Reservoir-induced landslides and risk control in Three Gorges Project on Yangtze River,China

The Three Gorges region in China was basically a geohazard-prone area prior to construction of the Three Gorges Reservoir （TGR）. After construction of the TGR, the water level was raised from 70 m to 175 m above sea level （ASL）, and annual reservoir regulation has caused a 30-m water level difference after impoundment of the TGR since September 2008. This paper first presents the spatiotemporal distribution of landslides in six periods of 175 m ASL trial impoundments from 2008 to 2014. The results show that the number of landslides sharply decreased from 273 at the initial stage to less than ten at the second stage of impoundment. Based on this, the reservoir-induced landslides in the TGR region can be roughly classified into five failure patterns, i.e. accumulation landslide, dip-slope landslide, reversed bedding landslide, rockfall, and karst breccia landslide. The accumulation landslides and dip-slope landslides account for more than 90%. Taking the Shuping accumulation landslide （a sliding mass volume of 20.7 × 106 m^3） in Zigui County and the Outang dip-slope landslide （a sliding mass volume of about 90 × 106 m^3） in Fengjie County as two typical cases, the mechanisms of reactivation of the two landslides are analyzed. The monitoring data and factor of safety （FOS） calculation show that the accumulation landslide is dominated by water level variation in the reservoir as most part of the mass body is under 175 m ASL, and the dip-slope landslide is controlled by the coupling effect of reservoir water level variation and precipitation as an extensive recharge area of rainfall from the rear and the front mass is below 175 m ASL. The characteristics of landslide-induced impulsive wave hazards after and before reservoir impoundment are studied, and the probability of occurrence of a landslide-induced impulsive wave hazard has increased in the reservoir region. Simulation results of the Ganjingzi landslide in Wushan County indicate the strong relationship between landslide-induced surge and water variation with high potential risk to shipping and residential areas. Regarding reservoir regulation in TGR when using a single index, i.e. 1-d water level variation, water resources are not well utilized, and there is also potential risk of disasters since 2008. In addition, various indices such as 1-d, 5-d, and 10-d water level variations are proposed for reservoir regulation. Finally, taking reservoir-induced landslides in June 2015 for example, the feasibility of the optimizing indices of water level variations is verified.

Take Bitcoin into your portfolio:a novel ensemble portfolio optimization framework for broad commodity assets

The emergence and growing popularity of Bitcoins have attracted the attention of the financial world.However,few empirical studies have considered the inclusion of the newly emerged commodity asset in the global commodity market.It is of great importance for investors and policymakers to take advantage of this asset and its potential benefits by incorporating it as a part of the broad commodity trading portfolio.In this study,we propose a novel ensemble portfolio optimization(NEPO)framework utilized for broad commodity assets,which integrates a hybrid variational mode decomposition-bidirectional long short-term memory deep learning model for future returns forecast and a reinforcement learning-based model for optimizing the asset weight allocation.Our empirical results indicate that the NEPO framework could effectively improve the prediction accuracy and trend prediction ability across various commodity assets from different sectors.In addition,it could effectively incorporate Bitcoins into the asset pool and achieve better financial performance compared to traditional asset allocation strategies,commodity funds,and indices.

Dynamic Risk Spillovers in Non-Ferrous Metal Future Markets During COVID-19:A Frequency Domain Analysis

During the COVID-19 pandemic,the international financial markets experienced severe turbulence.Under the background of“Made in China 2025”,substantial entity enterprises have a large demand for non-ferrous metals.With the enhancement of financial attributes of non-ferrous metals,it is vital to prevent financial systemic risk contagion in the non-ferrous metal markets.In this article,the ensemble empirical mode decomposition method is used to decompose the prices of eight important non-ferrous metals futures,and then the dynamic DY risk spillover index model is established from the perspectives of long-term and short-term.The risk spillover between non-ferrous metals during the COVID-19 is quantitatively analyzed from different frequency domains.The study finds that in the long run,the risk spillover relationship between non-ferrous metals remained basically stable,and the change of it after the epidemic is slight.In the short run,the risk spillover relationship has different degrees of structural changes after the outbreak of the COVID-19 pandemic.The ensemble empirical mode decomposition method can distinguish the risk spillovers in different cycles,and help to formulate policies for preventing systemic risks in the non-ferrous metal markets according to the different length of terms.

Return and Volatility Connectedness between Stock Markets and Macroeconomic Factors in the G-7 Countries

We examine the relationship between return and volatility of the stock markets and macroeconomic fundamentals for the G-7 countries by using monthly data ranging from July 1985 to June 2015. To meet this end, we apply the spillover index approach based on the generalized VAR framework developed by Diebold and Yilmaz (2012, 2014). The empirical analysis shows strong interactions between the returns and volatilities of the G-7 stock markets and the considered set of corresponding macroeconomic factors including industrial production, money supply, interest rates, inflation, oil prices and exchange rates. The return and volatility spillover transmission/reception dynamics of the relationships between these stock markets and the macroeconomic fundamentals have changed after the global financial crisis of 2008. Our findings provide useful insights for investors and policy makers concerned with the unprecedented swings in the stock markets of G-7 countries.

A decomposition clustering ensemble learning approach for forecasting foreign exchange rates

A decomposition clustering ensemble(DCE)learning approach is proposed for forecasting foreign exchange rates by integrating the variational mode decomposition(VMD),the selforganizing map(SOM)network,and the kemel extreme leaming machine(KELM).First,the exchange rate time series is decomposed into N subcomponents by the VMD method.Second,each subcomponent series is modeled by the KELM.Third,the SOM neural network is introduced to cluster the subcomponent forecasting results of the in-sample dataset to obtain cluster centers.Finally,each cluster's ensemble weight is estimated by another KELM,and the final forecasting results are obtained by the corresponding clusters'ensemble weights.The empirical results illustrate that our proposed DCE learning approach can significantly improve forecasting performance,and statistically outperform some other benchmark models in directional and level forecasting accuracy.

A KELM-Based Ensemble Learning Approach for Exchange Rate Forecasting

In this paper, a KELM-based ensemble learning approach, integrating Granger causality test, grey relational analysis and KELM(Kernel Extreme Learning Machine), is proposed for the exchange rate forecasting. The study uses a set of sixteen macroeconomic variables including, import,export, foreign exchange reserves, etc. Furthermore, the selected variables are ranked and then three of them, which have the highest degrees of relevance with the exchange rate, are filtered out by Granger causality test and the grey relational analysis, to represent the domestic situation. Then, based on the domestic situation, KELM is utilized for medium-term RMB/USD forecasting. The empirical results show that the proposed KELM-based ensemble learning approach outperforms all other benchmark models in different forecasting horizons, which implies that the KELM-based ensemble learning approach is a powerful learning approach for exchange rates forecasting.