Estimation of fire potential index in mountainous protected region using remote sensing

Adelabu, Samuel; Mofokeng, Olga D.

doi:10.1080/10106049.2018.1499818

Cited by 20 publications

(10 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adaptive governance at multiple scales with the help of aggressive data processing and involving all the stakeholders is the key to success in mitigating the effect and hazards of the wildfire [171]. In this regards, good papers the readers can read include [172][173][174][175][176][177]. Big data measurement and analysis related to fire occurrences and prediction of fire events require a more significant framework incorporating the government and communities living nearby fire-prone areas to increase wildfire resilience.…”

Section: Prediction Of Propagation Of Firementioning

confidence: 99%

Role of Machine Learning Algorithms in Forest Fire Management: A Literature Review

Arif¹,

K²,

A³

et al. 2021

J Robotics Autom

View full text Add to dashboard Cite

Forest fire disasters are recently getting lots of attention due to climate change globally. Globally, climate changes are rapidly changing the fire patterns on Earth. Effective fire management requires accurate information about the fire occurrence, its spread, and impact on the environment. Prediction of fire activities in the forest guides the authorities to make optimal, efficient, and sound decisions in fire management. This paper aims to summarize recent trends in the forest fire events prediction, detection, spread rate, and mapping of the burned areas. Furthermore, fire emissions in terms of smoke also put the Earth's public health and ecological system at greater risk. Hence, future policymaking can be more accurate in saving billions of dollars, improving the healthy environment and ecological cycle for the inhabitants of this Earth. This paper provides a comprehensive review of the usage of different machine learning algorithms in forest fire or wildfire management. Furthermore, we have identified some potential areas where new technologies and data can help better fire management decision making.

show abstract

Section: Prediction Of Propagation Of Firementioning

confidence: 99%

Role of Machine Learning Algorithms in Forest Fire Management: A Literature Review

Arif¹,

K²,

A³

et al. 2021

J Robotics Autom

View full text Add to dashboard Cite

show abstract

“…The main factors that determine forest fire risk include the moisture content of fuel and weather conditions, in which the moisture content of fuel is affected by vegetation growth, soil moisture, temperature, and other factors. At present, the forest fire risk index of early warning mountain fire is widely used, including fire weather index (FWI) [16], FSI [17] and fire potential index (FPI) [18]. Forest fire index is usually evaluated by meteorological information and optical image information, and it has certain limitations in the case of complex terrain and meteorology.…”

Section: The Mountain Fires Early Warning Model Based On Mecmentioning

confidence: 99%

Adoption of image surface parameters under moving edge computing in the construction of mountain fire warning method

Cheng¹,

Zhou²,

Chai³

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

In order to cope with the problems of high frequency and multiple causes of mountain fires, it is very important to adopt appropriate technologies to monitor and warn mountain fires through a few surface parameters. At the same time, the existing mobile terminal equipment is insufficient in image processing and storage capacity, and the energy consumption is high in the data transmission process, which requires calculation unloading. For this circumstance, first, a hierarchical discriminant analysis algorithm based on image feature extraction is introduced, and the image acquisition software in the mobile edge computing environment in the android system is designed and installed. Based on the remote sensing data, the land surface parameters of mountain fire are obtained, and the application of image recognition optimization algorithm in the mobile edge computing (MEC) environment is realized to solve the problem of transmission delay caused by traditional mobile cloud computing (MCC). Then, according to the forest fire sensitivity index, a forest fire early warning model based on MEC is designed. Finally, the image recognition response time and bandwidth consumption of the algorithm are studied, and the occurrence probability of mountain fire in Muli county, Liangshan prefecture, Sichuan is predicted. The results show that, compared with the MCC architecture, the algorithm presented in this study has shorter recognition and response time to different images in WiFi network environment; compared with MCC, MEC architecture can identify close users and transmit less data, which can effectively reduce the bandwidth pressure of the network. In most areas of Muli county, Liangshan prefecture, the probability of mountain fire is relatively low, the probability of mountain fire caused by non-surface environment is about 8 times that of the surface environment, and the influence of non-surface environment in the period of high incidence of mountain fire is lower than that in the period of low incidence. In conclusion, the surface parameters of MEC can be used to effectively predict the mountain fire and provide preventive measures in time.

