基于长短期记忆网络的轨道交通短期OD客流量预测

为了更准确地掌握轨道交通客流在线网中的时空分布,更高效地匹配客流需求与运输能力,实现提高轨道交通运输效率、改善运营服务质量的目的,提出了一种基于长短期记忆网络的短期OD(交通起止点)客流量预测方法。以历史客流数据为基础,定性分析车站间OD客流量的时空相关性,利用回归分析法定量分析客流影响因素,筛选出运营时刻、运营日特征、最低气温3个时间特征。为提高预测精度,以长短期记忆网络为基础,结合时间特征,为每对起讫点单独构建预测模型,形成了基于长短期记忆网络的轨道交通短期OD客流量预测模型。以苏州市为例进行验证,结果表明,加入了时间特征的短期OD客流量预测模型较移动平均模型、仅利用历史客流数据训练的基于LSTM网络的短期OD客流量预测模型,预测结果与真实值之间的误差降低了6.27%～8.58%,所提出的方法和模型可为轨道交通运营部门制定列车运行计划、组织客运工作提供更准确的数据资料。     

International environmental agreements under different evolutionary imitation mechanisms

This paper explores how the formation and stability of international environmental agreements vary with two often adopted mechanisms: imitating-the-best-average and imitating-the-best-total rules. We first show that the possible long-run equilibria of two dynamics are the same. They are countries' full participation, no-participation, and the two equilibria combined. However, the occurring conditions of these equilibria under two dynamics may differ. Then, we prove that countries' full participation is more likely to be long-run equilibrium in international environmental agreements when imitating-the-best-average rule is adopted. Moreover, all findings of this study hold whatever the function forms of countries' abnoatement benefits and costs are, and are unaffected by the positive affine transformation of countries' total payoffs.     

整县光伏发电的综合LSTM功率预测模型研究

为了更好实现整县屋顶光伏集约化发展，提高大规模分布式屋顶光伏并网经济性，分析基于气象数据的预测方法弊端问题，挖掘海量时序光伏发电功率数据规律，提出基于改进长短期记忆递归神经网络（LSTM）的整县光伏综合功率预测模型。使用所提模型进行单一光伏电源预测实验，结果表明，改进LSTM模型较其他模型更精准，且在整县光伏综合功率预测场景下具有更高整体预测精度，可以用于整县光伏发电功率预测，有助于实现高比例分布式光伏消纳。     

Discrete-time risk sensitive portfolio optimization with proportional transaction costs

In this paper we consider a discrete-time risk sensitive portfolio optimization over a long time horizon with proportional transaction costs. We show that within the log-return i.i.d. framework the solution to a suitable Bellman equation exists under minimal assumptions and can be used to characterize the optimal strategies for both risk-averse and risk-seeking cases. Moreover, using numerical examples, we show how a Bellman equation analysis can be used to construct or refine optimal trading strategies in the presence of transaction costs.     

涡轮式水力振荡器在涪陵页岩气水平井中的应用

涪陵页岩气田长水平段水平井钻井施工中面临着轨迹调整频繁、摩阻扭矩大、定向钻井托压等技术难题和挑战。涡轮式水力振荡器通过机械振动将滑动钻进时钻柱与井壁的静摩擦转变为动摩擦，取得了良好的降摩减阻效果，大幅提高长水平段一趟钻完钻成功率。介绍涡轮式水力振荡器结构及其降摩减阻机理，开展结构及性能专项优化，分析涪陵地区该水力振荡器的应用情况，对下一阶段该水力振荡器在涪陵页岩气田中的推广应用提出建议。     

验证大气预测模式的实用性

在对鹿泉市市区内的污染源进行调查的基础上，总结出污染物的排放源强。根据全市的气象资料和混合层高度，利用两种方法对鹿泉市市区的污染因子二氧化硫的长期浓度进行估算，并把计算浓度和常规监测浓度进行比较，做误差分析，最后讨论了两种计算方法的特点及在鹿泉市大气环境预测中的实用性     

Modeling dynamic conditional correlations with leverage effects and volatility spillover effects: Evidence from the Chinese and US stock markets affected by the recent trade friction

In this article, we investigate the dynamic conditional correlations (DCCs) with leverage effects and volatility spillover effects that consider time difference and long memory of returns, between the Chinese and US stock markets, in the Sino-US trade friction and previous stable periods. The widespread belief that the developed markets dominate the emerging markets in stock market interactions is challenged by our findings that both the mean and volatility spillovers are bidirectional. We do find that most of the shocks to these DCCs between the two stock markets are symmetric, and all the symmetric shocks to these DCCs are highly persistent between Shanghai’s trading return and S&P 500′s trading or overnight return, however all the shocks to these DCCs are short-lived between S&P 500′s trading return and Shanghai’s trading or overnight return. We also find clear evidence that the DCC between Shanghai’s trading return and S&P 500′s overnight return has a downward trend with a structural break, perhaps due to the “America First” policy, after which it rebounds and fluctuates sharply in the middle and later periods of trade friction. These findings have important implications for investors to pursue profits.     

Household consumption patterns and the consumer price index,England, 1260–1869

Existing long-run consumer price indices for England rely on a fixed consumption basket. Here we construct a methodologically improved, chained-Laspeyres price index for ordinary households based on their changing expenditure patterns between 1260 and 1869. Rather than offering a revisionist perspective on long-run costs, it confirms the broad accuracy of existing indices for the pre-industrial period. The dominant dependence of the key items of expenditure on agricultural, particularly arable, prices explains this finding. The industrial period introduced a new dynamic. The shift in household expenditure towards imported groceries and manufactured goods allowed for more substitution in response to relative price and income changes. Adding the current series to those chained-Laspeyres indices available for later periods provides a CPI for ordinary households in England over nearly eight centuries; from 1260 to the present day.     

LSTM在低能见度预报中的应用

低能见度天气是制约交通出行的主要因素之一，提前做好低能见度的预报工作能利于提前决策、规避风险、降低损失。由于低能见度天气是时间序列问题，针对这种问题，近年来深度学习的长短时记忆网络模型能够显著提高预报精度，因此利用多变量数据对茅台机场低能见度进行预测。首先进行气象因素分析，利用皮尔逊相关系数法来挑选相关性高的气象因子，从而减小数据量得到更利于训练的数据集。然后利用LSTM网络对多元时间序列进行建模，实现机场低能见度的预测。经过试验，模型对茅台机场能见度的准确预报率为85.43%，为机场低能见度预报提供了新的方法。     

Long memory in the high frequency cryptocurrency markets using fractal connectivity analysis: The impact of COVID-19

In this paper, we study the long memory behavior of the hourly cryptocurrency returns during the COVID-19 pandemic period. Initially, we apply different tests against the spurious long memory, with the results indicating the presence of true long memory for most cryptocurrencies. Yet, using the multivariate test, the series are found to be contaminated by level shifts or smooth trends. Then, we adopt the wavelet-based multivariate long memory approach suggested by Achard and Gannaz (2016) to model their long memory connectivity. The findings indicate a change in persistence for all series during the sample period. The fractal connectivity clustering indicates a similarity among Ethereum (ETH) and Litecoin (LTC), Monero (XMR), Bitcoin (BTC), and EOC token (EOS), while Stellar (XLM) is clustered away from the remaining series, indicating the absence of any interdependence with other crypto returns. Overall, shocks arising from COVID-19 crisis have led to changes in long-run correlation structure.