Fire Weather Index Research Articles

Trend Analysis and Spatial Behaviour of the Fire Weather Index in the Mediterranean Iberian Peninsula, 1971–2022

ABSTRACTThe Fire Weather Index (FWI) is a widely used metric to estimate the wildfire risk based on climatological variables. As anthropogenic climate change is expected to increase wildfire risk by affecting the climate of the Mediterranean Iberian Peninsula, we assess the expected increase in wildfire risk during the past decades. For this purpose, we employ a dataset containing daily FWI values in a 0.25° × 0.25° grid for each day of a 52‐year period, between 1971 and 2022, and perform a trend analysis at a statistically significant level. We evaluate the relation between FWI and spatial (altitude, latitude, and distance to the sea) variables to look for significant correlations. An analysis is performed at the geographic level by focusing on changes in concrete, relatively homogenous zones (subregions) to broadly study spatial patterns of change. The most relevant results are (1) the FWI shows an increasing trend across the study area (0.01 confidence level); (2) the FWI is determined by temperature variations on a multiyear scale, but annually by more volatile precipitation patterns; (3) the FWI does not uniformly behave across either space or time, and is subject to different variations in different zones; (4) summer and winter are the seasons with the most significant increase, and autumn is the only not significant season; (5) very high or extreme risks are increasingly prevalent across the territory, increasing wildfire risk and (6) the FWI more rapidly rises in areas further north, at a longer distance to the sea and at higher altitudes, with the Iberian System being the most affected region. The increase in wildfire risk requires putting in place more preventive measures. Our study results coincide with climatological trend studies on the region and bridge a knowledge gap as regards the historical climatology of the FWI.

Prediction of fire danger index using a new machine learning based method to enhance power system resiliency against wildfires

AbstractWildfires, which can cause significant damage to power systems, are mostly inevitable and unpredictable. Fire danger indexes, such as the Forest Fire Danger Index (FFDI) and the Canadian Fire Weather Index (FWI), measure the potential wildfire danger at a given time and location. Thus, by predicting these fire danger indexes in advance, power system operators can obtain valuable insight into the potential wildfire risks and can better be prepared to tackle the wildfires. However, due to dependency on weather conditions, these indexes usually have volatile time series, which make their prediction complex. Taking these facts into account, this paper, unlike previous approaches that predict fire danger indexes based on climatological models, develops a machine learning‐based forecast process to predict these indexes using the relevant weather data and past performance. To do this, first, a volatility analysis approach is presented to analyse the volatility level of the time series data of a fire danger index. Afterwards, an effective machine learning‐based forecast methodology using a new deep feature selection model is proposed to predict fire danger indexes. The developed forecast methodology is tested on the real‐world data of FFDI and FWI and is compared with several popular alternative methods reported in the literature.

Enhanced prediction of extreme fire weather conditions in spring using the Hot-Dry-Windy Index in Alberta, Canada

Background Fire weather indices forecast fire behaviour and provide valuable information for wildland fire prevention, preparedness, and suppression. However, these indices do not directly account for atmospheric conditions aloft. The province of Alberta, Canada has experienced extreme fire weather conditions during spring for decades, leading to the continued occurrence of disastrous wildland fires. Aims We examined the Hot-Dry-Windy Index (HDWI) and spread days over the first 4 days of 80 large wildland fires that started in May 1990–2019 in Alberta. Methods HDWI values were calculated using ERA5 reanalysis data from the 1000, 975 and 950 hPa levels. Differences between HDWI distributions on spread days and non-spread days were examined using permutation tests. Initial Spread Index was also examined as it is considered an important Fire Weather Index System value for wildland fire spread during spring in Alberta. Key results Higher median HDWI values were observed on spread days than non-spread days, where median Initial Spread Index values showed little to no difference. Conclusions This analysis suggests that HDWI can contribute to the prediction of significant spring wildland fire spread in Alberta. Implications Forecasted HDWI and HDWI climatologies may provide additional decision support for wildland fire management agencies.

