https://journalarsvot.com/index.php/ajvah <p><strong>Asian Journal of Vocational Education and Humanities (AJVAH) [ISSN 2735-0215 eISSN 2735-1165]</strong> is a peer-reviewed international journal which welcomes submission involving a critical discussion of policy and practice, as well as contributions to conceptual and theoretical developments in the field not only restricted in the context of Asian region but also open to other regions. It includes articles based on empirical research and analysis (qualitative, quantitative and mix method), systematic literature review and short communication in which it welcomes papers from a wide range of disciplinary in the context of education and inter-disciplinary perspectives vocational and humanities.</p> Association for Researcher of Skills and Vocational Training en-US Asian Journal of Vocational Education And Humanities 2735-0215 https://journalarsvot.com/index.php/ajvah/article/view/930 <p style="font-weight: 400;">Fine particulate matter (PM2.5) prediction in tropical coastal industrial zones is complicated by continuous industrial emissions, localized precipitation, sea-breeze circulation, and humidity-related measurement effects. This study developed a comparative and interpretable framework for daily PM2.5 estimation in the Perai Heavy Industrial Zone, Penang, using 97 concurrent observations from 2025-2026. Four meteorological predictors--temperature, wind speed, pressure, and precipitation--were evaluated with Multiple Linear Regression (MLR), Support Vector Regression (SVR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). MLR achieved the strongest baseline predictive performance, indicating that simple linear structure can remain competitive when sample size is limited and temporal leakage is controlled. XGBoost was retained for interpretation because it captured non-linear local interactions more effectively than the other ensemble alternative. SHapley Additive exPlanations (SHAP) identified temperature and precipitation as the dominant drivers. The positive precipitation-PM2.5 relationship suggests that hygroscopic aerosol growth and optical sensor response may partly offset the expected wet-scavenging effect in this setting. The findings show that localized, interpretable modelling can support air-quality warning, sensor calibration, and meteorology-sensitive emission management in tropical industrial regions.</p> Hongzhi Lu Hongxue Lu Copyright (c) 2026 Hongzhi Lu, Hongxue Lu https://creativecommons.org/licenses/by-nc-sa/4.0 2026-05-27 2026-05-27 7 1 1 8 10.53797/ajvah.v7i1.1.2026