A stochastic model for time series prediction of the number of post-earthquake fire ignitions in buildings based on the ignition record for the 2011 Tohoku Earthquake

Nishino, Taneo; Hokugo, Akihiko

doi:10.1177/8755293019878184

Cited by 9 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Himoto [2] found a similar pattern between two major earthquake events in Japan (1995 Kobe and 2011 Tōhoku earthquakes), in which approximately 70% of ignitions occurred within the first 24 hours and the remaining 30% were spread across the following 9 days. Ignitions across a 21-day period following the 2011 Tōhoku earthquake were evaluated by Nishino and Hokugo [8],…”

Section: Ignitionmentioning

confidence: 99%

Estimating fire following earthquake risk for Wellington City, New Zealand

Scheele

Luković

Moratalla

et al. 2022

BNZSEE

View full text Add to dashboard Cite

Fire following earthquake (FFE) is a significant hazard in urban areas subject to high seismicity. Wellington City has many characteristics that make it susceptible to ignitions and fire spread. These include proximity to major active faults, closely spaced timber-clad buildings, vulnerable water and gas infrastructure, frequent high winds and challenging access for emergency services. We modelled the ignitions, fire spread and suppression for five earthquake sources. Uncertainty in ground motions, the number and location of ignitions, weather conditions and firefighting capacity were accounted for. The mean loss per burn zone (area burnt due to ignition and fire spread) is $46m without fire suppression, indicating the potential property damage avoided by controlling the fire spread. The mean total loss for earthquake scenarios ranges from $0.28b for the Wairau Fault through to $3.17b for a Hikurangi Subduction Zone scenario, including the influence of fire suppression. Wind speed has a strong influence on the potential losses for each simulation and is a more significant factor than the number of ignitions for evaluating losses. Areas in Wellington City of relatively high risk are identified, which may inform risk mitigation strategies. The models may be applied to other urban areas.

show abstract

Section: Ignitionmentioning

confidence: 99%

Estimating fire following earthquake risk for Wellington City, New Zealand

Scheele

Luković

Moratalla

et al. 2022

BNZSEE

View full text Add to dashboard Cite

show abstract

“…[1][2][3] The Emergency Operations Center wants to use SSA drones and hovering drones carrying repeaters to better obtain front line data feedback, so as to provide the best forest fire response plan in terms of capacity, economy and safety. [4][5]…”

Section: Introduction 11 Problem Backgroundmentioning

confidence: 99%

A multi-objective programming model that can monitor and feedback front line fires data based on UAV cruising

Guo,

Lv,

Cheng

et al. 2024

Fourth International Conference on Geology, Mapping, and Remote Sensing (ICGMRS 2023)

View full text Add to dashboard Cite

The wildfires that have raged across Australia for over three months have left an indelible impact on every state. In response, we have developed a multi-objective planning model and a fire monitoring model that are suitable for SSA (sub-Saharan Africa) unmanned aerial vehicles. These models provide assurance for fire prevention and timely understanding of fire front issues while also ensuring cost control.

show abstract

A multi-resolution physics-informed recurrent neural network: formulation and application to musculoskeletal systems

Taneja,

He,

et al. 2023

Comput Mech

View full text Add to dashboard Cite

This work presents a multi-resolution physics-informed recurrent neural network (MR PI-RNN), for simultaneous prediction of musculoskeletal (MSK) motion and parameter identification of the MSK systems. The MSK application was selected as the model problem due to its challenging nature in mapping the high-frequency surface electromyography (sEMG) signals to the low-frequency body joint motion controlled by the MSK and muscle contraction dynamics. The proposed method utilizes the fast wavelet transform to decompose the mixed frequency input sEMG and output joint motion signals into nested multi-resolution signals. The prediction model is subsequently trained on coarser-scale input–output signals using a gated recurrent unit (GRU), and then the trained parameters are transferred to the next level of training with finer-scale signals. These training processes are repeated recursively under a transfer-learning fashion until the full-scale training (i.e., with unfiltered signals) is achieved, while satisfying the underlying dynamic equilibrium. Numerical examples on recorded subject data demonstrate the effectiveness of the proposed framework in generating a physics-informed forward-dynamics surrogate, which yields higher accuracy in motion predictions of elbow flexion–extension of an MSK system compared to the case with single-scale training. The framework is also capable of identifying muscle parameters that are physiologically consistent with the subject’s kinematics data.

show abstract

A stochastic model for time series prediction of the number of post-earthquake fire ignitions in buildings based on the ignition record for the 2011 Tohoku Earthquake

Cited by 9 publications

References 14 publications

Estimating fire following earthquake risk for Wellington City, New Zealand

Estimating fire following earthquake risk for Wellington City, New Zealand

A multi-objective programming model that can monitor and feedback front line fires data based on UAV cruising

A multi-resolution physics-informed recurrent neural network: formulation and application to musculoskeletal systems

Contact Info

Product

Resources

About