Wang Yongjun, Guo Mingze, Vo Thanh Hung, Zhang Hemeng, Liu Xiaoying, Zheng Qian, Zhang Xiaoming, Daoud Mohammad Sh, Abualigah Laith
College of Safety Science and Engineering, Liaoning Technical University, Huludao 125105, China; Institute of Engineering and Environment, Liaoning Technical University, Huludao 125105, China; Key Laboratory of Mine Thermodynamic Disasters and Control of Ministry of Education, Huludao 125105, China.
College of Safety Science and Engineering, Liaoning Technical University, Huludao 125105, China; Institute of Engineering and Environment, Liaoning Technical University, Huludao 125105, China.
J Adv Res. 2025 Apr;70:587-601. doi: 10.1016/j.jare.2024.10.034. Epub 2024 Nov 7.
Underground coal fires pose significant environmental and health risks due to releasing CO emissions. Predicting surface CO 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 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 flux prediction in coal fire areas and inform environmental monitoring and management strategies.
The study involves the collection of an experimental dataset specific to underground coal fire areas, encompassing various parameters related to CO flux and underground coal fire characteristics. Innovative feature engineering techniques are applied to capture the unique characteristics of underground coal fire areas and their impact on CO flux. Different machine learning algorithms, including Natural gradient boosting regression (NGRB), Extreme gradient boosting (XGboost), Light gradient boosting (LGRB), and random forest (RF), are evaluated and compared for their predictive capabilities. The models are trained, optimized, and assessed using appropriate performance metrics.
The NGRB model yields the best predictive performances with R of 0.967 and MAE of 0.234. The novel contributions of this study include the development of accurate prediction models tailored to underground coal fire areas, shedding light on the underlying factors driving CO flux. The findings have practical implications for delineating the spontaneous combustion zone and mitigating CO emissions from underground coal fires, contributing to global efforts in combating climate change.
地下煤火由于释放一氧化碳排放物而带来重大的环境和健康风险。准确预测地下煤火区域的地表一氧化碳通量对于了解自燃区域的分布以及制定有效的缓解策略至关重要。近年来，先进的机器学习技术在各种与碳相关的研究中显示出了前景。本研究采用实验方法来探索先进机器学习方案在预测地下煤火区域一氧化碳通量方面的能力。
通过利用先进机器学习方案和实验方法的力量，本研究旨在为煤火区域的一氧化碳通量预测提供有价值的见解，并为环境监测和管理策略提供信息。
该研究涉及收集特定于地下煤火区域的实验数据集，包括与一氧化碳通量和地下煤火特征相关的各种参数。应用创新的特征工程技术来捕捉地下煤火区域的独特特征及其对一氧化碳通量的影响。评估并比较了不同的机器学习算法，包括自然梯度提升回归（NGRB）、极端梯度提升（XGboost）、轻梯度提升（LGRB）和随机森林（RF）的预测能力。使用适当的性能指标对模型进行训练、优化和评估。
NGRB模型具有最佳的预测性能，R值为0.967，平均绝对误差（MAE）为0.234。本研究的新贡献包括开发了针对地下煤火区域的准确预测模型，揭示了驱动一氧化碳通量的潜在因素。这些发现对于划定自燃区域和减少地下煤火的一氧化碳排放具有实际意义，有助于全球应对气候变化的努力。
