Related Experiment Video
Updated: Jan 9, 2026
08:18
Design and Use of a Full Flow Sampling System FFS for the Quantification of Methane Emissions
Published on: June 12, 2016
17.3K
RETRACTED: Natural gas price prediction based on artificial intelligence models
Xuhui Liu1, Meiqi Tang2, Yu Feng1
1School of Economics, Management and Law, Jilin Normal University, Siping, China.
Plos One
|December 1, 2025
Summary
Accurate multi-step natural gas price forecasting is crucial for energy security. The Long Short-Term Memory (LSTM) model demonstrates superior performance in predicting price fluctuations, outperforming other AI models in multi-day forecasts.
Area of Science:
- Energy Economics
- Artificial Intelligence
- Time Series Forecasting
Background:
- Geopolitical risks, such as the Russia-Ukraine conflict, expose vulnerabilities in global natural gas supply chains.
- Existing AI-driven energy price forecasting often lacks multi-step prediction analysis, failing to address performance degradation in dynamic frameworks.
Purpose of the Study:
- To construct and evaluate a multi-step forecasting framework for natural gas prices.
- To systematically compare the performance of four AI models in predicting natural gas prices across different forecast horizons.
Main Methods:
- Utilized daily natural gas price data from the US Henry Hub (1997-2024).
- Developed a multi-step prediction framework with forecast horizons of 1 to 4 days.
- Compared feedforward neural networks, support vector machines, random forests, and Long Short-Term Memory (LSTM) networks.
Main Results:
- The Long Short-Term Memory (LSTM) network consistently exhibited the lowest error rates across all prediction steps.
- In one-step forecasting, the LSTM model achieved a Mean Absolute Percentage Error (MAPE) of 8.53%.
Conclusions:
- LSTM models offer a robust solution for accurate multi-step natural gas price forecasting.
- Findings support enhanced energy security policy-making and optimized trading strategies for energy markets.
Related Concept Videos
01:03Prediction Intervals
3.1K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.1K
01:16Non-equilibrium in the Cell
5.3K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
5.3K