Attribution analysis of the persistent and extreme drought in southwest China during 2022–2023

Abstract Southwest China experienced a severe drought during winter 2022–spring 2023. This drought mainly struck Yunnan Province and surrounding regions (21°–30° N, 97°–106° E), with precipitation deficit lasting for about 8 months from Oct 2022 to May 2023. The area-mean precipitation and surface soil moisture in the study region during the drought were both the lowest recorded for the same period since 1950. The Standardized Precipitation Evapotranspiration Index (SPEI) also reached its lowest level since 1950 at −2.76. Quantitative analysis shows that precipitation deficit and potential evapotranspiration (PET) increase contributed 71.36%, and 28.64% to the SPEI, respectively. Of the raw contribution of PET, 7.05% can in turn be attributed to the changes in precipitation. Using data from the CMIP6 Detection and Attribution Model Intercomparison Project (DAMIP), we found that anthropogenic forcing increased the likelihood of a PET anomaly such as the one during the drought by about 133 times, with a fraction of attributable risk (FAR) of 0.99 [0.98, 1.00]. For the precipitation anomaly, we obtained a FAR of 0.26 [−1.12, 0.70], suggesting that anthropogenic forcings may have little impact. The extreme drought also increased the risk of fires, with the Fire Weather Index reaching its second-highest value since 1950 and abnormally high burned areas observed by satellites.

Simulation of Fire Occurrence Based on Historical Data in Future Climate Scenarios and Its Practical Verification

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.

Wildfire Burnt Area and Associated Greenhouse Gas Emissions under Future Climate Change Scenarios in the Mediterranean: Developing a Robust Estimation Approach

Wildfires burn annually over 400,000 ha in Mediterranean countries. By the end of the 21st century, wildfire Burnt Area (BA) and associated Green House Gas (GHG) emissions may double to triple due to climate change. Regional projections of future BA are urgently required to update wildfire policies. We present a robust methodology for estimating regional wildfire BA and GHG emissions under future climate change scenarios in the Mediterranean. The Fire Weather Index, selected drought indices, and meteorological variables were correlated against BA/GHG emissions data to create area-specific statistical projection models. State-of-the-art regional climate models (horizontal resolution: 12 km), developed within the EURO-CORDEX initiative, simulated data under three climate change scenarios (RCP2.6, RCP4.5, and RCP8.5) up to 2070. These data drove the statistical models to estimate future wildfire BA and GHG emissions in three pilot areas in Greece, Montenegro, and France. Wildfire BA is projected to increase by 20% to 130% up to 2070, depending on the study area and climate scenario. The future expansion of fire-prone areas into the north Mediterranean and mountain environments is particularly alarming, given the large biomass present here. Fire-smart landscape management may, however, greatly reduce the projected future wildfire BA and GHG increases.

High-resolution projections of future FWI conditions for Portugal according to CMIP6 future climate scenarios

Wildfires are catastrophes of natural origin or initiated by human activities with high disruptive potential. "Portugal, located in western Iberia, has recently experienced several large fire events, including megafires, due to a combination of factors such as orography, vegetation, climate, and socio-demographic conditions that contribute to fuel accumulation.". One approach to studying fire danger is to use fire weather indices that are commonly used to quantify meteorological conditions that can lead to fire ignition and spread. This study aims to provide high-resolution (~ 6 km) future projections of the Fire Weather Index (FWI) for Portugal using the Weather Research and Forecasting (WRF) model, forced by the Max Planck Institute (MPI) model from the CMIP6 suite, under three emission scenarios (SSP2-4.5, SSP3-7.0, and SSP58.5) for the present period (1995–2014) and two future periods (2046–2065 and 2081–2100). The results show good agreement between FWI and its subcomponents from the WRF and reanalysis. The modelled FWI reproduced the climatological distribution of fire danger Projections indicate an increase in days with very high to extreme fire danger (FWI > 38) across all scenarios and time frames, with the southern and northeastern regions experiencing the most significant changes. The southern and northeastern parts of the territory experienced the largest changes, indicating significant changes between the scenarios and regions. This study suggests that FWI and its subcomponents should be investigated further. Our results highlight the importance of creating new adaptation measures, especially in the areas most at risk, prepared in advance by different players and authorities, so that the increasing risk of wildfires can be mitigated in the future.

