Aerial Firefighting Research Articles

A Deep Learning Approach for Predicting Aerial Suppressant Drops in Wildland Firefighting Using Automatic Dependent Surveillance–Broadcast Data

This study utilizes Automatic Dependent Surveillance–Broadcast (ADS-B) data sourced by the OpenSky Network to curate a dataset aimed at enhancing the precision of aerial suppressant drop predictions in wildland firefighting. By amalgamating ADS-B data with Automated Telemetry Unit (ATU) drop information, this research constructs a reliable base for analyzing the spatial aspects of aerial firefighting operations. Using sequential machine learning models, specifically Long Short-Term Memory (LSTM) networks and 1D Convolutional Neural Networks (1DCNN), the study interprets complex flight dynamics to predict drop locations. The dataset, covering 2017 to 2023, is labeled and segmented to reflect accurate suppressant release events, facilitating the distinction between drop and non-drop activities in fixed-wing aircraft. The LSTM model demonstrated strong predictive performance with an F1 score of 0.922, effectively identifying suppressant drop events with high accuracy. This model’s reliable predictions can significantly improve situational awareness in real-time aerial firefighting operations, enabling more informed decision-making and better coordination of resources during wildfire events.

The cost of operational complexity: A causal assessment of pre-fire mitigation and wildfire suppression

Pre-fire mitigation efforts that include the installation and maintenance of fuel breaks are integral to wildfire suppression in Southern California. Fuel breaks alter fire behavior and assist in fire suppression at strategic locations on the landscape. However, the combined effectiveness of fuel breaks and wildfire suppression is not well studied. Using daily firefighting personnel to proxy the quantity and diversity of potential fire suppression operations (i.e., operational complexity), we examined 15 wildfires from 2017 to 2020 in the Los Padres, Angeles, San Bernardino, and Cleveland National Forests to assess how weather and site-specific fuel break characteristics influenced wildfire containment when leveraged during suppression operations. After removing effects of fuel treatments, wildfire and aerial firefighting, we estimated that expanding fuel break width in grass-dominant systems from 10 to 100 m increased the average success rate against a heading fire from 31 % to 41 %. Likewise, recently cleared fuel breaks had higher success rates compared to poorly maintained fuel breaks in both grass (25 % to 45 %) and shrub systems (20 % to 45 %). Combined, grass and shrub systems exhibited an estimated success rate of 80 % under mild weather conditions (20th percentile) and 19 % under severe weather (80th percentile). Other significant determinants included forb and grass production, adjacent tree canopy cover and terrain. Consistent with complexity theory and previous suppression effectiveness research, our analysis showed signs of suppression effectiveness declining as firefighter personnel increased. Future work could better account for the role of suppression with improved data on firefighting resource types, actions, locations, and timing.

Numerical model of aerial drop characteristic of mass firefighting units for aerial firefighting

The aerial drop characteristic of mass firefighting units has a significant influence on the effectiveness of aerial firefighting. In order to accurately describe the aerial drop characteristic of mass firefighting units, a numerical model covering the fundamental stages of the whole operation process was developed in the present study. In the model, mass firefighting units' filling and discharging processes are simulated by the discrete element method; the falling process is simulated by aerodynamic analysis, and the ground pattern characteristics are obtained. The model validation shows that, the numerical result agrees well with the experimental result with a maximum deviation of 14 %. The initial velocity distribution characteristic remains constant with varying filling amounts, and the mass fire firefighting units' initial velocities at different times follow a special normal distribution; the standard deviation of the initial velocities’ distribution primarily determines the width of mass firefighting units' ground pattern, while initial velocity and filling amount primarily determine the length of the ground pattern; the maximum coverage level is about 10 L/m2.

Using Optimization Modeling to Determine Locations for Aerial Firefighting Resources Based on Wildfire Risk Data

The increase of the global mean temperature likely leads to more frequent and prolonged fire weather periods, with hot and dry conditions. This would also lead to increased frequency and magnitude of wildfires, and increased risk of spatial and temporal co-occurrence. A key to control and suppress wildfires during fire weather is a strong initial response, for which aerial firefighting resources can be used. This paper investigates the potential of optimization modeling to support pre-wildfire location planning of aerial firefighting resources, by developing a binary integer programing model and test it on Swedish case data. The model produces useful results given considerably less amount of available input data to determine the locations, compared with the manual planning. With relatively short solution times, it shows potential to support fast relocation of resources during sudden changes of circumstances, and to facilitate implementation of a standard operating procedure, with less expert knowledge dependence.

