Bayesian networks elucidate interactions between fire and other drivers of terrestrial fauna distributions

Hradsky, Bronwyn A.; Penman, Trent D.; Ababei, Dan; Hanea, Anca M.; Ritchie, Euan G.; York, Alan; Stefano, Julian Di

doi:10.1002/ecs2.1926

Cited by 36 publications

(23 citation statements)

References 97 publications

(169 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These findings contrast strongly with other Australian studies that have found that variation in predation rates and fire strongly influence the abundance (rather than occurrence) of native herbivores (Dexter et al ; Foster et al ), although effects on native herbivore occurrence are less well understood. Our findings are, however, consistent with other studies that have found little influence of time‐since‐fire on fox distribution at a landscape scale (Payne et al ; Hradsky et al ) and broader trends across other predators species (Geary et al ).…”

Section: Discussionsupporting

confidence: 92%

Predators, fire or resources: What drives the distribution of herbivores in fragmented mesic forests?

et al. 2020

Self Cite

View full text Add to dashboard Cite

Trophic interactions and disturbance events can shape the structure and function of ecosystems. However, the effects of drivers such as predation, fire and climatic variables on species distributions are rarely considered concurrently. We used a replicated landscape-scale predator management experiment to compare the effects of red fox Vulpes vulpes control, time-since-fire, vegetation type and other environmental variables on native herbivore distributions. Occurrence data for four native herbivores and an invasive predatorthe red foxwere collected from 240 sites across three baited (for lethal fox control) and three unbaited forest blocks (4659-9750 ha) in south-western Victoria, Australia, and used to build species distribution models. The herbivore taxa were as follows: red-necked wallaby Macropus rufogriseus, black wallaby Wallabia bicolour, grey kangaroo Macropus fuligenosus and Macropus giganteus and common brushtail possum Trichosurus vulpecula. Fox control and fire had little effect on herbivore occurrence, despite the literature suggesting it can influence abundance, while climate, proximity to farmland and topography were more influential. This may be because the region's high productivity and agricultural pastures subsidise food resources for both predators and prey within the forest blocks and so dampen trophic interactions. Alternatively, these drivers may affect herbivore abundance, but not herbivore occurrence. Understanding the drivers of herbivore distributions is an important step in predicting the effects of herbivory on other species, particularly after management interventions such as predator control and prescribed burns.

show abstract

Section: Discussionsupporting

confidence: 92%

Predators, fire or resources: What drives the distribution of herbivores in fragmented mesic forests?

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Considering the potential impacts of wildfires on wildlife, it is perhaps surprising that relatively few of such studies have adopted ML approaches; however, ML methods have been used to predict the impacts of wildfire and other drivers on species distributions and arthropod communities. Hradsky et al (2017), for example, used nonparametric BNs to describe and quantify the drivers of faunal distributions in wildfire-affected landscapes in southeastern Australia. Similarly, Reside et al (2012) used MaxEnt to model bird species distributions in response to fire regime shifts in northern Australia, which is an important aspect of conservation planning in the region.…”

Section: Post-fire Regeneration Succession and Ecologymentioning

confidence: 99%

A review of machine learning applications in wildfire science and management

et al. 2020

View full text Add to dashboard Cite

Artiﬁcial intelligence has been applied in wildﬁre science and management since the 1990s, with early applications including neural networks and expert systems. Since then the ﬁeld has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildﬁre science and management. Our overall objective is to improve awareness of ML methods among wildﬁre researchers and managers, as well as illustrate the diverse and challenging range of problems in wildﬁre science available to ML data scientists. To that end, we ﬁrst present an overview of popular ML approaches used in wildﬁre science to date, and then review the use of ML in wildﬁre science as broadly categorized into six problem domains, including: 1) fuels characterization, ﬁre detection, and mapping; 2) ﬁre weather and climate change; 3) ﬁre occurrence, susceptibility, and risk; 4) ﬁre behavior prediction; 5) ﬁre eﬀects; and 6) ﬁre management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildﬁres within a data science context. In total, we identfied 300 relevant publications up to the end of 2019, where the most frequently used ML methods across problem domains included random forests, MaxEnt, artiﬁcial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods — including deep learning and agent based learning — in the wildﬁre sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML methods to learn on their own, expertise in wildﬁre science is necessary to ensure realistic modelling of ﬁre processes across multiple scales, while the complexity of some ML methods, such as deep learning, requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildﬁre research and management communities play an active role in providing relevant, high quality, and freely available wildﬁre data for use by practitioners of ML methods.

show abstract

“…However, ML methods have been used to predict the impacts of wildfire and other drivers on species distributions and arthropod communities. Hradsky et al (2017), for example, used non-parametric BNs to describe and quantify the drivers of faunal distributions in wildfire-affected landscapes in southeastern Australia. Similarly, (Reside, VanDerWal, Kutt, Watson, & Williams, 2012) used MaxEnt to model bird species distributions in response to fire regime shifts in northern Australia, which is an important aspect of conservation planning in the region.…”

Section: Post-fire Regeneration Succession and Ecologymentioning

confidence: 99%

A review of machine learning applications in wildfire science and management

Jain,

Coogan,

Subramanian

et al. 2020

Preprint

View full text Add to dashboard Cite

Artificial intelligence has been applied in wildfire science and management since the 1990s, with early applications including neural networks and expert systems. Since then the field has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildfire science and management. Our overall objective is to improve awareness of ML methods among wildfire researchers and managers, as well as illustrate the diverse and challenging range of problems in wildfire science available to ML data scientists.To that end, we first present an overview of popular ML approaches used in wildfire science to date, and then review the use of ML in wildfire science as broadly categorized into six problem domains, including: 1) fuels characterization, fire detection, and mapping; 2) fire weather and climate change; 3) fire occurrence, susceptibility, and risk; 4) fire behavior prediction; 5) fire effects; and 6) fire management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildfires within a data science context. In total, we identified 298 relevant publications, where the most frequently used ML methods across problem domains included random forests, MaxEnt, artificial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods -including deep learning and agent based learning -in the wildfire sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML models to learn on their own, expertise in wildfire science is necessary to ensure realistic modelling of fire processes across multiple scales, while the complexity of some ML methods, such as deep learning, requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildfire research and management communities play an active role in providing relevant, high quality, and freely available wildfire data for use by practitioners of ML methods.

show abstract

Bayesian networks elucidate interactions between fire and other drivers of terrestrial fauna distributions

Cited by 36 publications

References 97 publications

Predators, fire or resources: What drives the distribution of herbivores in fragmented mesic forests?

Predators, fire or resources: What drives the distribution of herbivores in fragmented mesic forests?

A review of machine learning applications in wildfire science and management

A review of machine learning applications in wildfire science and management

Contact Info

Product

Resources

About