MaskIoU branch is reconstructed by a U-shaped network in order to reduce the segmentation error. Experimental results show that the precision of our MaskSU R-CNN reached 91.85%, recall 88.81%, F1-score 90.30%, and mean intersection over union (mIoU) 82.31%. Compared with many state-of-the-art segmentation models, our method achieves satisfactory results on forest-fire dataset. [ABSTRACT FROM AUTHOR]

The paper presents the results on the study of the possible application of the Canadian Forest Fire Weather Index and the Modified Angstrom Index in forest fire risk assessments. The daily values of these indices for the period 2005-2015 were related to the forest fire database. It was found that there is a relatively weak to moderate correlation between forest fires and the values of the Canadian Forest Fire Weather Index. In order to improve the wildfire risk assessments (including forest fires), the index was modified. The modified index has a significantly greater correlation with the actual events of forest fires and consequently a much wider application in southern Serbia. The modified index can be of great importance in the future concepts of forest fire risk management. [ABSTRACT FROM AUTHOR]

There is a worldwide risk of fire spread due to the mismanagement of stubble in agricultural land. In 2019, 3.6% of the forest area was damaged by fires in Turkey due to stubble burning. The burning of agriculture residues negatively affects soil properties, air quality and water resources. This finally threatens humankind sustainability. However, there is a lack of information analyzing this problem from the current policies in Turkey. Therefore, this paper reviews the legislation currently applied to understand the specific competencies to achieve sustainable fire and forest management. A holistic analysis of the legal regulations and practices to prevent stubble burning in Turkey shown here the farmer´s perception of the use of fire as an agriculture tool and the relevance of stubble burning to explain the location and recurrence of wildfires. Then, we discussed the relevance to shed light on how effective are the laws to avoid stubble burning and its impact on the environment. We claim for an update of the legislation to allow the farmers to manage the stubble and encourage the policymakers to develop new strategies to compost the stubble and achieve sustainable management within the Sustainable Development Goals of the United Nations that will contribute to achieving the Land Degradation Neutrality Challenge. [ABSTRACT FROM AUTHOR]

Forest landscapes across western North America (wNA) have experienced extensive changes over the last two centuries, while climatic warming has become a global reality over the last four decades. Resulting interactions between historical increases in forested area and density and recent rapid warming, increasing insect mortality, and wildfire burned areas, are now leading to substantial abrupt landscape alterations. These outcomes are forcing forest planners and managers to identify strategies that can modify future outcomes that are ecologically and/or socially undesirable. Past forest management, including widespread harvest of fire‐ and climate‐tolerant large old trees and old forests, fire exclusion (both Indigenous and lightning ignitions), and highly effective wildfire suppression have contributed to the current state of wNA forests. These practices were successful at meeting short‐term demands, but they match poorly to modern realities. Hagmann et al. review a century of observations and multi‐scale, multi‐proxy, research evidence that details widespread changes in forested landscapes and wildfire regimes since the influx of European colonists. Over the preceding 10 millennia, large areas of wNA were already settled and proactively managed with intentional burning by Indigenous tribes. Prichard et al. then review the research on management practices historically applied by Indigenous tribes and currently applied by some managers to intentionally manage forests for resilient conditions. They address 10 questions surrounding the application and relevance of these management practices. Here, we highlight the main findings of both papers and offer recommendations for management. We discuss progress paralysis that often occurs with strict adherence to the precautionary principle; offer insights for dealing with the common problem of irreducible uncertainty and suggestions for reframing management and policy direction; and identify key knowledge gaps and research needs. [ABSTRACT FROM AUTHOR]

