Search Results (9)

Accurate natural gas price forecasting is vital for risk management, trading strategies, and policy-making in energy markets. This study proposes and evaluates four hybrid deep learning architectures—CNN-LSTM-Attention, CNN-BiLSTM-Attention, TCN-LSTM-Attention, and TCN-BiLSTM-Attention—integrating convolutional feature extraction, sequential learning, and attention mechanisms. Using Henry Hub and NYMEX datasets, the models are trained on long historical periods and tested under multi-step horizons. The results show that all hybrid models significantly outperform the traditional moving average benchmark, achieving R² values above 95% for one-step-ahead forecasts and maintaining an accuracy of over 87% at longer horizons. CNN-BiLSTM-Attention performs best in short-term prediction due to its ability to capture bidirectional dependencies, while TCN-based models demonstrate greater robustness over extended horizons due to their effective modeling of long-range temporal structures. These findings confirm the advantages of deep learning hybrids in energy forecasting and emphasize the importance of horizon-sensitive evaluation. This study contributes methodological innovation and provides practical insights for market participants, with future directions including the integration of macroeconomic and climatic factors, exploration of advanced architectures such as Transformers, and probabilistic forecasting for uncertainty quantification. Full article

After the economic shock caused by COVID-19, with relevant effects on both the supply and demand for energy assets, there was greater interest in understanding the relationships between key energy prices. In order to contribute to a deeper understanding of energy price relationships, this paper analyzes the dynamics between the weekly spot prices of oil, natural gas and benchmark ethanol in the US markets. The analysis period started on 23 June 2006 and ended on 10 June 2022. This study used the DMCA cross-correlation coefficient in a dynamic way, using sliding windows. Among the main results, it was found that: (i) in the post-pandemic period, oil and natural gas were not correlated, in both short- and long-term timescales; and (ii) ethanol was negatively associated with natural gas in the most recent post-pandemic period, especially in short-term scales. The results of the present study are potentially relevant for both market and public agents regarding investment diversification strategies and can aid public policies due to the understanding of the interrelationship between energy prices. Full article

Natural gas plays an important role in energy supply, and its fields of application are diverse. However, the world’s largest growth potential among fossil fuels is attributed to liquefied natural gas (LNG). In the last few years, the U.S. rapidly increased LNG exports, and it is expected that they will further increase the liquefaction capacities. The cost of the LNG value chain is composed of the natural gas price in the country of origin, and the LNG process costs for liquefaction, transportation, storage, and regasification. Thus, the Henry Hub (HH) price in the U.S. is important for U.S. LNG exports to Western Europe. In this paper, gas flows in Western Europe at the beginning of the 2030s are analyzed if the price at HH is higher or lower than expected. Furthermore, the effect of the HH price on monthly U.S. LNG exports are studied. For the calculations, the global gas market model WEGA is used. The results reveal that the price at HH has a significant effect on annual gas flows in Western Europe and also on U.S. LNG exports during the summer. Furthermore, it is shown that pipeline gas in Western Europe will absorb fluctuations of U.S. LNG exports between the presented scenarios. Full article

In the literature on modeling commodity futures prices, we find that the stochastic behavior of the spot price is a response to between one and four factors, including both short- and long-term components. The more factors considered in modeling a spot price process, the better the fit to observed futures prices—but the more complex the procedure can be. With a view to contributing to the knowledge of how many factors should be considered, this study presents a new way of computing the best number of factors to be accounted for when modeling risk-management of energy derivatives. The new method identifies the number of factors one should consider in the model and the type of stochastic process to be followed. This study aims to add value to previous studies which consider principal components by assuming that the spot price can be modeled as a sum of several factors. When applied to four different commodities (weekly observations corresponding to futures prices traded at the NYMEX for WTI light sweet crude oil, heating oil, unleaded gasoline and Henry Hub natural gas) we find that, while crude oil and heating oil are satisfactorily well-modeled with two factors, unleaded gasoline and natural gas need a third factor to capture seasonality. Full article

