Data for "Exploring the Monthly Contribution of Drivers on European Summer Wildfires with Explainable Artificial Intelligence (XAI)"

Abstract

We applied an XAI method to analyze the monthly contribution of wildfire drivers on summer fires in European forest, shrub and herbaceous vegetation areas from 2014 to 2023. Using burn area data and 18 features including meteorology, vegetation, topography, and anthropogenic activity, we developed a reliable wildfire occurrence model using the LSTM method.

Methods

The fire point data is provided by the European Forest Fire Information System (EFFIS). A total of 18 features were selected for modeling. Among these features, the four meteorological variables (Prep, LST, SM, and SR), along with the corresponding four condition indexes (RCI, TCI, SMCI, SRCI) derived from them, the Wind Speed (WS), and the two vegetation variables (Normalized Difference Vegetation Index (NDVI) and Leaf Area Index (LAI)), were used as monthly time series. The Lightning Frequency dataset is monthly but represents an average of data from 2012 to 2021, remaining constant across different years. The remaining six feature datasets do not vary over time. Data download and analysis were conducted using Google Earth Engine, QGIS, and Python.

Subject keywords

Deep learning, Europe, Earth and related environmental sciences, vegetation, wildfire

Description of the data and file structure

train_data_no_2023.npy and train_Y_data_no_2023.npy: These contain the features and labels for the training set (excluding data from 2023).

TEST_X_2023.npy and TEST_Y_2023.npy: These represent the features and labels for the test set, specifically for the year 2023.

model.h5: This is the final trained model.

shap_values_train_data.npy: This file contains the SHAP values for the training set, used to explain model predictions.

The order of features:

Label = ['Prep', 'LST', 'SM', 'SR', 'RCI', 'TCI', 'SMCI', 'SRCI', 'WS', 'NDVI', 'LAI', 'LF', 'CH', 'Elevation', 'Slope', 'Aspect', 'DR', 'DS']