scholarly journals A Physics-Guided Deep Learning Model for 10-h Dead Fuel Moisture Content Estimation

Forests ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 933
Author(s):  
Chunquan Fan ◽  
Binbin He
Keyword(s):  
Deep Learning ◽  
Moisture Content ◽  
Short Term Memory ◽  
Simulation Models ◽  
Fuel Moisture ◽  
Site Characteristics ◽  
Important Input ◽  
Lstm Network ◽  
Fuel Moisture Content ◽  
Process Based Models

Dead fuel moisture content (DFMC) is a key driver for fire occurrence and is often an important input to many fire simulation models. There are two main approaches to estimating DFMC: empirical and process-based models. The former mainly relies on empirical methods to build relationships between the input drivers (weather, fuel and site characteristics) and observed DFMC. The latter attempts to simulate the processes that occur in the fuel with energy and water balance conservation equations. However, empirical models lack explanations for physical processes, and process-based models may provide an incomplete representation of DFMC. To combine the benefits of empirical and process-based models, here we introduced the Long Short-Term Memory (LSTM) network and its combination with an effective physics process-based model fuel stick moisture model (FSMM) to estimate DFMC. The LSTM network showed its powerful ability in describing the temporal dynamic changes of DFMC with high R2 (0.91), low RMSE (3.24%) and MAE (1.97%). When combined with a FSMM model, the physics-guided model FSMM-LSTM showed betterperformance (R2 = 0.96, RMSE = 2.21% and MAE = 1.41%) compared with the other models. Therefore, the combination of the physics process and deep learning estimated 10-h DFMC more accurately, allowing the improvement of wildfire risk assessments and fire simulating.

Soil Moisture and Live Fuel Moisture Content as key remote sensing variables to unlock improved wildfire predictions

2021 ◽  
Author(s):  
Florian Briquemont ◽  
Akli Benali
Keyword(s):  
Soil Moisture ◽  
Moisture Content ◽  
Fire Risk ◽  
Simulation Models ◽  
Fire Spread ◽  
Fuel Moisture ◽  
Live Fuel Moisture ◽  
Risk Maps ◽  
Fuel Moisture Content ◽  
The Impact

<p>Large wildfires are amongst the most destructive natural disasters in southern Europe, posing a serious threat to both human lives and the environment.</p><p>Although wildfire simulations and fire risk maps are already very a useful tool to assist fire managers in their decisions, the complexity of fire spread and ignition mechanisms can greatly hinder their accuracy. An important step in improving the reliability of wildfire prediction systems is to implement additional drivers of fire spread and fire risk in simulation models.</p><p>Despite their recognized importance as factors influencing fuel flammability and fire spread, soil moisture and live fuel moisture content are rarely implemented in the simulation of large wildfires due to the lack of sufficient and accurate data. Fortunately, new satellite products are giving the opportunity to assess these parameters on large areas with high temporal and spatial resolution.</p><p>The purpose of this study is twofold. First, we aimed to evaluate the capabilities of satellite data to estimate soil moisture and live fuel moisture content in different landcovers.  Secondly, we focused on the potential of these estimates for assessing fire risk and fire spread patterns of large wildfires in Portugal. Ultimately, the goal of this study is to implement these estimated variables in fire spread simulations and fire risk maps.<br><br>We compared datasets retrieved from Sentinel 1, SMAP (Soil Moisture Active Passive radiometer) and MODIS (Moderate Resolution Imaging Spectrometer) missions. Several estimators of LFMC based on spectral indices were tested and their patterns were compared with field data. Based on these estimators, we assessed the impact of LFMC and soil moisture on the extent and occurrence of large wildfires. Finally, we built a database of detailed historical wildfire progressions, which we used to evaluate the influence of soil moisture and LFMC on the velocity and direction of the fire spread.</p>

Live fuel moisture content estimation from MODIS: A deep learning approach

2021 ◽  
Vol 179 ◽  
pp. 81-91
Author(s):  
Liujun Zhu ◽  
Geoffrey I. Webb ◽  
Marta Yebra ◽  
Gianluca Scortechini ◽  
Lynn Miller ◽  
...  
Keyword(s):  
Deep Learning ◽  
Moisture Content ◽  
Learning Approach ◽  
Fuel Moisture ◽  
Live Fuel Moisture ◽  
Fuel Moisture Content

scholarly journals Real-Time Detection of Dictionary DGA Network Traffic Using Deep Learning

