Can I read Fire danger forecasting using machine learning-based models and meteorological observation: a case study in Northeastern China on EtoBox?

Fire danger forecasting using machine learning-based models and meteorological observation: a case study in Northeastern China by Zhenyu Chen; Chen Zhang; Wendi Li; Lanyu Gao; Liming Liu; Lei Fang; Changsheng Zhang is a Computer Science article available to read on EtoBox.

What is Fire danger forecasting using machine learning-based models and meteorological observation: a case study in Northeastern China about?

Wildfire is one of the primary natural disturbance agents in the forests of China. The forecast of fire danger is critically important to assist stakeholders to avoid and mitigate wildfire-induced hazards and losses to both human society and natural ecosystems. Currently, fire danger rating methods often focus on fire weather classification based on fixed thresholds, which has shortcomings in generalizability and robustness. Based on historical fire occurrence data and meteorological data of Northeastern China from 2004 to 2015, we proposed a forest fire danger rating classification and forecasting model by combining the advantages of the Canadian Fire Weather Index (FWI) system and two machine learning models such as the Long Short-Term Memory (LSTM) network and Random Forest (RF) model. The method is divided into two stages. The first stage is the LSTM-based FWI system indexes prediction. In the first stage, the future FWI system indexes are obtained through the LSTM-based prediction model, and the RMSE and MAE of the prediction results are calculated to verify the prediction performance of the model. The second stage is random forest-based fire danger rating prediction method. I

Who reads Fire danger forecasting using machine learning-based models and meteorological observation: a case study in Northeastern China?

Author

Zhenyu Chen; Chen Zhang; Wendi Li; Lanyu Gao; Liming Liu; Lei Fang; Changsheng Zhang

Publisher

Springer Science and Business Media LLC

Published

2023

Language

EN

Field

Computer Science (Physical Sciences)