Forest firefighting technology: Strategic water reservoir placement for terrestrial and aerial vehicles

Forest fires pose significant environmental, economic, and social threats to protected areas. Understanding their destructive potential is crucial for effective risk management. Two key factors in firefighting are water availability and emergency response networks. This study aimed to determine optimal locations for water reservoirs, supporting terrestrial and/or aerial firefighting in the Caparaó National Park within the Brazilian Atlantic Forest biome. Geotechnological tools (fuzzy logic, Euclidean distance, network analysis) were employed to identify strategic reservoir locations, considering land use, slope, proximity to roads, watercourses, and fire risk. The application of these methodologies revealed that terrestrial firefighting alone fell short of meeting the specified demand, capable of addressing at most 92.13 % of demand within the longest available timeframe (20 min). Additionally, the number of reservoirs required for this method was significantly higher (724 reservoirs) compared to aerial firefighting (42 reservoirs). Analyzing the investment needed for reservoir construction relative to the covered area in each evaluated scenario, it is evident that the terrestrial approach incurs a significantly higher cost ($40,664.35.km−2) than the aerial approach ($2358.98.km−2). From these results, it was concluded that the use of geotechnological tools is efficient in identifying strategic water reservoir locations for replenishing firefighting vehicles, and all methodologies support the creation of priority measures and plans for firefighting, proving to be viable, applicable, replicable, and adaptable to any other protected areas and economically significant regions.

Flight performance analysis of aerial fire fighting

AbstractThis paper investigates the operational patterns and techniques of aerial fire fighting. It is demonstrated that manoeuvrability and endurance are the main characteristics when choosing air tactical aircraft; focus is on load capability for helicopters and air tankers. Water tank filling and deployment techniques are evaluated. Aircraft using pressure deployment systems are found to produce more uniform and heavy coverage in comparison with gravity systems. ADS-B open source data of flight operations and performance was collected. Operational patterns are found to be independent on the size of particular aircraft category (non-amphibious and amphibious air tanker, helicopter, air-tactical aircraft). Effectiveness and cost are modelled using the retardant dropped per operation and the average number of daily missions. The largest aircraft, Type-I helicopters and very large air tankers (VLAT) are found to be the most effective water- and retardant-dropping aircraft. The best cost-to-litre-dropped ratio for water-dropping aircraft is attributed to Type-III helicopters and amphibious Type-III aircraft; for retardant-dropping aircraft, VLAT are most effective. To maximise fire fighting effectiveness, Type-I helicopters and VLAT should be used as far as possible, with pressure deployment systems.

Flight Simulation of Fire-Fighting Aircraft Based on Multi-Factor Coupling Modeling of Forest Fire

Forest fires can develop rapidly and may cause a wide range of hazards. Therefore, aerial firefighting, which has the ability to respond and reach fire fields quickly, is of great significance to the emergency response to and subsequent extinguishing of forest fires. The burning of forest fires generates a lot of heat and smoke, which changes the air flow environment and vision over the region and brings challenges to aerial firefighting. In the present work, aerial forest firefighting simulation was divided into the forest fire spread model, the air flow model and the aircraft flight dynamic and automatic control model. Each model was constructed based on a physical method. An integrated framework was designed to realize the interaction among fire fields, airfields, and aircraft, and is verified. The proposed framework can be used for the emergency response decision of aerial forest fire fighting and subsequent fire-fighting mission planning.

Experimental study of water spreading parameters when extinguishing fires using aircraft sprinklers

This paper reports results of an experimental study on hydrodynamic processes when water is dropped from a height, as well as their influence on the movement of liquid, in order to optimize the processes of aviation firefighting. The main parameters of water dispersion were determined based on a series of experiments. It was established that the average diameter of drops when dropped from a height of 10 meters is 2.5 mm, with a maximum spraying distance of up to 15 meters. The size distribution of the droplets showed that 30 % of the droplets have a diameter of less than 2 mm, 50 % are between 2 and 5 mm, and 20 % are more than 5 mm. During the experiments, it was measured that the time for pouring water from the container is 3 seconds, and the speed of movement of water fractions when dropped from a height of 10 meters is 9.8 m/s. With an increase in the discharge height by 5 meters, the speed of water movement increased by 20 %. One of the key points of the study is the improvement of the Torricelli equation by introducing the coefficient K (0.85), which takes into account the viscosity and density of water, which improved the accuracy of calculations by 15 % compared to the standard equation. Python was used to process and interpret the video data, along with libraries such as OpenCV for image processing, NumPy for high-performance mathematical computations, and Matplotlib for data visualization. The resulting data open up new prospects for devising aerial firefighting strategies, providing a 20 % increase in coverage area, and a 25 % reduction in firefighting time. Torricelli's equation was improved; a new procedure was devised for the experimental determination of water dispersion parameters, which has an important practical application in the field of fire safety. In the field of fire safety, the data obtained could be used to improve aviation firefighting strategies, which would allow for greater efficiency and safety

