Advanced machine learning schemes for prediction CO2 flux based experimental approach in underground coal fire areas

作者：Yongjun Wang, Mingze Guo, Hung Vo Thanh, Hemeng Zhang, Xiaoying Liu, Qian Zheng, Xiaoming Zhang, Mohammad Sh. Daoud, Laith Abualigah · 发表于：Journal of Advanced Research · 年份：2024 · DOI：10.1016/j.jare.2024.10.034 · 被引用次数：16 · 研究领域：Coal Properties and Utilization、Underground infrastructure and sustainability、Safety and Risk Management

• This paper presents a highly effective approach aimed at reducing the necessity for costly and time-consuming experimental investigations of CO 2 flux in coal fire areas. • The study revealed that the NGRB scheme emerged as the most accurate method for estimating CO 2 flux in coal fire areas. • The study employed the estimation of SHAP values to assess the impact of input variables on the CO 2 flux estimation. • This study introduces an intelligent tool for predicting CO 2 flux in coal fires, which holds great potential for aiding in the evaluation of various disciplines within the mining sector. Underground coal fires pose significant environmental and health risks due to releasing CO 2 emissions. Predicting surface CO 2 flux accurately in underground coal fire areas is crucial for understanding the distribution of spontaneous combustion zones and developing effective mitigation strategies. In recent years, advanced machine learning techniques have shown promise in various carbon-related studies. This research uses an experimental approach to explore the power of advanced machine learning schemes for predicting CO 2 flux in underground coal fire areas. By leveraging the power of advanced machine learning schemes and experimental approaches, this research aims to provide valuable insights into CO 2 flux prediction in coal fire areas and inform environmental monitoring and management strategies. The study involves the collection of an experimental dataset specific to undergr...