Status : Verified
| Personal Name | Catan, Aizel Marie C. |
|---|---|
| Resource Title | Future pathways for ML and AI integration in Philippine weather forecasting: a scenario building approach |
| Date Issued | 17 December 2025 |
| Abstract | The Philippines is highly vulnerable to extreme weather events, making accurate and timely weather forecasting a critical public-sector function. However, existing forecasting systems remain heavily dependent on manual processes and resource-intensive numerical weather prediction (NWP), which pose limitations in scalability, speed, and adaptability to increasing climate variability. While recent advances in machine learning (ML) and artificial intelligence (AI) present opportunities to enhance forecasting performance, their adoption in the Philippine context requires careful assessment from a technology management perspective. This study examines the readiness of the Philippine weather forecasting system to integrate ML and AI-based predictive models, focusing on strategic, organizational, and institutional dimensions rather than technical model development. Using a technology foresight approach anchored in scenario building, the research evaluates key predictable variables and critical uncertainties affecting ML/AI adoption, including data and infrastructure maturity, human resource availability, governance and regulatory frameworks, funding mechanisms, and inter-organizational collaboration. STEEP and SWOT analyses, variable clustering and ranking, and expert interviews and surveys were used to construct four plausible future scenarios for ML and AI integration. The findings indicate that successful adoption of ML and AI-based weather forecasting is contingent on sustained government prioritization, strategic investment in data infrastructure and human capital, and effective coordination among government agencies, academic institutions, and private-sector partners. Based on the scenario outcomes, a strategic roadmap is proposed outlining short, medium, and long-term actions to support capability building, policy alignment, and resource allocation. The study concludes that ML and AI can significantly enhance the effectiveness of Philippine weather forecasting |
| Degree Course | Master of Technology Management |
| Language | English |
| Keyword | Machine learning; Artificial intelligence; Weather forecasting; Meteorology; Technology foresight |
| Material Type | Thesis/Dissertation |
Preliminary Pages
260.08 Kb
Category : P - Author wishes to publish the work personally.
Access Permission : Limited Access