Wildfire Danger Prediction and Understanding With Deep Learning

Kondylatos, Spyros; Prapas, Ioannis; Ronco, Michele; Papoutsis, Ioannis; Camps‐Valls, Gustau; Piles, María; Fernández‐Torres, Miguel‐Ángel

doi:10.1029/2022gl099368

Cited by 36 publications

(28 citation statements)

References 55 publications

(77 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Son et al 2022). Finally, traditional FWIs are mostly based on a limited number of independent variables; specifically, some of the variables described in the previous paragraph are not reflected in the traditional FWIs (Kondylatos et al 2022). One promising direction of research that could address exactly these issues is the application of ML models.…”

Section: Introductionmentioning

confidence: 99%

Developing novel machine-learning-based fire weather indices

Shmuel

Heifetz²

2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Accurate wildfire risk estimation is an essential yet challenging task. As the frequency of extreme fire weather and wildfires is on the rise, forest managers and firefighters require accurate wildfire risk estimations to successfully implement forest management and firefighting strategies. Wildfire risk depends on non-linear interactions between multiple factors; therefore, the performance of linear models in its estimation is limited. To date, several traditional fire weather indices (FWIs) have been commonly used by weather services, such as the Canadian FWI. Traditional FWIs are primarily based on empirical and statistical analyses. In this paper, we propose a novel FWI that was developed using machine learning (ML) – the MLFWI. We present the performance of the MLFWI and compare it withvarious traditional FWIs. We find that the MLFWI significantly outperforms traditional indices in predicting wildfire occurrence, achieving an AUC score of 0.99 compared to 0.62-0.80. We recommend applying the MLFWI in wildfire warning systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Developing novel machine-learning-based fire weather indices

Shmuel

Heifetz²

2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Although they obtained encouraging accuracy and precision from this approach, the model's predictive capability was found to be limited by the influence of human activity on fire ignitions. Kondylatos et al (2022) applied machine-learning methods to predict next-day wildfire danger based on vegetation, meteorological, and soil-moisture data; when applied to two fire seasons in the Eastern Mediterranean region, this deep-learning approach evidently outperformed the more commonly used Fire Weather Index.…”

Section: New Methods and Technologies In Fire Researchmentioning

confidence: 99%

“…Kondylatos et al. (2022) applied machine‐learning methods to predict next‐day wildfire danger based on vegetation, meteorological, and soil‐moisture data; when applied to two fire seasons in the Eastern Mediterranean region, this deep‐learning approach evidently outperformed the more commonly used Fire Weather Index.…”

Section: New Methods and Technologies In Fire Researchmentioning

confidence: 99%

Fire in the Earth System: Introduction to the Special Collection

et al. 2023

View full text Add to dashboard Cite

Fire has always been an important component of many ecosystems, but anthropogenic global climate change is now altering fire regimes over much of Earth's land surface, spurring a more urgent need to understand the physical, biological, and chemical processes associated with fire as well as its effects on human societies. In 2020, AGU launched a Special Collection that spanned 10 journals, soliciting papers under the theme “Fire in the Earth System” to encourage state‐of‐the‐art publications in fire‐related science. The completed Special Collection comprises more than 100 papers. Here, we summarize the articles published in this collection, considering them to be grouped into seven themes: paleofire and its ties to climate; evolution of fire patterns in the recent past and the future, including the effects of ongoing climate change; physical (atmospheric) and chemical processes associated with fire; ecosystem effects, including on biogeochemical cycles; physical landscape change after fire and its associated hazards; fire effects on water quality, air quality, and human health; and new methods and technologies applied to fire research.

show abstract

“…Spatio-temporal learning The ConvLSTM [50] was first introduced for precipitation nowcasting. Subsequently, spatio-temporal forecasting of the Earth system has gained traction, with strong results not only on precipitation nowcasting [42,51], but also on weather forecasting [7,26,38], climate projection [35] and wildfire modeling [24]. Beyond the Earth system, video prediction is spatio-temporal learning.…”

Section: Related Workmentioning

confidence: 99%

Forecasting localized weather impacts on vegetation as seen from space with meteo-guided video prediction

Benson¹,

Requena-Mesa²,

Robin³

et al. 2023

Preprint

View full text Add to dashboard Cite

We present a novel approach for modeling vegetation response to weather in Europe as measured by the Sentinel 2 satellite. Existing satellite imagery forecasting approaches focus on photorealistic quality of the multispectral images, while derived vegetation dynamics have not yet received as much attention. We leverage both spatial and temporal context by extending state-of-the-art video prediction methods with weather guidance. We extend the EarthNet2021 dataset to be suitable for vegetation modeling by introducing a learned cloud mask and an appropriate evaluation scheme. Qualitative and quantitative experiments demonstrate superior performance of our approach over a wide variety of baseline methods, including leading approaches to satellite imagery forecasting. Additionally, we show how our modeled vegetation dynamics can be leveraged in a downstream task: inferring gross primary productivity for carbon monitoring. To the best of our knowledge, this work presents the first models for continental-scale vegetation modeling at fine resolution able to capture anomalies beyond the seasonal cycle, thereby paving the way for predictive assessments of vegetation status.

show abstract

Wildfire Danger Prediction and Understanding With Deep Learning

Cited by 36 publications

References 55 publications

Developing novel machine-learning-based fire weather indices

Developing novel machine-learning-based fire weather indices

Fire in the Earth System: Introduction to the Special Collection

Forecasting localized weather impacts on vegetation as seen from space with meteo-guided video prediction

Contact Info

Product

Resources

About