2021 ◽  
Vol 2 (2) ◽  
Author(s):  
Kate Highnam ◽  
Domenic Puzio ◽  
Song Luo ◽  
Nicholas R. Jennings
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Traffic ◽  
Short Term Memory ◽  
Domain Names ◽  
Control Networks ◽  
Detection Techniques ◽  
Lstm Network ◽  
And Control

AbstractBotnets and malware continue to avoid detection by static rule engines when using domain generation algorithms (DGAs) for callouts to unique, dynamically generated web addresses. Common DGA detection techniques fail to reliably detect DGA variants that combine random dictionary words to create domain names that closely mirror legitimate domains. To combat this, we created a novel hybrid neural network, Bilbo the “bagging” model, that analyses domains and scores the likelihood they are generated by such algorithms and therefore are potentially malicious. Bilbo is the first parallel usage of a convolutional neural network (CNN) and a long short-term memory (LSTM) network for DGA detection. Our unique architecture is found to be the most consistent in performance in terms of AUC, $$F_1$$ F 1 score, and accuracy when generalising across different dictionary DGA classification tasks compared to current state-of-the-art deep learning architectures. We validate using reverse-engineered dictionary DGA domains and detail our real-time implementation strategy for scoring real-world network logs within a large enterprise. In 4 h of actual network traffic, the model discovered at least five potential command-and-control networks that commercial vendor tools did not flag.

Predicting 1-H Dead Fuel Moisture Content at Regional Scales Using Machine Learning from Himawari-8 Data

2021 ◽  
Author(s):  
Chunquan Fan ◽  
Binbin He ◽  
Peng Kong ◽  
Hao Xu ◽  
Qiang Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Moisture Content ◽  
Fuel Moisture ◽  
Fuel Moisture Content

scholarly journals Detection of dementia on raw voice recordings using deep learning: A Framingham Heart Study

2021 ◽  
Author(s):  
Chonghua Xue ◽  
Cody Karjadi ◽  
Ioannis Ch. Paschalidis ◽  
Rhoda Au ◽  
Vijaya B. Kolachalama
Keyword(s):  
Deep Learning ◽  
Framingham Heart Study ◽  
Short Term Memory ◽  
Neuropsychological Testing ◽  
Heart Study ◽  
Audio Recordings ◽  
Lstm Network ◽  
Sensitivity Specificity ◽  
Normal Cognition ◽  
Mean Sensitivity

AbstractBackgroundIdentification of reliable, affordable and easy-to-use strategies for detection of dementia are sorely needed. Digital technologies, such as individual voice recordings, offer an attractive modality to assess cognition but methods that could automatically analyze such data without any pre-processing are not readily available.MethodsWe used a subset of 1264 digital voice recordings of neuropsychological examinations administered to participants from the Framingham Heart Study (FHS), a community-based longitudinal observational study. The recordings were 73 minutes in duration, on average, and contained at least two speakers (participant and clinician). Of the total voice recordings, 483 were of participants with normal cognition (NC), 451 recordings were of participants with mild cognitive impairment (MCI), and 330 were of participants with dementia. We developed two deep learning models (a two-level long short-term memory (LSTM) network and a convolutional neural network (CNN)), which used the raw audio recordings to classify if the recording included a participant with only NC or only dementia, and also to differentiate between recordings corresponding to non-demented (NC+MCI) and demented participants.FindingsBased on 5-fold cross-validation, the LSTM model achieved a mean (±std) area under the sensitivity-specificity curve (AUC) of 0.744±0.038, mean accuracy of 0.680±0.032, mean sensitivity of 0.719±0.112, and mean specificity of 0.652±0.089 in predicting cases with dementia from those with normal cognition. The CNN model achieved a mean AUC of 0.805±0.027, mean accuracy of 0.740±0.033, mean sensitivity of 0.735±0.094, and mean specificity of 0.750±0.083 in predicting cases with only dementia from those with only NC. For the task related to classification of demented participants from non-demented ones, the LSTM model achieved a mean AUC of 0.659±0.043, mean accuracy of 0.701±0.057, mean sensitivity of 0.245±0.161 and mean specificity of 0.856±0.105. The CNN model achieved a mean AUC of 0.730±0.039, mean accuracy of 0.735±0.046, mean sensitivity of 0.443±0.113, and mean specificity of 0.840±0.076 in predicting cases with dementia from those who were not demented.InterpretationThis proof-of-concept study demonstrates the potential that raw audio recordings of neuropsychological testing performed on individuals recruited within a community cohort setting can provide a level of screening for dementia.

