Temporally Robust Rainfall Classification from Radiosonde-Derived Atmospheric Instability Indices: A Machine Learning Approach with SHAP Interpretability
Open Access
- 9 October 2026
- journal article
- research article
- Published by MDPI AG in Meteorology
- Vol. 5 (4) , 36
Abstract
We evaluate binary rainfall occurrence classification in southern Thailand using 00 UTC radiosonde profiles from Phuket Airport and rainfall observations at Phuket, Krabi, Takua Pa (Phang-nga) and Nakhon Si Thammarat. Of 2631 soundings from 2011 to 2021, 1487 met quality-control and layer-continuity criteria. Five classifiers (logistic regression, support vector machines, random forests, extreme gradient boosting, and multilayer perceptrons) were evaluated using year-grouped cross-validation (2011–2019) and a chronological holdout (2020–2021). Holdout receiver operating characteristic area under the curve (ROC-AUC) reached 0.845 at Phuket, 0.793 at Krabi and 0.873 at Takua Pa, exceeding station-specific climatological baselines. At Nakhon Si Thammarat, the maximum holdout ROC-AUC was 0.691, indicating reduced spatial representativeness. Tree-based Shapley Additive Explanations (TreeSHAP) identified the K-index as the leading thermodynamic contributor across western stations, with geographically varying secondary contributions. Because daily rainfall windows include pre- and post-sounding periods, separate six-hour post-sounding evaluations (07:00–13:00, 13:00–19:00 and 19:00–01:00 local time) were conducted. Evening discrimination was consistently lower than morning discrimination across station–classifier combinations. A localized terrain–wind proxy provided negligible improvement. These results support temporally validated, station-specific rainfall occurrence classification while highlighting spatial representativeness and lead-time limitations for prospective operational use.Keywords
Funding Information
- University of Phayao
This publication has 19 references indexed in Scilit:
- Influence and variability of monsoon trough and front on rainfall in ThailandInternational Journal of Climatology, 2021
- From local explanations to global understanding with explainable AI for treesNature Machine Intelligence, 2020
- Evaluation of Machine Learning Classifiers for Predicting Deep ConvectionJournal of Advances in Modeling Earth Systems, 2019
- Cross‐validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structureEcography, 2017
- XGBoost2016
- Long-term trends and variability of total and extreme precipitation in ThailandAtmospheric Research, 2016
- On the use of cross-validation for time series predictor evaluationInformation Sciences, 2012
- Random ForestsMachine Learning, 2001
- Flash Flood Forecasting: An Ingredients-Based MethodologyWeather and Forecasting, 1996
- Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple TestingJournal of the Royal Statistical Society Series B: Statistical Methodology, 1995