Hybrid Climate Forecasting using Ensemble Learning and Trend Detection
Bibliographic record
Abstract
Understanding local climate change patterns is vital for establishing an effective adaptation plan, especially in climate-sensitive places like Rajshahi, Bangladesh. This study examines monthly temperature data from 1980 to 2024 to forecast future climatic conditions and find long-term trends using hybrid analytics, which integrates strong machine learning algorithms with standard statistical approaches. Sen's Slope estimator, Linear Regression, and the statistical model Mann-Kendall test were applied to do trend analysis during the first phase. These techniques exhibited a substantial growing trend in both maximum and minimum temperatures, which indicates a long-term warming signal. Three supervised models were employed to predict monthly temperatures for 2025–2027: Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Linear Regression (LR). The study employed three performance evaluation matrices for measuring model performance: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R2Score. Random Forest was best at the lowest temperature (R2 = 0.997, RMSE = 0.101°C). On the other hand, XGBoost performs well at the maximum temperature (R2 = 0.994, RMSE = 0.154°C) with exceptional precision. By studying the findings, this research acknowledges that the data-driven strategy at the regional climate trend assessment boosts the forecasting and trend analysis reliability by merging both machine learning and statistical techniques. Deep learning models and integrating new meteorological variables will be vital for future research to enhance prediction accuracy and scalability.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".