GIS-Enhanced River Stage Prediction for Ungauged Basins: A Case Study of the Upper Ping River Basin, Thailand
Bibliographic record
Abstract
Accurate prediction of river stage in ungauged basins is essential for flood forecasting and water resource management, particularly in regions with limited observational data.This study investigates the integration of Geographic Information Systems (GIS) enhanced reanalysis data with machine learning (ML) techniques to predict river stage levels in the Upper Ping River Basin, northern Thailand.Five years of hourly hydrometeorological variables from the ERA5-Land dataset, combined with observed river stage measurements from the P.1 Hydrological Station, were used to train and evaluate four ML models: Random Forest Regression (RFR), Extreme Gradient Boosting (XGB), Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP).Bayesian hyperparameter optimization and five-fold cross-validation were employed to ensure robust model training and evaluation.Among the models, XGB achieved the highest accuracy with an R² score of 0.9882, followed by RFR (0.9792), while SVR and MLP exhibited lower performance and higher sensitivity to data variability.Feature importance was further examined using SHapley Additive exPlanations (SHAP), revealing that runoff and soil moisture variables contributed most significantly to model performance, while wind, temperature, and even precipitation showed comparatively lower influence.A feature exclusion analysis confirmed that removing the top 14 ranked features substantially reduced prediction accuracy, underscoring their importance.The results highlight the potential of interpretable ML models combined with high-resolution GIS-based data for reliable river stage prediction in data-scarce regions.This framework offers promising applications in real-time flood forecasting and hydrological decision-making.
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) | 0.001 | 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 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".