This study measures the connectedness of natural gas and electricity spot returns to their futures returns with different maturities. We employ the Henry Hub and the Pennsylvania, New Jersey, and Maryland (PJM) Western Hub Peak as the natural gas price indicator and the wholesale electricity price indicator, respectively. We also use each commodity’s spot prices and 12 types of futures prices with one to twelve months maturities and realize results in fourfold. First, we observe mutual spillover effects between natural gas futures returns and learn that the natural gas futures market is integrated. Second, we observe the spillover effects from natural gas futures returns to natural gas spot returns (however, the same is not evident for natural gas spot returns to natural gas futures returns). We find that futures markets have better natural gas price discovery capabilities than spot markets. Third, we observe the spillover effects from natural gas spot returns to electricity spot returns, and the spillover effects from natural gas futures returns to electricity futures returns. We learn that the marginal cost of power generation (natural gas prices) is passed through to electricity prices. Finally, we do not observe any spillover effects amongst electricity futures returns, except for some combinations, and learn that the electricity futures market is not integrated. Full article

We examine spillovers among the North American, European, and Asia–Pacific natural gas markets based on daily data. We use daily natural gas price indexes from 2 February 2009 to 28 February 2019 for the Henry Hub, National Balancing Point, Title Transfer Facility, and Japan Korea Marker. The results of spillover analyses indicate the total connectedness of the return and volatility series to be 22.9% and 32.8%, respectively. In other words, volatility is more highly integrated than returns. The results of the spectral analyses indicate the spillover effect of the return series can largely be explained by short-term factors, while that of the volatility series can be largely explained by long-term factors. The results of the dynamic analyses with moving window samples do not indicate that global gas market liquidity increases with the increasing spillover index. However, the results identify the spillover effect fluctuation caused by demand and supply. Full article

Natural gas has been proposed as a solution to increase the security of energy supply and reduce environmental pollution around the world. Being able to forecast natural gas price benefits various stakeholders and has become a very valuable tool for all market participants in competitive natural gas markets. Machine learning algorithms have gradually become popular tools for natural gas price forecasting. In this paper, we investigate data-driven predictive models for natural gas price forecasting based on common machine learning tools, i.e., artificial neural networks (ANN), support vector machines (SVM), gradient boosting machines (GBM), and Gaussian process regression (GPR). We harness the method of cross-validation for model training and monthly Henry Hub natural gas spot price data from January 2001 to October 2018 for evaluation. Results show that these four machine learning methods have different performance in predicting natural gas prices. However, overall ANN reveals better prediction performance compared with SVM, GBM, and GPR. Full article

Natural gas is often described as the cleanest fossil fuel. The consumption of natural gas is increasing rapidly. Accurate prediction of natural gas spot prices would significantly benefit energy management, economic development, and environmental conservation. In this study, the least squares regression boosting (LSBoost) algorithm was used for forecasting natural gas spot prices. LSBoost can fit regression ensembles well by minimizing the mean squared error. Henry Hub natural gas spot prices were investigated, and a wide range of time series from January 2001 to December 2017 was selected. The LSBoost method is adopted to analyze data series at daily, weekly and monthly. An empirical study verified that the proposed prediction model has a high degree of fitting. Compared with some existing approaches such as linear regression, linear support vector machine (SVM), quadratic SVM, and cubic SVM, the proposed LSBoost-based model showed better performance such as a higher R-square and lower mean absolute error, mean square error, and root-mean-square error. Full article

The paper examines both the time-varying price and volatility transmission between US natural gas and crude oil wholesale markets, over the period 1990–2017. Short iterations suggest that neither commodity determines other’s returns, but sub-periods with very short-lived causal relationships exist. It can be asserted that the markets are decoupled, where unconventional production further enhances the already established commodities’ independence. Using Momentum Threshold Autoregressive (MTAR) cointegration methodology, we find evidence of positive asymmetry from crude oil to natural gas prices, i.e., oil price increases cause faster adjustments to natural gas prices than decreases. We also find that an 1% change of oil price has positive and significantly larger long-term impact (between 0.01% to 0.02%) to the gas price, compared to the negligible impact of gas to oil. Volatility transmission is examined using the Dynamic Conditional Covariance (DCC)-Generalized Autoregressive Conditional Heteroscedasticity (GARCH) methodology, presenting their time-varying correlation. Results show that both commodities influence each other’s volatility at the aggregate level. Finally, we conclude that both regional commodity markets are liquid and integrated, where the market fundamentals drive their price formulation. However, although markets are decoupled and not appropriate for perfect hedging of each other, the existence of bidirectional volatility transmission and their substitutability might be useful for diversified portfolio allocation. Full article