The Role of Field Measurements of Fine Dead Fuel Moisture Content in the Canadian Fire Weather Index System—A Study Case in the Central Region of Portugal

The Canadian Fire Weather Index System (CFWIS), empirically developed for forests in Canada, estimates the fuel moisture content (mf) at different depths and loads through meteorological parameters. While it is often suggested that adapting an existing fire danger rating system like CFWIS for a new environment requires developing new relationships or modifying existing ones, it is worth considering if such adaptations are always necessary. Based on a dataset of field measurements for surface litter (Pinus pinaster) carried out in the central region of Portugal (2014–2023), we propose a correction of mf based on the Fine Fuel Moisture Code (FFMC) of the CFWIS. This moisture correction was used to determine the Initial Spread Index (ISI) directly and, subsequently, the Fire Weather Index (FWI). Fire records from the study region were used to analyze the performance of the corrected indices. We found that the moisture correction led to higher values and potentially more accurate indices under dry conditions but did not provide a significant improvement in predicting the number of fires and burned areas compared to the original indices. The results suggest that, in relation to fire activity, the CFWIS is sufficiently robust to variations in the fuel moisture content in the study region.

Controlling factors of wildfires in Australia and their changes under global warming

Abstract This study investigates a fire weather index (FWI) and its associated components in Australia using the downscaled projects for the Coupled Model Intercomparison Project phase 6 (CMIP6) dataset, aiming to understand how they respond to global warming, particularly associated with different phases of the El Niño-Southern Oscillation (ENSO). In the historical simulation, multimodel mean composite results show positive anomalies of FWI during El Niño and negative anomalies during La Niña over most of Australia relative to the neutral year. At the end of the 21st century under the Shared Socioeconomic Pathways (SSP585 scenario), FWI anomalies increased across Australia; however, ENSO wildfire teleconnections weakened (-4.4%) during El Niño but strengthened (+6.0%) during La Niña, especially in northern Australia. Further examination of the contribution from individual environmental variables that enter the FWI shows that increased temperature and drought conditions with warming in La Niña strengthen positive FWI anomalies, thus making fire more favorable in north and central Australia. The impacts of relative humidity and wind speed anomaly changes also favor fire activity toward the north. These results suggest a more robust modulation of FWI in northern Australia by ENSO in a warmer climate; future efforts to predict wildfire will depend on the model’s ability to predict local climate conditions.

Investigating FWI Moisture Codes in Relation to Satellite-Derived Soil Moisture Data across Varied Resolutions

In the Mediterranean region, particularly in Antalya, southern Türkiye, rising forest fire risks due to climate change threaten ecosystems, property, and lives. Reduced soil moisture during the growing season is a key factor increasing fire risk by stressing plants and lowering fuel moisture content. This study assessed soil moisture and fuel moisture content (FMC) in ten fires (2019–2021) affecting over 50 hectares. The Fire Weather Index (FWI) and its components (FFMC, DMC, DC) were calculated using data from the General Directorate of Meteorology, EFFIS (8 km), and ERA5 (≈28 km) satellite sources. Relationships between FMCs, satellite-based soil moisture datasets (SMAP, SMOS), and land surface temperature (LST) data (MODIS, Landsat 8) were analyzed. Strong correlations were found between FWI codes and satellite soil moisture, particularly with SMAP. Positive correlations were observed between LST and FWIs, while negative correlations were evident with soil moisture. Statistical models integrating in situ soil moisture and EFFIS FWI (R: −0.86, −0.84, −0.83 for FFMC, DMC, DC) predicted soil moisture levels during extended fire events effectively, with model accuracy assessed through RMSE (0.60–3.64%). The SMAP surface (0–5 cm) dataset yielded a lower RMSE of 0.60–2.08%, aligning with its higher correlation. This study underlines the critical role of soil moisture in comprehensive fire risk assessments and highlights the necessity of incorporating modeled soil moisture data in fire management strategies, particularly in regions lacking comprehensive in situ monitoring.

