doi: 10.7763/IJCTE.2026.V18.1394
Interpretable Machine Learning for Ambient Temperature Prediction: Insights from SHAP, ICE, PDP, and ALE
Hirushan Sajindra1,2
,
Thilina Abekoon2 ,
Salani Buthpitiya3 ,
Yasitha Alahakoon4 ,
Namal Rathnayake5 ,
Komali Kantamaneni6,7 ,
Upaka Rathnayake1,*
- 1Faculty of Engineering and Design, Atlantic Technological University, Sligo, F91 YW50, Ireland
- 2Water Resources Management and Soft Computing Research Laboratory, Millennium City, Athurugiriya, 10150, Sri Lanka
- 3Department of Chemistry, Faculty of Science, University of Kelaniya, 11600, Sri Lanka
- 4Department of Civil Engineering, Faculty of Engineering, University of Peradeniya, Peradeniya, Sri Lanka
- 5Advanced Institute for Marine Ecosystem Change (WPI-AIMEC), Japan Agency for Marine-Earth Science and Technology (JAMSTEC), Yokohama 236-0001, Japan
- 6United Nations-SPIDER-UK Regional Support Office, Preston PR1 2HE, United Kingdom
- 7School of Engineering and Computing, University of Lancashire, Preston PR1 2HE, United Kingdom
- Manuscript receivedAugust 29, 2025
- revisedDecember 15, 2025
- acceptedMarch 19, 2026
- publishedMay 16, 2026
Abstract
Accurate ambient temperature prediction is essential for climate monitoring, urban planning, and environmental management, particularly in regions experiencing rapid climatic variability such as Sri Lanka. This study investigates the application of explainable machine learning models for short-term ambient temperature prediction in Battaramulla, Sri Lanka. Five regression algorithms-K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Regression (SVR), and Histogram-based Gradient Boosting Regressor (HGBR) were evaluated using 14 meteorological and environmental predictors, including temporal variables, relative humidity, solar radiation, rainfall, wind speed, and air pollutant concentrations (CO2, NOₓ, CH4, O3, CO, PM2.5, and PM10). Among the models tested, HGBR demonstrated superior predictive performance, achieving R² values of 1.00 (training) and 0.96 (testing), with corresponding mean squared error values of 0.01 and 0.11. Model interpretability was examined using SHapley Additive exPlanations (SHAP), Partial Dependence Plots (PDP), Individual Conditional Expectation (ICE) analyses, and Accumulated Local Effects (ALE), which identified several features as the most influential predictors. Model validation using 192 real-time observations showed close agreement between predicted and measured temperatures, although the evaluation was limited to a single location and time period. A web-based application, ‘Therma’, was developed to facilitate practical deployment of the model for localized temperature estimation. Overall, this study demonstrates the utility of explainable machine learning for localized climate prediction while highlighting the need for broader spatiotemporal validation in future work.
Keywords
- ambient temperature
- explainable artificial intelligence
- Histogram-Based Gradient Boosting Regression (HGBR)
- prediction
How to Cite
Hirushan Sajindra, Thilina Abekoon, Salani Buthpitiya, Yasitha Alahakoon, Namal Rathnayake, Komali Kantamaneni, and Upaka Rathnayake, "Interpretable Machine Learning for Ambient Temperature Prediction: Insights from SHAP, ICE, PDP, and ALE," International Journal of Computer Theory and Engineering, vol. 18, no. 2, pp. 118-132, 2026. https://doi.org/10.7763/IJCTE.2026.V18.1394
Copyright & License
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).