Improving Hybrid Models for Precipitation Forecasting by Combining Nonlinear Machine Learning Methods
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Precipitation forecast is key for water resources management in semi-arid climates. The traditional hybrid models simulate linear and nonlinear components of precipitation series separately. But they do not still provide accurate forecasts. This research aims to improve hybrid models by using an ensemble of linear and nonlinear models. Preprocessing configurations and each of the Gene Expression Programming (GEP), Support Vector Regression (SVR), and Group Method of Data Handling (GMDH) models were used as in the traditional hybrid models. They were compared against the proposed hybrid models with a combination of all these three models. The performance of the hybrid models was improved by different methods. Two weather stations of Tabriz and Rasht in Iran with respectively annual and monthly time steps were selected to test the improved models. The results showed that Theil’s coefficient, which measures the inequality degree to which forecasts differ from observations, improved by 9% and 15% for SVR and GMDH relative to GEP for the Tabriz station. The applied error criteria indicated that the proposed hybrid models have a better representation of observations than the traditional hybrid models. Mean square error decreased by 67% and Nash Sutcliffe increased by 5% in the Rasht station when we combined the three machine learning models using genetic algorithm instead of SVR. Generally, the representation of the nonlinear models within the improved hybrid models showed better performance than the traditional hybrid models. The improved models have implications for modeling highly nonlinear systems using the full advantages of machine learning methods.
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.
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 | 0.002 | 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 | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| 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 it