Impacts of fire prevention strategies in a changing climate: an assessment for Portugal

Abstract Climate change poses a formidable strain on societies worldwide, demanding viable and timely adaptation measures to ensure future prosperity while avoiding the impact of more frequent and intense extreme events, like wildfires, that affect all continents and biomes, leaving authorities grappling to respond effectively. Here, we focus on mainland Portugal that is inserted in the Mediterranean climate change hotspot and investigate the impact of different adaptation strategies on wildfire risk. Relying on an ensemble of regional climate models from the EURO-CORDEX initiative, we project Fire Weather Index (FWI) and Fire Radiative Power (FRP) for various Representative Concentration Pathways (RCPs).
Our findings reveal that very energetic fires, with energy release exceeding 1000 MW, may increase up to more than three-fold, depending on the RCP. Even under strong mitigation scenarios, the likelihood of having megafires increases by 1.5-fold. This underscores the need for proactive adaptation regardless of mitigation efforts.
We present three different ignition avoidance strategies under different climate change scenarios. For all cases results indicate that a reduction between 20 and 60% is achievable for intense wildfires (above 1000 MW).

The fire weather in Europe: large-scale trends towards higher danger

Abstract The climate over Europe has been recorded to be hotter, drier, and more fire-prone over the last decade than ever before, leading to concerns about how climate change will alter fire weather in the future. A typical measure to estimate fire weather severity based on climate is the Canadian fire weather index (FWI). In this study, we used high-resolution, bias-corrected climate model output (∼9 km) from six CMIP6 climate models and four shared socio-economic pathway projections (SSPs) to calculate consistent and comparable daily FWI datasets for Europe from 1950 to 2080. Our study aims to identify regional and large-scale shifts in fire weather severity and its predictability over time to support adaptive planning. We show that irrespective of the future SSP, fire weather will become more severe, but the increase is much stronger under high greenhouse gas emissions. This leads to new areas being exposed to severe fire weather, such as central Europe and rapidly warming mountainous areas. Already fire-prone regions in southern Europe will experience more extreme conditions. We conclude that only the low-emission SSP1-2.6 pathway can prevent strong increases in fire weather beyond the 2050s. Fire surveillance and management will become more important, even in areas and in seasons where they have not been in the focus so far.

Differences in the intensity of past forest fire events inferred from stable oxygen isotope analysis of charred bark

Understanding past fire regimes requires reliable proxy data that record fire conditions and preserve them over time. The objective of this study was to determine if the oxygen isotope composition of charred bark samples (pyrogenic organic matter) could be used as proxy data to differentiate wildfires based on burn intensity. We collected charred and uncharred bark samples from three fire sites in northern Ontario, Canada that represented a gradient of fire intensity as depicted by Fire Weather Index (FWI) data. We hypothesized that the mean Δ18Obark-char (the difference between δ18O of uncharred bark and a charred sample) would be greater for fires with higher intensities. Analysis of variance of Δ18Obark-char indicated a significant effect of fire event ( F = 73.6, p < 0.001), which explained 57.0% of the variance. A prescribed surface fire treatment (mean FWI = 9.5) had significantly lower Δ18Obark-char than two natural crown fires (FWI = 21 and 27). These results demonstrate that Δ18Obark-char differentiated moderate from high intensity fires in a similar manner to the FWI data.

Multiscale Interactions between Local Short- and Long-Term Spatio-Temporal Mechanisms and Their Impact on California Wildfire Dynamics

California has experienced a surge in wildfires, prompting research into contributing factors, including weather and climate conditions. This study investigates the complex, multiscale interactions between large-scale climate patterns, such as the Boreal Summer Intraseasonal Oscillation (BSISO), El Niño Southern Oscillation (ENSO), and the Pacific Decadal Oscillation (PDO) and their influence on moisture and temperature fluctuations, and wildfire dynamics in California. The combined impacts of PDO and BSISO on intraseasonal fire weather changes; the interplay between fire weather index (FWI), relative humidity, vapor pressure deficit (VPD), and temperature in assessing wildfire risks; and geographical variations in the relationship between the FWI and climatic factors within California are examined. The study employs a multi-pronged approach, analyzing wildfire frequency and burned areas alongside climate patterns and atmospheric conditions. The findings reveal significant variability in wildfire activity across different climate conditions, with heightened risks during specific BSISO phases, La-Niña, and cool PDO. The influence of BSISO varies depending on its interaction with PDO. Temperature, relative humidity, and VPD show strong predictive significance for wildfire risks, with significant relationships between FWI and temperature in elevated regions (correlation, r > 0.7, p ≤ 0.05) and FWI and relative humidity along the Sierra Nevada Mountains (r ≤ −0.7, p ≤ 0.05).

