High-resolution mapping of wildfire drivers in California based on machine learning

Qiu，Linghua1,2; Chen，Ji2; Fan，Linfeng1; Sun，Liqun3; Zheng，Chunmiao1,4

2022-08-10

10.1016/j.scitotenv.2022.155155

SCIENCE OF THE TOTAL ENVIRONMENT   影响因子和分区

0048-9697

1879-1026

Wildfires are important natural disturbances of ecosystems; however, they threaten the sustainability of ecosystems, climate and humans worldwide. It is vital to quantify and map the controlling drivers of wildfires for effective wildfire prediction and risk management. However, high-resolution mapping of wildfire drivers remains challenging. Here we established machine-learning (Random Forests) models using 23 climate and land surface variables as model inputs to reconstruct the spatial variability and seasonality of wildfire occurrence and extent in California. The importance of individual drivers was then quantified based on the Shapley value method. Thus, we provided spatially resolved maps of wildfire drivers at high resolutions up to 0.004° × 0.004°. The results indicated that precipitation and soil moisture are the major drivers dominating 37% of the total burnt area for large and extreme wildfires in summer and 63% in autumn, while elevation plays a major role for 15–58% of burnt areas in small wildfires in all seasons. Winds are also an important contributor to summer wildfires, accounting for 41% of large and extreme burnt areas. This study enhanced our knowledge of spatial variability of wildfire drivers across diverse landscapes in a fine-scale mapping, providing valuable perspectives and case studies for other regions of the world with frequently occurred wildfire.

Machine learning methods Precipitation and soil moisture Shapley value method Wildfire drivers Wildfire occurrence and extent

SCI ; EI

英语

第一 ; 通讯

National Natural Science Foundation of China[41861124003];

Environmental Sciences & Ecology

Environmental Sciences

WOS:000808120000001

ELSEVIER

20221611986672

Climate models ; Decision trees ; Ecosystems ; Fires ; Game theory ; Machine learning ; Mapping ; Risk management

Surveying:405.3 ; Meteorology:443 ; Ecology and Ecosystems:454.3 ; Soils and Soil Mechanics:483.1 ; Fires and Fire Protection:914.2 ; Mathematics:921 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4 ; Probability Theory:922.1 ; Systems Science:961

ENVIRONMENT/ECOLOGY

2-s2.0-85128303453

Scopus

1.School of Environmental Science and Engineering,Southern University of Science and Technology,Shenzhen,China
2.Department of Civil Engineering,The University of Hong Kong,Hong Kong
3.Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China
4.Shenzhen Institute of Sustainable Development,Southern University of Science and Technology,Shenzhen,China

Qiu，Linghua,Chen，Ji,Fan，Linfeng,et al. High-resolution mapping of wildfire drivers in California based on machine learning[J]. SCIENCE OF THE TOTAL ENVIRONMENT,2022,833.

Qiu，Linghua,Chen，Ji,Fan，Linfeng,Sun，Liqun,&Zheng，Chunmiao.(2022).High-resolution mapping of wildfire drivers in California based on machine learning.SCIENCE OF THE TOTAL ENVIRONMENT,833.

Qiu，Linghua,et al."High-resolution mapping of wildfire drivers in California based on machine learning".SCIENCE OF THE TOTAL ENVIRONMENT 833(2022).