This study utilizes the Dynamic Conditional Correlation-Generalized Autoregressive Conditional Heteroskedasticity (DCC-GARCH) model to investigate the dynamic relationship between Chinese and U.S. stock markets amid t...This study utilizes the Dynamic Conditional Correlation-Generalized Autoregressive Conditional Heteroskedasticity (DCC-GARCH) model to investigate the dynamic relationship between Chinese and U.S. stock markets amid the COVID-19 pandemic. Initially, a univariate GARCH model is developed to derive residual sequences, which are then used to estimate the DCC model parameters. The research reveals a significant rise in the interconnection between the Chinese and U.S. stock markets during the pandemic. The S&P 500 index displayed higher sensitivity and greater volatility in response to the pandemic, whereas the CSI 300 index showed superior resilience and stability. Analysis and model estimation suggest that the market’s dependence on historical data has intensified and its sensitivity to recent shocks has heightened. Predictions from the model indicate increased market volatility during the pandemic. While the model is proficient in capturing market trends, there remains potential for enhancing the accuracy of specific volatility predictions. The study proposes recommendations for policymakers and investors, highlighting the importance of improved cooperation in international financial market regulation and investor education.展开更多
钻井过程中发生钻井液漏失时,现有的井漏智能监测方法,难以获取长时数据序列特征,无法实现对微量漏失的及时监测和预警,进而容易导致更为严重的漏失发生。为此,提出了一种结合扩张因果卷积网络(Dilated and Causal Convolution,DCC)特...钻井过程中发生钻井液漏失时,现有的井漏智能监测方法,难以获取长时数据序列特征,无法实现对微量漏失的及时监测和预警,进而容易导致更为严重的漏失发生。为此,提出了一种结合扩张因果卷积网络(Dilated and Causal Convolution,DCC)特征映射能力和长短期记忆网络(Long Short-Term Memory,LSTM)时序特征提取能力的DCC-LSTM钻井液微量漏失智能监测方法,弥补长短期记忆网络对于长期记忆衰减的不足,实现了对钻井液微量漏失的准确监测和预测。研究结果表明:①DCC-LSTM井漏智能监测模型利用扩张因果卷积网络提取监测参数的长时特征,并将其映射为短序列表示,利用长短期记忆网络处理特征短序列获取监测数据的长时变化趋势,实现了微量漏失的准确监测;②扩张因果卷积网络层数确定方法可以获得最佳网络层数,得到的DCC网络结构使LSTM对长时序列趋势信息的遗忘减少24%;③与其他井漏监测方法相比,DCC-LSTM网络能够准确监测早期微量漏失,井漏预警时间最长可提前26 min,监测准确率由96.9%提升至99.4%,漏报率由6.4%降低为1.1%。结论认为,该方法能够获取监测参数的长时趋势变化特征,经矿场试验验证与其他方法相比有明显优势,为微量漏失监测和预测提供一种可行的方法,对油气钻井井漏风险的防控具有重要指导意义。展开更多
文摘This study utilizes the Dynamic Conditional Correlation-Generalized Autoregressive Conditional Heteroskedasticity (DCC-GARCH) model to investigate the dynamic relationship between Chinese and U.S. stock markets amid the COVID-19 pandemic. Initially, a univariate GARCH model is developed to derive residual sequences, which are then used to estimate the DCC model parameters. The research reveals a significant rise in the interconnection between the Chinese and U.S. stock markets during the pandemic. The S&P 500 index displayed higher sensitivity and greater volatility in response to the pandemic, whereas the CSI 300 index showed superior resilience and stability. Analysis and model estimation suggest that the market’s dependence on historical data has intensified and its sensitivity to recent shocks has heightened. Predictions from the model indicate increased market volatility during the pandemic. While the model is proficient in capturing market trends, there remains potential for enhancing the accuracy of specific volatility predictions. The study proposes recommendations for policymakers and investors, highlighting the importance of improved cooperation in international financial market regulation and investor education.
