クリーン生産による低炭素化：ガス抽出シミュレーションと機械学習モデルによる炭層ガス量予測
Low carbon advancement through cleaner production: gas extraction simulation and machine learning model prediction of coal rock gas volume (原題)
Junjie Cai, Xijian Li, Shoukun Chen
🤖 gxceed AI 要約
日本語
本研究は、貴州青龍炭鉱の採掘現場を対象に、COMSOLによる多物理場シミュレーションと機械学習モデルを組み合わせて炭層ガス抽出量を高精度に予測する手法を提案。XGBoost-LSTMハイブリッドモデルが最良で、R²=0.9998を達成し、誤差指標が大幅に改善。ガス抽出量には石炭層の浸透率と温度が特に影響することを特定し、低炭素生産戦略の科学的根拠を提供する。
English
This study proposes a method combining COMSOL multi-physics simulation and machine learning to accurately predict coal rock gas extraction volume, targeting the Qinglong Coal Mine in Guizhou. The XGBoost-LSTM hybrid model achieved the best performance with R²=0.9998 and significantly reduced error metrics. It identifies coal seam permeability and temperature as key factors, providing a scientific basis for low-carbon production strategies.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本では石炭産業の規模は小さいが、メタン排出削減と炭素回収・貯留（CCS）技術はGX実現に重要。本手法は、炭鉱ガス利用やCCSの効率化に応用可能であり、日本のエネルギー転換やカーボンニュートラル戦略に示唆を与える。
In the global GX context
Globally, this research contributes to methane emission control and carbon sequestration efforts, aligning with international climate goals. The integration of simulation and machine learning for gas extraction prediction offers a replicable approach for optimizing coal mine operations and reducing greenhouse gas emissions, relevant to global decarbonization pathways.
👥 読者別の含意
🔬研究者:Provides a novel hybrid ML approach for predicting gas extraction volumes, with potential applications in carbon accounting and CCUS optimization.
🏢実務担当者:Offers a data-driven tool for improving gas extraction efficiency and supporting low-carbon production strategies in coal mining operations.
🏛政策担当者:Highlights the potential of AI-driven predictive models in facilitating methane emission reductions and supporting clean energy transitions.
📄 Abstract（原文）
Accurate prediction of the volume of coal rock gas is a key prerequisite for the low carbon transformation of the coal industry. Based on this foundation, strengthening the extraction and utilization of gas, and through the substitution of methane for fossil fuels, coupling CO₂ displacement for increased production and geological storage technologies, it is possible to jointly achieve methane emission control, resource efficiency improvement, and carbon sequestration, precisely meeting the industry’s demands for low carbon development. This study takes the 21,605 working face of Guizhou Qinglong Coal Mine as the research object. Employ COMSOL software for multi-physics field simulations and integrate machine learning models to predict gas extraction volumes, further refining the prediction accuracy through optimization algorithms. The results demonstrate that the combination of numerical simulation and machine learning methods markedly boosts the precision and reliability of gas extraction volume predictions. Evaluation using the Entropy Weight Method shows that the eXtreme Gradient Boosting (XGBoost)- Long Short-Term Memory (LSTM) hybrid model has the highest weight. Compared to the base XGBoost model, MAE, MAPE, MSE, and RMSE decreased by 72.64%, 46.89%, 95.77%, and 79.44%, respectively. Compared to the base LSTM model, these metrics dropped by 79.53%, 33.39%, 98.65%, and 88.37%, respectively. The R² value improved to 0.9998. This study identifies that gas extraction volumes are influenced by multiple factors, with coal seam permeability and temperature being particularly significant. This research not only provides a scientific basis for the low carbon production technology strategy of coal rocks, but also offers new approaches and tools for accurately predicting the volume of gas extraction from coal rocks.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1007/s44442-026-00119-0first seen 2026-09-02 04:52:57
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。