An Optimized Gradient Boosting Model by Genetic Algorithm for Forecasting Crude Oil Production
The forecasting of crude oil production is essential to economic plans and decision-making in the oil and gas industry. Several techniques have been applied to forecast crude oil production. Artificial Intelligence (AI)-based techniques are promising that have been applied successfully to several se...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/17/6416 |
| _version_ | 1827666397617979392 |
|---|---|
| author | Eman H. Alkhammash |
| author_facet | Eman H. Alkhammash |
| author_sort | Eman H. Alkhammash |
| collection | DOAJ |
| description | The forecasting of crude oil production is essential to economic plans and decision-making in the oil and gas industry. Several techniques have been applied to forecast crude oil production. Artificial Intelligence (AI)-based techniques are promising that have been applied successfully to several sectors and are capable of being applied to different stages of oil exploration and production. However, there is still more work to be done in the oil sector. This paper proposes an optimized gradient boosting (GB) model by genetic algorithm (GA) called GA-GB for forecasting crude oil production. The proposed optimized model was applied to forecast crude oil in several countries, including the top producers and others with less production. The GA-GB model of crude oil forecasting was successfully developed, trained, and tested to provide excellent forecasting of crude oil production. The proposed GA-GB model has been applied to forecast crude oil production and has also been applied to oil price and oil demand, and the experiment of the proposed optimized model shows good results. In the experiment, three different actual datasets are used: crude oil production (OProd), crude oil price (OPrice), and oil demand (OD) acquired from various sources. The GA-GB model outperforms five regression models, including the Bagging regressor, KNN regressor, MLP regressor, RF regressor, and Lasso regressor. |
| first_indexed | 2024-03-10T01:51:09Z |
| format | Article |
| id | doaj.art-86e37ff5e7b346478407302ea5850e2a |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T01:51:09Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-86e37ff5e7b346478407302ea5850e2a2023-11-23T13:05:46ZengMDPI AGEnergies1996-10732022-09-011517641610.3390/en15176416An Optimized Gradient Boosting Model by Genetic Algorithm for Forecasting Crude Oil ProductionEman H. Alkhammash0Department of Computer Science, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi ArabiaThe forecasting of crude oil production is essential to economic plans and decision-making in the oil and gas industry. Several techniques have been applied to forecast crude oil production. Artificial Intelligence (AI)-based techniques are promising that have been applied successfully to several sectors and are capable of being applied to different stages of oil exploration and production. However, there is still more work to be done in the oil sector. This paper proposes an optimized gradient boosting (GB) model by genetic algorithm (GA) called GA-GB for forecasting crude oil production. The proposed optimized model was applied to forecast crude oil in several countries, including the top producers and others with less production. The GA-GB model of crude oil forecasting was successfully developed, trained, and tested to provide excellent forecasting of crude oil production. The proposed GA-GB model has been applied to forecast crude oil production and has also been applied to oil price and oil demand, and the experiment of the proposed optimized model shows good results. In the experiment, three different actual datasets are used: crude oil production (OProd), crude oil price (OPrice), and oil demand (OD) acquired from various sources. The GA-GB model outperforms five regression models, including the Bagging regressor, KNN regressor, MLP regressor, RF regressor, and Lasso regressor.https://www.mdpi.com/1996-1073/15/17/6416gradient boosting modelgenetic algorithmoil productionoil priceoil demand |
| spellingShingle | Eman H. Alkhammash An Optimized Gradient Boosting Model by Genetic Algorithm for Forecasting Crude Oil Production Energies gradient boosting model genetic algorithm oil production oil price oil demand |
| title | An Optimized Gradient Boosting Model by Genetic Algorithm for Forecasting Crude Oil Production |
| title_full | An Optimized Gradient Boosting Model by Genetic Algorithm for Forecasting Crude Oil Production |
| title_fullStr | An Optimized Gradient Boosting Model by Genetic Algorithm for Forecasting Crude Oil Production |
| title_full_unstemmed | An Optimized Gradient Boosting Model by Genetic Algorithm for Forecasting Crude Oil Production |
| title_short | An Optimized Gradient Boosting Model by Genetic Algorithm for Forecasting Crude Oil Production |
| title_sort | optimized gradient boosting model by genetic algorithm for forecasting crude oil production |
| topic | gradient boosting model genetic algorithm oil production oil price oil demand |
| url | https://www.mdpi.com/1996-1073/15/17/6416 |
| work_keys_str_mv | AT emanhalkhammash anoptimizedgradientboostingmodelbygeneticalgorithmforforecastingcrudeoilproduction AT emanhalkhammash optimizedgradientboostingmodelbygeneticalgorithmforforecastingcrudeoilproduction |