The Interannual Variability of Global Burned Area Is Mostly Explained by Climatic Drivers

AbstractBetter understanding how fires respond to climate variability is an issue of current interest in light of ongoing climate change. However, evaluating the global‐scale temporal variability of fires in response to climate presents a challenge due to the intricate processes at play and the limitation of fire data. Here, we investigate the links between year‐to‐year variability of burned area (BA) and climate using BA data, the Fire Weather Index (FWI), and the Standardized Precipitation Evapotranspiration Index (SPEI) from 2001 to 2021 at ecoregion scales. Our results reveal complex spatial patterns in the dependence of BA variability on antecedent and concurrent weather conditions, highlighting where BA is mostly influenced by either FWI or SPEI and where the combined effect of both indicators must be considered. Our findings indicate that same‐season weather conditions have a more pronounced relationship with BA across various ecoregions, particularly in climatologically wetter areas. Additionally, we note that BA is also significantly associated with periods of antecedent wetness and coolness, with this association being especially evident in more arid ecoregions. About 60% of the interannual variations in BA can be explained by climatic variability in a large fraction (∼77%) of the world's burnable regions.

Forecasting Hourly Wildfire Risk: Enhancing Fire Danger Assessment Using Numerical Weather Prediction

Abstract Wildfire agencies use fire danger rating systems (FDRSs) to deploy resources and issue public safety measures. The most widely used FDRS is the Canadian fire weather index (FWI) system, which uses weather inputs to estimate the potential for wildfires to start and spread. Current FWI forecasts provide a daily numerical value, representing potential fire severity at an assumed midafternoon time for peak fire activity. This assumption, based on typical diurnal weather patterns, is not always valid. To address this, we developed an hourly FWI (HFWI) system using numerical weather prediction. We validate HFWI against the traditional daily FWI (DFWI) by comparing HFWI forecasts with observation-derived DFWI values from 917 surface fire weather stations in western North America. Results indicate strong correlations between forecasted HFWI and the observation-derived DFWI. A positive mean bias in the daily maximum values of HFWI compared to the traditional DFWI suggests that HFWI can better capture severe fire weather variations regardless of when they occur. We confirm this by comparing HFWI with hourly fire radiative power (FRP) satellite observations for nine wildfire case studies in Canada and the United States. We demonstrate HFWI’s ability to forecast shifts in fire danger timing, especially during intensified fire activity in the late evening and early morning hours, while allowing for multiple periods of increased fire danger per day—a contrast to the conventional DFWI. This research highlights the HFWI system’s value in improving fire danger assessments and predictions, hopefully enhancing wildfire management, especially during atypical fire behavior.

A perspective and survey on the implementation and uptake of tools to support decision-making in Canadian wildland fire management

The level of implementation and uptake of specific tools used to support wildland fire management decision-making has received little attention in Canada. Our aim is to aid the fire research-to-practice discourse in Canada by describing key terms and concepts for characterizing implementation, uptake, and capacity. We also designed and conducted a survey to assess the implementation and uptake of some of the available tools used by Canadian provincial and territorial fire management agencies. We assessed nine tools and found distinct differences in their implementation and uptake, with differing results at national versus provincial and territorial scale. The Canadian Fire Weather Index and Fire Behaviour Prediction Systems had the highest level of both implementation and uptake nationally. The other tools have substantially lower but varying degrees of implementation and uptake across the country. The results encourage further investigation into the factors affecting implementation and uptake of fire management tools, both nationally and in provinces and territories.