The Brazilian savannah-like Cerrado is classified as a fire-dependent biome. Human activities have altered the fire regimes in the region, and as a result, not all fires have ecological benefits. The indigenous lands (ILs) of the Brazilian Cerrado have registered the recurrence of forest fires. Thus, the diagnosis of these events is fundamental to understanding the burning regimes and their consequences. The main objective of this paper is to evaluate the fire regimes in Cerrado's indigenous lands from 2008 to 2017. We used the Landsat time series, at 30 m spatial resolution, available in the Google Earth Engine platform to delineate the burned areas. We used precipitation data from a meteorological station to define the rainy season (RS), early dry season (EDS), middle dry season (MDS), and late dry season (LDS) periods. During 2008-2017, our results show that the total burned area in the indigenous lands and surrounding area was 2,289,562 hectares, distributed in 14,653 scars. Most fires took place between June and November, and the annual burned area was quite different in the years studied. It was also possible to identify areas with high fire recurrence. The fire regime patterns described here are the first step towards understanding the fire regimes in the region and establishing directions to improve management strategies and guide public policies. [ABSTRACT FROM AUTHOR]

The Alaskan boreal forest is characterized by frequent extensive wildfires whose spatial extent has been mapped for the past 70 years. Simple predictions based on this record indicate that area burned will increase as a response to climate warming in Alaska. However, two additional factors have affected the area burned in this time record: the Pacific decadal oscillation (PDO) switched from cool and moist to warm and dry in the late 1970s and the Alaska Fire Service instituted a fire suppression policy in the late 1980s. In this paper a geographic information system (GIS) is used in combination with statistical analyses to reevaluate the changes in area burned through time in Alaska considering both the influence of the PDO and fire management. The authors found that the area burned has increased since the PDO switch and that fire management drastically decreased the area burned in highly suppressed zones. However, the temporal analysis of this study shows that the area burned is increasing more rapidly in suppressed zones than in the unsuppressed zone since the late 1980s. These results indicate that fire policies as well as regional climate patterns are important as large-scale controls on fires over time and across the Alaskan boreal forest. [ABSTRACT FROM AUTHOR]

Copyright of Forest Engineering is the property of Forest Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The article discusses various reports published within the issue, including one by B. M. Wotton on the use of Canadian forest fire danger rating system, one by Boychuk and colleagues on the use of renewal processes for crown fire modeling which is spread through a prevailing wind, and one by Hering and colleagues on the use of spatial point processes in spatial wildfire distribution modeling.

Forest fires have been showing an increasing trend in the past few years. Hundreds of hectares of forests are damaged every year. Thus, it is crucial to identify and implement appropriate forest fire management measures. GIS hotspot analysis has become an advantageous technique for the analysis of spatial clustering of forest fires. However, inadequate research has been undertaken on the validation of forest fire hotspot analysis in GIS. The objective of this paper is to validate forest fire hotspots identified by two statistical-based and one non-statistical-based GIS hotspot analysis methods, namely Getis-Ord Gi*, Anselin Local Moran's I and Kernel Density Estimation (KDE), in a study area. The three hotspot analyses were validated by evaluating the spatial interference between the identified forest fire hotspots by each method and existing forest fire contributory factors. The study found that KDE resulted in better spatial matching of forest fire hotspots and forest fire contributory factors, compared to Getis-Ord Gi*. However, Anselin Local Moran's I did not identify any statistically significant forest fire hotspots in the study area. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel approach for estimating the burned area of forest fires using the TabNet transformer-based architecture. Forest fires pose a significant threat to ecosystems, and accurate estimation of the affected area is essential for effective disaster management and resource allocation. We conducted a comprehensive analysis of various Machine Learning (ML) and Deep Learning (DL) methods, including Random Forest, Neural Networks, Neural Architecture Search (NAS), TabNet with Transformers, and Self-Supervised Learning with Autoencoders, to identify the most accurate and efficient model for area estimation. Our experiments employed a publicly available dataset, UCI Forest Fires, containing a combination of meteorological, geospatial, and categorical data. We implemented a thorough preprocessing pipeline that included handling categorical variables, standardization, and feature engineering. The results demonstrate that TabNet outperforms other methods, achieving state-of-the-art accuracy and generalization in predicting the target variable with a Mean Squared Error (MSE) of 2319 in training and 7781 in testing. [ABSTRACT FROM AUTHOR]

