A Multivariate Long Short-Term Memory Neural Network for Coalbed Methane Production Forecasting
Owing to the importance of coalbed methane (CBM) as a source of energy, it is necessary to predict its future production. However, the production process of CBM is the result of the interaction of many factors, making it difficult to perform accurate simulations through mathematical models. We must...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/12/12/2045 |
| _version_ | 1797545196567658496 |
|---|---|
| author | Xijie Xu Xiaoping Rui Yonglei Fan Tian Yu Yiwen Ju |
| author_facet | Xijie Xu Xiaoping Rui Yonglei Fan Tian Yu Yiwen Ju |
| author_sort | Xijie Xu |
| collection | DOAJ |
| description | Owing to the importance of coalbed methane (CBM) as a source of energy, it is necessary to predict its future production. However, the production process of CBM is the result of the interaction of many factors, making it difficult to perform accurate simulations through mathematical models. We must therefore rely on the historical data of CBM production to understand its inherent features and predict its future performance. The objective of this paper is to establish a deep learning prediction method for coalbed methane production without considering complex geological factors. In this paper, we propose a multivariate long short-term memory neural network (M-LSTM NN) model to predict CBM production. We tested the performance of this model using the production data of CBM wells in the Panhe Demonstration Area in the Qinshui Basin of China. The production of different CBM wells has similar characteristics in time. We can use the symmetric similarity of the data to transfer the model to the production forecasting of different CBM wells. Our results demonstrate that the M-LSTM NN model, utilizing the historical yield data of CBM as well as other auxiliary information such as casing pressures, water production levels, and bottom hole temperatures (including the highest and lowest temperatures), can predict CBM production successfully while obtaining a mean absolute percentage error (MAPE) of 0.91%. This is an improvement when compared with the traditional LSTM NN model, which has an MAPE of 1.14%. In addition to this, we conducted multi-step predictions at a daily and monthly scale and obtained similar results. It should be noted that with an increase in time lag, the prediction performance became less accurate. At the daily level, the MAPE value increased from 0.24% to 2.09% over 10 successive days. The predictions on the monthly scale also saw an increase in the MAPE value from 2.68% to 5.95% over three months. This tendency suggests that long-term forecasts are more difficult than short-term ones, and more historical data are required to produce more accurate results. |
| first_indexed | 2024-03-10T14:11:00Z |
| format | Article |
| id | doaj.art-af3e1b70e40f4778bd81c14234c4c0cd |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-10T14:11:00Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-af3e1b70e40f4778bd81c14234c4c0cd2023-11-21T00:10:22ZengMDPI AGSymmetry2073-89942020-12-011212204510.3390/sym12122045A Multivariate Long Short-Term Memory Neural Network for Coalbed Methane Production ForecastingXijie Xu0Xiaoping Rui1Yonglei Fan2Tian Yu3Yiwen Ju4College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing 211000, ChinaCollege of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, ChinaCollege of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, ChinaKey Laboratory of Computational Geodynamics, College of Earth and Planetary Sciences, University of Chinese Academy of Sciences, Beijing 100049, ChinaOwing to the importance of coalbed methane (CBM) as a source of energy, it is necessary to predict its future production. However, the production process of CBM is the result of the interaction of many factors, making it difficult to perform accurate simulations through mathematical models. We must therefore rely on the historical data of CBM production to understand its inherent features and predict its future performance. The objective of this paper is to establish a deep learning prediction method for coalbed methane production without considering complex geological factors. In this paper, we propose a multivariate long short-term memory neural network (M-LSTM NN) model to predict CBM production. We tested the performance of this model using the production data of CBM wells in the Panhe Demonstration Area in the Qinshui Basin of China. The production of different CBM wells has similar characteristics in time. We can use the symmetric similarity of the data to transfer the model to the production forecasting of different CBM wells. Our results demonstrate that the M-LSTM NN model, utilizing the historical yield data of CBM as well as other auxiliary information such as casing pressures, water production levels, and bottom hole temperatures (including the highest and lowest temperatures), can predict CBM production successfully while obtaining a mean absolute percentage error (MAPE) of 0.91%. This is an improvement when compared with the traditional LSTM NN model, which has an MAPE of 1.14%. In addition to this, we conducted multi-step predictions at a daily and monthly scale and obtained similar results. It should be noted that with an increase in time lag, the prediction performance became less accurate. At the daily level, the MAPE value increased from 0.24% to 2.09% over 10 successive days. The predictions on the monthly scale also saw an increase in the MAPE value from 2.68% to 5.95% over three months. This tendency suggests that long-term forecasts are more difficult than short-term ones, and more historical data are required to produce more accurate results.https://www.mdpi.com/2073-8994/12/12/2045coalbed methane (CBM)production forecastinglong short-term memory neural networks (LSTM NN)multi-step predictions |
| spellingShingle | Xijie Xu Xiaoping Rui Yonglei Fan Tian Yu Yiwen Ju A Multivariate Long Short-Term Memory Neural Network for Coalbed Methane Production Forecasting Symmetry coalbed methane (CBM) production forecasting long short-term memory neural networks (LSTM NN) multi-step predictions |
| title | A Multivariate Long Short-Term Memory Neural Network for Coalbed Methane Production Forecasting |
| title_full | A Multivariate Long Short-Term Memory Neural Network for Coalbed Methane Production Forecasting |
| title_fullStr | A Multivariate Long Short-Term Memory Neural Network for Coalbed Methane Production Forecasting |
| title_full_unstemmed | A Multivariate Long Short-Term Memory Neural Network for Coalbed Methane Production Forecasting |
| title_short | A Multivariate Long Short-Term Memory Neural Network for Coalbed Methane Production Forecasting |
| title_sort | multivariate long short term memory neural network for coalbed methane production forecasting |
| topic | coalbed methane (CBM) production forecasting long short-term memory neural networks (LSTM NN) multi-step predictions |
| url | https://www.mdpi.com/2073-8994/12/12/2045 |
| work_keys_str_mv | AT xijiexu amultivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting AT xiaopingrui amultivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting AT yongleifan amultivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting AT tianyu amultivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting AT yiwenju amultivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting AT xijiexu multivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting AT xiaopingrui multivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting AT yongleifan multivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting AT tianyu multivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting AT yiwenju multivariatelongshorttermmemoryneuralnetworkforcoalbedmethaneproductionforecasting |