Predictive modelling and spatial flow analysis of United States of America crude oil imports
Bibliographic record
Abstract
The global energy system significantly dependent on crude oil and it is also a major driver of the transportation industry and petrochemical production. By 2040, oil and gas will likely account for over half of the universal energy mix due to increasing demands in various countries of the world, despite developing interest in renewable energy. The United States is a major importer of crude oil due to the role it plays in the country’s economy and energy requirements. Nevertheless, economic uncertainty and geopolitical tensions, such as the battle between Russia and Ukraine, weaken global oil markets. Hence, the need for countries to be able to understand how their supply would be affected. In order to enhance how countries can predict their future supply from different sources, this study evaluates the predictive performance of two machine learning (ML) models: Random Forest (RF), and Support Vector Regression (SVR) in relation to the commonly used Linear Regression (LR). Data of crude oil import from Iraq, Saudi Arabia, Venezuela, Mexico, Canada and Russia into the USA from 1973 to 2023 was obtained for the study from Energy Information Administration. The data were subjected to clearing. Afterwards, 80% of the data was trained while 20% were used to test the predictive performance of the three models by predicting the import flows from 2024 to 2033. Metrics used for the test were root-mean-squared error (RMSE) and mean absolute error (MAE). Maps were used to visualise the flow of the crude oil imports from each country based on the data and the prediction of the three models. With an RMSE of 259.35 and an MAE of 169.17, Random Forest scored better than the other models, showing balanced geographical flows and high predicted accuracy from important importers like Saudi Arabia and Canada. On the other hand, due to their difficulties with nonlinear dynamics, SVR (RMSE: 568.04, MAE: 365.99) and Linear Regression (RMSE: 538.02, MAE: 384.77) performed poorly. Random Forest's ability to forecast import volumes and optimize trade routes was confirmed by spatial flow maps. The result suggest that energy security and supply chain resilience can be improved by incorporating ML models and geographical analysis into energy planning. Keywords: Crude Oil, Machine learning, Random Forest, Linear Regression, Support Vector Regression.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".