Helicopter Aerial Work: Technology to Meet Growing Needs in Critical Missions

Helicopters provide aerial services such as firefighting, medical transport, agriculture, and construction for critical industries that form the backbone of modern society. These "aerial work" applications comprise the majority of the current market for civilian helicopters and include a diverse set of mission types and flight profiles; in many cases, aerial work applications are meeting growing needs driven by the climate crisis and energy transition. Through a series of more than 180 interviews with operators, pilots, and users across helicopter aerial work, this paper — the largest contemporary study of its kind — surveys the challenges that the industry sees for itself. Part I analyzes and summarizes our original primary source data to provide both qualitative and quantitative assessments of the needs of this community. Part II presents a case study for aerial firefighting, where a growing demand driven by record-breaking climatic changes is straining the existing air crews, aircraft fleet, and firefighting technology. Many issues identified in firefighting are endemic problems that beset other neighboring applications within aerial work such as public services, energy infrastructure, construction, and agriculture; technologies that have the potential to have a significant impact on re ghting are discussed. Part III is an analysis of technology and how it might better meet the needs of helicopter aerial work. We identify characteristics such as compatibility, reliability, and application specialization that are valued by helicopter aerial work customers and operators. In the backdrop of unprecedented venture capital investment and technology development in new types of vertical takeoff and landing aircraft for AAM, this paper's core nding is that the needs of helicopter aerial work are not being met: a venture capital culture prioritizes innovation that can create new markets over solving challenges in existing ones. Innovation for commercial air transport missions that operate under different market, environmental, and operational conditions does not "trickle down" to aerial work. We identify a need for increased collaboration between technologists and the aerial work community and for a more thoughtful approach towards investment and development to meet the growing challenges of the industry.

NUMERICAL CALCULATIONS OF WATER DROP USING A FIREFIGHTING AIRCRAFT

The study involved a numerical analysis of the water dropping process by fixed-wing aircraft. This method, also known as air attack, is used for aerial firefighting, primarily in green areas such as forests and meadows. The conducted calculations allowed for the analysis of the process over time. The calculations were performed based on a SolidWorks model of the M18B Dromader aircraft. After defining the computational domain and setting the boundary conditions, the simulations were carried out using the ANSYS Fluent software. The resulting water dropping area was used to analyze the intensity of water distribution. The volumetric distribution and airflow velocity distribution were analyzed for specified time steps. The boundary layer where air no longer mixes with water during the final phase of water dropping was also determined. The obtained results provide an important contribution to further analyses aimed at optimizing the water dropping process by fixed-wing aircraft.

Examining the Effectiveness of Aerial Firefighting with the Components of Firebreak Requirements and Footprint Geometry—Critics of the Present Practice

The negative impact of climate change is increasingly evident in the severity of forest fires. Fires are becoming more intense and can often only be controlled by aerial means. Aerial firefighting is known as a very effective method—in some cases, it is the only option—of suppressing fire, but it is a very expensive solution. Recently, the effectiveness of this method has received a lot of criticism, with some studies showing a loss of between 60 and 95%, so it is worth approaching this issue in a different way. The aim of this study is to estimate losses using a new method that has not been used before. For this purpose, this study focuses on two components: the requirements of the firebreak and the geometry of the footprint. For the first, the rules of thumb of the practice were applied depending on the fireline intensity. One is the required coverage level of the surface with suppressant, and the other is the required wetted bandwidth, which is the firebreak. In practice, the firebreak should be 2–2.5 times wider than the length of the flame. For the footprint geometry, the author used the results of previous studies dealing with footprint formation. At the end, the design of the required firebreak and the simplified design of the footprint, which is an ellipsoid, were compared to each other. The results show that, in the case of a fireline intensity of 3 MWm−1 and a coverage level of 2.4 kgm−2, the loss is approximately 36.4–44.6% for the ellipsoidal footprint alone and 86–87.8% for the total amount of extinguishing agent. The conclusion is that future work should focus not on a more accurate description and understanding of emissions but on developing a technology that can change the shape of the footprint from an elliptical to a rectangular shape.

