Ensemble modeling of the climate-energy nexus for renewable energy generation across multiple US states
Bibliographic record
Abstract
Abstract The effects of climate change on renewable energy generation are of growing concern, as shifts in weather patterns and extreme events can significantly impact energy production. This study aims to leverage machine learning models to predict renewable energy generation based on the surrounding climate. We analyze data from four key states: California, New York, Florida, and Georgia, and focus on three critical renewable energy sources: hydroelectric, solar, and wind power. To determine the optimal model, we test six primary machine learning techniques, as well as an ensemble and a mean-only baseline. The results indicate that the ensemble approach improves the predictive accuracy of the model. Using this ensemble, we projected the changes to climate-sensitive portion of the renewable energy generation under climate change. Our results indicated that there was a wide variation of possible futures, depending on the state, source, and season. For example, the model projected a reduction in California’s monthly total renewable energy generation in the summer by 0.5%, or about 30 000 MWh, under SSP5-8.5, the worst-case scenario, but an increase of 0.5%, or about 25 000 MWh, in New York’s monthly total summer renewable energy generation under the same scenario. The modeling techniques detailed in this study can be applied across new regions, sources, or time periods. Ultimately, by understanding the influence of climate on renewable energy generation, we can improve the long-term planning process for the electricity grid, while building resilience and ensuring sustainable climate change mitigation and adaptation.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".