Predictive analysis of fire frequency based on daily temperatures

Liu, Dingli; Xu, Zhisheng; Fan, Chuangang

doi:10.1007/s11069-019-03694-1

Cited by 18 publications

(7 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A 2-5 day time lag in indoor RH was observed after a step change to cold weather, i.e., corresponding to the drying of the internal wooden wall materials. A similar time lag in fire frequency versus ambient low temperatures was also recently found for cold climate urban fire frequency in China [9].…”

Section: Introductionsupporting

confidence: 82%

Reducing Wooden Structure and Wildland-Urban Interface Fire Disaster Risk through Dynamic Risk Assessment and Management

Log

Vandvik

Velle

et al. 2020

ASI

View full text Add to dashboard Cite

In recent years, severe and deadly wildland-urban interface (WUI) fires have resulted in an increased focus on this particular risk to humans and property, especially in Canada, USA, Australia, and countries in the Mediterranean area. Also, in areas not previously accustomed to wildfires, such as boreal areas in Sweden, Norway, and in the Arctic, WUI fires have recently resulted in increasing concern. January 2014, the most severe wooden town fire in Norway since 1923 raged through Laerdalsøyri. Ten days later, a wildfire raged through the scattered populated community of Flatanger and destroyed even more structures. These fires came as a surprise to the fire brigades and the public. We describe and analyze a proposed way forward for exploring if and how this increasing fire incidence can be linked to concomitant changes in climate, land-use, and habitat management; and then aim at developing new dynamic adaptive fire risk assessment and management tools. We use coastal Norway as an example and focus on temporal changes in fire risk in wooden structure settlements and in the Norwegian Calluna vulgaris L. dominated WUI. In this interface, the fire risk is now increasing due to a combination of land-use changes, resulting in large areas of early successional vegetation with an accumulation of biomass, and the interactive effects of climatic changes resulting in increased drought risk. We propose a novel bow-tie framework to explore fire risk and preventive measures at various timescales (years, months, weeks, hours) as a conceptual model for exploring risk contributing factors and possibilities for risk management. Ignition is the top event of the bow-tie which has the potential development towards a fire disaster as a worst case outcome. The bow-tie framework includes factors such as changes in the built environment and natural habitat fuel moisture content due to the weather conditions, WUI fuel accumulation, possibly improved ecosystem management, contribution by civic prescribed burner groups, relevant fire risk modeling, and risk communication to the fire brigades and the public. We propose an interdisciplinary research agenda for developing this framework and improving the current risk understanding, risk communication, and risk management. This research agenda will represent important contributions in paving the road for fire disaster prevention in Norway, and may provide a model for other systems and regions.

show abstract

Section: Introductionsupporting

confidence: 82%

Reducing Wooden Structure and Wildland-Urban Interface Fire Disaster Risk through Dynamic Risk Assessment and Management

Log

Vandvik

Velle

et al. 2020

ASI

View full text Add to dashboard Cite

show abstract

“…Weighted least squares polynomial fitting is used to generate meaningful extreme possibility results for decisionmaking reference, and it can be used to obtain the relationship between the context index (SI) and the outcome index (CI) of high-level and extreme HCFs. To investigate the impact of temperature on the frequency of fires in Changsha, Liu Dingli et al [17] collected and processed 20,622 fire data as well as historical weather data in Changsha. Data mining reveals that the average daily fire frequency is lowest in the temperature range of 20 °C and 25 °C, which is likely due to the low power utilization rate.…”

Section: Polynomial Fittingmentioning

confidence: 99%

ARIMA Model-Based Fire Rescue Prediction

Zhang¹,

Zhou²,

Weng³

et al. 2021

Scientific Programming

View full text Add to dashboard Cite

In recent years, urban buildings have become taller, occupying more and more areas, frequent fires, and increasingly difficult fire rescue tasks. Predicting fire risks in advance will help fire rescue work. Therefore, this paper proposes a fire risk prediction based on the ARIMA model. By analyzing the fire rescue data of a certain place from 2016 to 2020 and based on the data from January 1, 2016, to December 31, 2019, an ARIMA model for predicting the number of fire rescue polices was established. The data from January 1, 2020, to December 31, 2020, are used as the validation data set of the model to evaluate the accuracy and stability of the model. The results show that the ARIMA model can be better applied to fire rescue prediction and provides a scientific prediction method for the research of smart fire rescue work.

show abstract

“…The degree of linearity is evaluated using the coefficient of determination, while the error term accounts for the variation or the difference between the predicted and actual variables. To ascertain the suitability of conducting MLR on a specific dataset, various tests such as the linearity, normality, missing value test and extreme value test are conducted [28,29].…”

Section: Multiple Linear Regression (Mlr)mentioning

confidence: 99%

Application of Adaptive Neuro-Fuzzy Inference System in Flammability Parameter Prediction

et al. 2020

View full text Add to dashboard Cite

The fire behavior of materials is usually modeled on the basis of fire physics and material composition. However, significant strides have been made recently in applying soft computing methods such as artificial intelligence in flammability studies. In this paper, multiple linear regression (MLR) was employed to test the degree of non-linearities in flammability parameter modeling by assessing the linear relationship between sample mass, heating rate, heat release capacity (HRC) and total heat release (THR). Adaptive neuro-fuzzy inference system (ANFIS) was then adopted to predict the HRC and THR of the extruded polystyrene measured from microscale combustion calorimetry experiments. The ANFIS models presented excellent predictions, showing very low mean training and testing errors as well as reasonable agreements between experimental and predicted datasets. Hence, it can be inferred that ANFIS can handle the non-linearities in flammability modeling, making it apt as a modeling technique for accurate and effective flammability assessments.Several chemistry-based models, such as inverse modeling, quantitative structure-property relationship (QSPR), quantitative structure-activity relationship (QSAR) and additive molar group contribution methods, have been developed over the years to estimate these important fire safety parameters (HRC and THR). Although effective, some disadvantages, like large prediction errors, have been identified in the traditional modeling approaches and need to be addressed.Until now, correlation analysis and statistical prediction models have been appropriate analytical tools in material flammability [11]. The significance of the prediction models lies in the employment of robust techniques and strategies for the accurate estimation of flammability parameters, whereas correlation analysis assesses the relationship between the predicted or measured parameters. Statistical analysis is mostly empirical, devoid of the chemical compositions and physical structure of the material under consideration [12]. It is imperative to note that fire experiments are demanding, expensive and time consuming. Similarly, traditional flammability parameter predictions involve sophisticated fire modeling and calibration, requiring a great deal of expertise and computing power. It is, therefore, quite convenient for researchers to opt for these system theoretical models as opposed to conceptual models. Statistical models in recent times largely embrace the artificial neural network (ANN) due to its ability to capture complex nonlinearities in a system when compared to linear regression methods. ANN mimics the operation of the human brain by processing information available to the input layers to achieve a desirable output.Generalized regression and the ANN's feed-forward back propagation methods have been applied in flammability studies to predict peak heat release rate, heat release capacity, total heat released, etc., with a high level of accuracy [13,14]. Deviation of the predicted results from the actual or ex...

show abstract

Predictive analysis of fire frequency based on daily temperatures

Cited by 18 publications

References 40 publications

Reducing Wooden Structure and Wildland-Urban Interface Fire Disaster Risk through Dynamic Risk Assessment and Management

Reducing Wooden Structure and Wildland-Urban Interface Fire Disaster Risk through Dynamic Risk Assessment and Management

ARIMA Model-Based Fire Rescue Prediction

Application of Adaptive Neuro-Fuzzy Inference System in Flammability Parameter Prediction

Contact Info

Product

Resources

About