Применение метода Кларка – Райта в задачах тушения лесных пожаров силами авиационной охраны

Introduction. The purpose of this study is to determine the minimum cost of a path to a standstill forest fire and its localization. To achieve this goal, it is necessary to perform the tasks of analyzing the selected method for calculating the minimum costs for the process of unloading a fire landing and the process of localization of a low forest fire accordingly; identifying and characterizing the necessary equipment used in localizing a low forest fire; on definition of the optimal way and the number of employees of the Ministry of Emergency Situations as part of a fire landing force using an algorithm in the form of a pseudocode. The analytical part. The models, methods and algorithms of search of shortest way, optimization, circulation routing of transport are reviewed. Some problem of extinguishing of forest fire is set. The application of the modi­fied Clarke and Wright algorithm, which considers a possibility of variation of depth of route splice and definition of optimal value of probability of realization of the worsening step, makes it possible to find the minimum time spent by aviation forest protection for localization of a low forest fire. A solution to the problem of fire troop deli­very thanks to pseudocode implementing the basic Clarke and Wright algorithm is given. Conclusions. The solution based on the modified Clarke and Wright algorithm provides circular air routes that will be assigned to a helicopter, so that the delivery of firefighting troops will become economically feasible. The results of the research will be useful to analysts and software developers for the implementation of aerial firefighting activities.

Diagnosing the Institutional Forces Impacting Australia’s Aerial Firefighting Capability

Climate change is resulting in more wildfires, and increasingly, there are overlapping wildfire seasons between the northern and southern hemispheres. The changing climate is especially impacting the nature of aerial firefighting. This study uses an institutional lens to analyse the resources and structures associated with aerial firefighting in Australia. A set of convergent interviews of subject matter experts surfaced the key issues that have led to the current aerial firefighting situation in Australia and showed the relationships between issues. The convergent interviewing method is used to identify the core, common issues that influence the aerial firefighting system in Australia. The results highlight how aerial firefighting suffers due to the complexities that exist between the states and from a lack of a national strategy. A lack of process standardisation, an overreliance on, often international, LATs and the lack of a coordinated mitigation approach are particularly notable specific issues. Institutional theory suggests that Australia’s aerial firefighting capability has succumbed to isomorphic pressures, with the desire for legitimacy driving ever-increasing institutionalization. To respond to the changing environment, institutional entrepreneurs will be needed to create new norms and significantly change the embedded structures.

Study on the ground fraction of air tankers

Background The ground fraction refers to the ratio of the liquid collected on the ground to the dropped liquid, which is the key index used to assess the drop ground pattern of air tankers when combating wildfires. However, there is no quantitative mechanism model to estimate ground fraction. Aims and methods The current work aims to create a simple model of the ground fraction by directly using full-scale drop test data with different firefighting agents for fitting. Key results and conclusions The result shows that the ground fraction can be estimated by simple quantitative relationships despite significant differences between the conditions of the drop tests. These relationships include factors that can be manipulated during aircraft and release system design as well as during aerial firefighting operations. Implications Based on the presented model, an equation for the maximum coverage level of the mean liquid distribution is solved, and the induced effects of drop velocity, drop height, liquid viscosity and other factors on the ground pattern are revealed, which can provide direct predictions of ground drop distributions.

산불 진화장비의 표준화를 위한 성능평가 기준 개발

The domestic wildfire extinguishing system is largely composed of ground and aerial firefighting. Ground firefighting used by manpower and extingushing residual fires. Currently, the Korea Forest Service is using a fire extinguisher, a mechanized system, and a back-pack pump as ground fire extinguishing equipment. Among the domestic wildfire extinguishing equipment, the mechanized system is the only firefighting system different from other countries as it utilizes manpower and machinery in consideration of the special forest fire environment in Korea. However, there is no standardized forest fire extinguishing system through quality control of extinguishing equipment and quantification of the efficiency of extinguishing activities. In this study, in order to establish performance evaluation criteria for domestic major ground firefighting equipment, such as fire extinguishing vehicles, mechanized systems, and back pack pumps, the performance evaluation criteria of overseas forest fire extinguishing equipment were investigated and analyzed, and domestic forest fire related activities were conducted through field demonstrations and public hearings. The performance evaluation criteria were presented by collecting the problems of the existing firefighting equipment and matters that need improvement by experts.

