用贝叶斯神经网络预测富埃戈火山热辐射功率，效果优于传统模型。
Forecasting Volcanic Radiative Power (VPR) at Fuego Volcano Using Bayesian Regularized Neural Network
- 采用贝叶斯正则化神经网络建模历史热辐射数据
- 均方误差1.77E+16，R²达0.50，优于SCG和LM模型
- 适合灾害预警研究者，可推广至多源地质数据融合
火山活动预测对灾害评估与风险防控至关重要。火山热辐射功率（VPR）由热遥感数据获取，是表征火山活动的关键指标。本研究基于富埃戈火山的历史数据，采用贝叶斯正则化神经网络（BRNN）预测未来VPR值，并与缩放共轭梯度（SCG）和列文伯格-马夸尔特（LM）模型进行对比。结果表明，BRNN在性能上优于两者，均方误差最低（1.77E+16），R²最高（0.50），展现出更强的变异性捕捉能力且有效抑制过拟合。尽管如此，模型预测精度仍有提升空间。未来研究应整合地震、气体排放等更多地球物理参数以增强预报精度。研究证实，机器学习模型尤其是BRNN，在火山活动预测中具有重要潜力，有助于构建更有效的早期预警系统。
原文摘要 · Abstract (English)
Forecasting volcanic activity is critical for hazard assessment and risk mitigation. Volcanic Radiative Power (VPR), derived from thermal remote sensing data, serves as an essential indicator of volcanic activity. In this study, we employ Bayesian Regularized Neural Networks (BRNN) to predict future VPR values based on historical data from Fuego Volcano, comparing its performance against Scaled Conjugate Gradient (SCG) and Levenberg-Marquardt (LM) models. The results indicate that BRNN outperforms SCG and LM, achieving the lowest mean squared error (1.77E+16) and the highest R-squared value (0.50), demonstrating its superior ability to capture VPR variability while minimizing overfitting. Despite these promising results, challenges remain in improving the model's predictive accuracy. Future research should focus on integrating additional geophysical parameters, such as seismic and gas emission data, to enhance forecasting precision. The findings highlight the potential of machine learning models, particularly BRNN, in advancing volcanic activity forecasting, contributing to more effective early warning systems for volcanic hazards.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。