scholarly journals Evaluating the Effects of Projected Climate Change on Forest Fuel Moisture Content

2014 ◽  
Vol 37 ◽  
pp. 65-69
Author(s):  
Kellen Nelson ◽  
Daniel Tinker
Keyword(s):  
Climate Change ◽  
Moisture Content ◽  
Stand Structure ◽  
Canopy Cover ◽  
Fire Season ◽  
Climate Change Scenarios ◽  
Fuel Moisture ◽  
Mature Forest ◽  
Forest Fuel ◽  
Fuel Moisture Content

Understanding how live and dead forest fuel moisture content (FMC) varies with seasonal weather and stand structure will improve researchers’ and forest managers’ ability to predict the cumulative effects of weather on fuel drying during the fire season and help identify acute conditions that foster wildfire ignition and high rates of fire spread. No studies have investigated the efficacy of predicting FMC using mechanistic water budget models at daily time scales through the fire season nor have they investigated how FMC may vary across space. This study addresses these gaps by (1) validating a novel mechanistic live FMC model and (2) applying this model with an existing dead FMC model at three forest sites using five climate change scenarios to characterize how FMC changes through time and across space. Sites include post-fire 24-year old forest, mature forest with high canopy cover, and mature forest affected by the mountain pine beetle with moderate canopy cover. Climate scenarios include central tendency, warm/dry, warm/wet, hot/dry, and hot/wet.

Effects of distribution of bulk density and moisture content on shrub fires

2013 ◽  
Vol 22 (5) ◽  
pp. 625 ◽  
Author(s):  
Ambarish Dahale ◽  
Selina Ferguson ◽  
Babak Shotorban ◽  
Shankar Mahalingam
Keyword(s):  
Moisture Content ◽  
Spatial Variation ◽  
Bulk Density ◽  
Solid Fuel ◽  
Numerical Solutions ◽  
Propagation Speed ◽  
Fire Spread ◽  
Fuel Moisture ◽  
Combustion Heat ◽  
Fuel Moisture Content

Formulation of a physics-based model, capable of predicting fire spread through a single elevated crown-like shrub, is described in detail. Predictions from the model, obtained by numerical solutions to governing equations of fluid dynamics, combustion, heat transfer and thermal degradation of solid fuel, are found to be in fairly good agreement with experimental results. In this study we utilise the physics-based model to explore the importance of two parameters – the spatial variation of solid fuel bulk density and the solid fuel moisture content – on the burning of an isolated shrub in quiescent atmosphere. The results suggest that vertical fire spread rate within an isolated shrub and the time to initiate ignition within the crown are two global parameters significantly affected when the spatial variation of the bulk density or the variation of fuel moisture content is taken into account. The amount of fuel burnt is another parameter affected by varying fuel moisture content, especially in the cases of fire propagating through solid fuel with moisture content exceeding 40%. The specific mechanisms responsible for the reduction in propagation speed in the presence of higher bulk densities and moisture content are identified.

Modelling fine fuel moisture content and the likelihood of fire spread in blue gum (Eucalyptus globulus) litter

2014 ◽  
pp. 353-359
Author(s):  
Anita Pinto ◽  
Juncal Espinosa-Prieto ◽  
Carlos Rossa ◽  
Stuart Matthews ◽  
Carlos Loureiro ◽  
...  
Keyword(s):  
Moisture Content ◽  
Eucalyptus Globulus ◽  
Fire Spread ◽  
Fuel Moisture ◽  
Fuel Moisture Content ◽  
Blue Gum
Sign in / Sign up

Export Citation Format

Share Document