Forest areas or green infrastructure have become a fundamental economic and social factor which has made it possible to generate new sources of employment and to maximize the use of basic resources. Nevertheless, good conservation of this type of infrastructure is a challenge. This is due to the problems deriving from, on the one hand, the increase of its physical scope and, on the other, poor management or no management at all. The Spanish region of Galicia is a historic place of natural wealth, especially concerning forest resources, wherein 2/3 of its territory is forest area from where more than half of the Spanish wood supply comes.This paper seeks to create a mapping of major forest fire disturbances on the Galician territory over extended periods of time. To achieve this, an automated multitemporal detection process based on vegetation indices and unsupervised learning is developed. The objective is to obtain data heterogeneity in terms of vegetation state, land use, and image properties, allowing a better understanding of forest land disturbances and improving their management. [ABSTRACT FROM AUTHOR]

Modern geospatial technologies and permanently updated wildfire monitoring datasets are the basis of improving forest firefighting on different administrative scales. One of the tasks is to use the spatial representation of forest fire locations during the fire season and offer timely suitable technical options for accessing them. We developed a GIS technology to create forest fire ground access routes for special firefighting vehicles moving from a ground firefighting base (fire-chemical station) to the place of the forest fire detection; the technology includes a statistical and geospatial accessibility analysis of the routes. The key data are a transport model consisting of public roads and forest glades on the regional scale. We described the main principles of the transport model construction and usage, and their implementation for the Russian Federal Districts. An access routes database for the 2002-2019 fire seasons, a central part of the Siberian Federal District, was produced and analysed. By using a hot spot analysis, we confirmed that forest fires are poorly accessible away from the centre of the Siberian District. The created road accessibility maps show "a proposed ground access zone" within the key area to fight forest fires for the fire seasons to come. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Fire Ecology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Forest fire is one of the dominant disturbances in the forests of Heilongjiang Province, China, and is one of the most rapid response predictors that indicate the impact of climate change on forests. This study calculated the Canadian FWI (Fire Weather Index) and its components from meteorological record over past years, and a linear model was built from the monthly mean FWI and monthly fire numbers. The significance test showed that fire numbers and FWI had a very pronounced correlation, and monthly mean FWI was suitable for predicting the monthly fire numbers in this region. Then FWI and its components were calculated from the SRES (IPCC Special Report on Emission Scenarios) A2 and B2 climatic scenarios, and the linear model was rebuilt to be suitable for the climatic scenarios. The results indicated that fire numbers would increase by 2.98–129.97% and −2.86–103.30% in the A2 and B2 climatic scenarios during 2020–2090, respectively. The monthly variation tendency of the FWI components is similar in the A2 and B2 climatic scenarios. The increasing fire risk is uneven across months in these two climatic scenarios. The monthly analysis showed that the FFMC (Fine Fuel Moisture Code) would increase dramatically in summer, and the decreasing precipitation in summer would contribute greatly to this tendency. The FWI would increase rapidly from the spring fire season to the autumn fire season, and the FWI would have the most rapid increase in speed in the spring fire season. DMC (Duff Moisture Code) and DC (Drought Code) have relatively balanced rates of increasing from spring to autumn. The change in the FWI in this region is uneven in space as well. In early 21st century, the FWI of the north of Heilongjiang Province would increase more rapidly than the south, whereas the FWI of the middle and south of Heilongjiang Province would gradually catch up with the increasing speed of the north from the middle of 21st century. The changes in the FWI across seasons and space would influence the fire management policy in this region, and the increasing fire numbers and variations in the FWI scross season and space suggest that suitable development of the management of fire sources and forest fuel should be conducted. [ABSTRACT FROM AUTHOR]