Global variation in ecoregion flammability thresholds

Anthropogenic climate change is altering the state of worldwide fire regimes, including by increasing the number of days per year when vegetation is dry enough to burn. Indices representing the percent moisture content of dead fine fuels as derived from meteorological data have been used to assess geographic patterns and temporal trends in vegetation flammability. To date, this approach has assumed a single flammability threshold, typically between 8 and 12%, controlling fire potential regardless of the vegetation type or climate domain. Here we use remotely sensed burnt area products and a common fire weather index calculated from global meteorological reanalysis data to identify and describe geographic variation in fuel moisture as a flammability threshold. This geospatial analysis identified a wide range of flammability thresholds associated with fire activity across 772 ecoregions, often well above or below the commonly used range of values. Many boreal and temperate forests, for example, can ignite and sustain wildfires with higher estimated fuel moisture than previously identified; Mediterranean forests, in contrast, tend to sustain fires with consistently low estimated fuel moisture. Statistical modelling showed that flammability thresholds derived from burnt area are primarily driven by climatological variables, particularly precipitation and temperature. Our analysis also identified complex associations between vegetation structure, fuel types, and climatic conditions highlighting the complexity in vegetation–climate–fire relationships globally. Our study provides a critical, necessary step in understanding and describing global pyrogeography and tracking changes in spatial and temporal fire activity.

Factors affecting severity of wildfires in Scottish heathlands and blanket bogs

Temperate heathlands and blanket bogs are globally rare and face growing wildfire threats. Ecosystem impacts differ between low and high severity fires, where severity reflects immediate fuel consumption. This study assessed factors influencing fire severity in Scottish heathlands and blanket bogs, including the efficacy of the Canadian Fire Weather Index System (CFWIS). Using remote sensing, we measured the differenced Normalised Burn Ratio at 92 wildfire sites from 2015 to 2021. We used Generalised Additive Mixed Models to investigate the impact of topography, habitat wetness, CFWIS components and 30-day weather on severity. Dry heath exhibited higher severity than wet heath and blanket bog, and slope, elevation and south facing aspect were positively correlated to severity. Weather effects were less clear due to data scale differences, yet still indicated weather's significant role in severity. Rainfall had an increasingly negative effect from approximately 15 days before the fire, whilst temperature had an increasingly positive effect. Vapour Pressure Deficit (VPD) was the weather variable with highest explanatory value, and predicted severity better than any CFWIS component. The best-explained fire severity model (R2 = 0.25) incorporated topography, habitat wetness wind and VPD on the day of the fire. The Drought Code (DC), predicting organic matter flammability at ≥10 cm soil depth, was the CFWIS component with the highest predictive effect across habitats. Our findings suggest that wildfires in wet heath and blanket bogs are typically characterised by low severity, but that warmer, drier weather may increase the risk of severe, smouldering fires which threaten peatland carbon stores.

Deep Learning-Based Forest Fire Risk Research on Monitoring and Early Warning Algorithms

With the development of image processing technology and video analysis technology, forest fire monitoring technology based on video recognition is more and more important in the field of forest fire prevention and control. The objects currently applied to forest fire video image monitoring system monitoring are mainly flames and smoke. This paper proposes a forest fire risk monitoring and early warning algorithm, which integrates a deep learning model, infrared monitoring and early warning, and forest fire weather index. The algorithm first obtains the current visible image and infrared image of the same forest area, utilizing a smoke detection model based on deep learning to detect smoke in the visible image, and obtains the confidence level of the occurrence of fire in said visible image. Then, it determines whether the local temperature value of said infrared image exceeds a preset warning value, and obtains a judgment result based on the infrared image. It calculates again a current FWI based on environmental data, and determines a current fire danger level based on the current FWI. Finally, it determines whether or not to carry out a fire warning based on said fire danger level, said confidence level of the occurrence of fire in said visible image, and said judgment result based on the infrared image. The experimental results show that the accuracy of the algorithm in this paper reaches 94.12%, precision is 96.1%, recall is 93.67, and F1-score is 94.87. The algorithm in this paper can improve the accuracy of smoke identification at the early stage of forest fire danger occurrence, especially by excluding the interference caused by clouds, fog, dust, and so on, thus improving the fire danger warning accuracy.