show abstract

“…These woodland communities in the Grassland biome are mostly restricted to deep valleys and drainage lines as compared to the dispersed spatial distribution of trees in the savanna biome. Studies undertaken in the grassland ecosystem suggest that plant communities respond in different ways to the increasing environmental changes and availability of moisture and protection against fire (Adagbasa, Adelabu & Okello 2018;Adagbasa, Adelabu & Okello 2020;Adelabu et al 2020;Botha, Archibald & Greve 2020;Everand 1986). Other studies in the African continent showed elevation, slope and aspect as the determinants for the spatial and temporal distribution of plant communities and species composition (Sala & Paruelo 1997).…”

Section: Introductionmentioning

confidence: 99%

“…The findings from these studies predict changes in dry woodland and Afromontane forests because of climatic changes. The increase in temperatures and other environmental factors are also expected to result in increased fire frequencies and changes in woodland communities (Abiem et al 2020;Adelabu, Adepoju & Mofokeng 2020;Everand 1986).…”

Section: Introductionmentioning

confidence: 99%

The spatial distribution of the woodland communities and their associated environmental drivers in the Golden Gate Highlands National Park, South Africa

Daemane

Ramoelo

Adelabu

2021

Koedoe

View full text Add to dashboard Cite

The extreme variability in the topography, altitude and climatic conditions in the temperate Grassland Mountains of Southern Africa is associated with the complex mosaic of grassland communities with pockets of woodland patches. Understanding the relationships between plant communities and environmental parameters is essential in biodiversity conservation, especially for current and future climate change predictions. This article focused on the spatial distribution of woodland communities and their associated environmental drivers in the Golden Gate Highlands (GGHNP) National Park in South Africa. A generalized linear model (GLM) assuming a binomial distribution, was used to determine the optimal environmental variables influencing the spatial distribution of the woodland communities. The Coefficient of Variation (CV) was relatively higher for the topographic ruggedness index (68.78%), topographic roughness index (68.03), aspect (60.04%), coarse fragments (37.46%) and the topographic wetness index (31.33) whereas soil pH, bulk density, sandy and clay contents had relatively less variation (2.39%, 3.23%, 7.56% and 8.46% respectively). In determining the optimal number of environmental variables influencing the spatial distribution of woodland communities, roughness index, topographic wetness index, soil coarse fragments, soil organic carbon, soil cation exchange capacity and remote-sensing based vegetation condition index were significant (p 0.05) and positively correlated with the woodland communities. Soil nitrogen, clay content, soil pH, fire and elevation were also significant but negatively correlated with the woodland communities. The area under the curve (AUC) of the receiver operating characteristics (ROC) was 0.81. This was indicative of a Parsimonious Model with explanatory predictive power for determination of optimal environmental variables in vegetation ecology.Conservation implications: The isolated woodland communities are sources of floristic diversity and important biogeographical links between larger forest areas in the wider Drakensberg region. They provide suitable habitats for a larger number of forest species and harbour some of the endemic tree species of South Africa. They also provide watershed protection and other important ecosystem services. Understanding the drivers influencing the spatial distribution and persistence of these woodland communities is therefore key to conservation planning in the area.

show abstract

Estimation of fire potential index in mountainous protected region using remote sensing

Cited by 20 publications

References 47 publications

Role of Machine Learning Algorithms in Forest Fire Management: A Literature Review

Role of Machine Learning Algorithms in Forest Fire Management: A Literature Review

Adoption of image surface parameters under moving edge computing in the construction of mountain fire warning method

The spatial distribution of the woodland communities and their associated environmental drivers in the Golden Gate Highlands National Park, South Africa

Contact Info

Product

Resources

About