A cooperative (or coordinated) multi-agency response to enhance the effectiveness of aerial bushfire suppression operations

An effective and efficient suppression of a bushfire is predicated on synchronised collaborative planning, information sharing, scheduling and tasks coordination between multiple agencies. This paper aims to develop a bushfire suppression optimisation model, which minimises the completion times and total costs within resource constraints. An algorithm is developed to tackle the highly complex operational response to bushfire suppression via aerial firefighting. A real case study of 2009 Black Saturday bushfires in Victoria is used to create the situational context and to derive model parameters. Three scenarios are designed to incorporate time and resource constraints to reflect a highly uncertain and dynamic situated bushfire environment. This study has generated bushfire suppression plans in emergency situations by improving resource utilisation efficiency and time scheduling. In the baseline scenario, the model indicates the ability of fire agencies to complete all operational activities, but in the scenarios where resource shortage and time limitations exist, the cost of unmet demands fell slightly. The outcomes of the proposed approach will help to enhance multi-agencies coordination in fire suppression evacuation plans to improve operational response and maximise geographic coverage of service delivery.

Prediction of Large-Scale Wildfires With the Canopy Stress Index Derived from Soil Moisture Active Passive

Land surface variables such as surface soil moisture are recognized as important wildfire indicators. However, quantifying wildfire fuel combustibility through only satellite-retrieved soil moisture remains challenging, because soil moisture does not provide information about vegetation (fuel) moisture and water availability to plants is complicated by another factor of soil properties. Thus, to enhance the wildfire prediction ability of the soil moisture active passive (SMAP) mission, this study examines a canopy stress index (CSI) retrieved from 1 km SMAP level 2 products. The strong relationship between prefire CSI and fire severity is demonstrated over two large-scale (greater than 1000 ha) wildfires in Gang-won Province, South Korea. CSI can effectively predict the severity of large-scale wildfires one week before fire events, differentiating dry soils from wildfire hazards. SMAP L2 data with a temporal resolution of 5–7 d over the study sites are suitable for supporting aerial firefighting activities and reducing false fire warnings.

A digital twin framework for machine learning optimization of aerial fire fighting and pilot safety

The objective of this work is to model and simulate aerial drops of fire retardants in dangerous fire environments. Specifically, the work develops a computational framework for a model problem combining: •[1.] A meshless discrete element component that tracks the trajectory of released airborne materials from a controlled aircraft, ranging from retardant powders to encapsulated packets, subjected to prevailing wind velocities and fire-driven updrafts.•[2.] A Machine Learning Algorithm (MLA) to rapidly ascertain the optimal aircraft (unmanned or manned) dynamics to maximize the fire-retardant release effectiveness (released material usage and target impact). The framework is designed to enable Digital Twin type technologies, i.e. digital replicas that run in real time with the physical system. However, it is also designed to run at much faster rates, in order to enable MLA’s to optimize the planning, by running quickly on laptops and mobile systems. The overall guiding motivation is to provide a useful tool to enable rapid flight-path planning for aerial first-responders in real-time and to train pilots. Numerical examples are provided to illustrate the process.

Operational conditions of aerial forest firefighting: efficiency and effectiveness

-

Aerial firefighter radio communication performance in a virtual training system: radio communication disruptions simulated in VR for Air Attack Supervision

Communication disruptions are frequent in aerial firefighting. Information is more easily lost over multiple radio channels, busy with simultaneous conversations. Such a high bandwidth of information throughput creates mental overload. Further problems with hardware or radio signals being disrupted over long distances or by mountainous terrain make it difficult to coordinate firefighting efforts. This creates stressful conditions and requires certain expertise to manage effectively. An experiment was conducted which tested the effects of disrupting users communications equipment and measured their stress levels as well as communication performance. This research investigated how realistic communication disruptions have an effect on behavioural changes in communication frequency, as well as physiological stress by means of measuring heart rate variability (HRV). Broken radio transmissions created a greater degree of stress than background chatter alone. Experts could maintain a more stable HRV during disruptions than novices, which was calculated on the change in HRV during the experiment. From this, we deduce that experts have a better ability to manage stress. We also noted strategies employed by experts such as relaying to overcome the radio challenges, as opposed to novices who would not find a solution, effectively giving up.