The accelerating pace of climate change and the growing demand for reliable meteorological and hydrological services highlight the urgent need to modernize training approaches in our field. Traditional pedagogical methods, while essential, are no longer sufficient to prepare professionals for increasingly complex, data-intensive, and rapidly evolving operational environments. Artificial Intelligence (AI) and emerging digital technologies now offer unprecedented opportunities to bridge this capacity gap by enabling interactive, adaptive, and immersive learning experiences.

This presentation examines how AI can be systematically integrated into meteorological and hydrological training, drawing upon my expertise in mathematics, machine learning, and hydrometeorology, as well as recent educational developments at the Institut Hydrométéorologique de Formation et de Recherches (IHFR). I will explore three key domains where AI is reshaping the way we learn, teach, and assess competencies:

  • Interactive and Immersive Learning
AI-powered simulations, virtual laboratories, and adaptive e-learning platforms allow learners to interact with meteorological processes and models in real time. These tools support a deeper conceptual understanding by simulating extreme weather events and enabling trainees to practice forecasting and decision-making strategies in safe, controlled environments.

  • Data-Driven Training and Assessment
Machine learning techniques provide powerful support for personalized learning. By analyzing trainee performance, AI can detect knowledge gaps, recommend targeted resources, and optimize learning pathways. Intelligent assessment systems further enhance feedback quality, offering detailed insights beyond simple correct/incorrect responses and promoting stronger analytical skills.

  • Ethics, Reliability, and Trust in AI Integration
The integration of AI into training must be accompanied by careful consideration of its risks—data bias, transparency, data protection, and regulatory compliance. Through case studies involving AI-based imputation of long-term meteorological datasets, I will illustrate both the potential and the limitations of these tools in educational contexts, especially when dealing with incomplete or heterogeneous data.

The presentation will share practical lessons learned from developing and implementing AI-supported modules at IHFR, emphasizing both the opportunities for enhancing learner engagement and the challenges related to data quality, digital infrastructure, and institutional readiness. A key message is the continued importance of human oversight: AI should augment, not replace, the educator. The role of instructors as mentors, interpreters, and ethical stewards remains central.

By the end of this presentation, you will gain a clear and actionable vision of how AI can be responsibly adopted as a catalyst for innovation - strengthening the integrity, reliability, and inclusiveness of meteorological training. This aligns with the broader WMO mission: preparing a new generation of meteorologists and hydrologists who are both technically skilled and capable of critically engaging with the digital tools shaping the future of climate and weather services.

Please click the image below to download the presentation.


Thank you,

Abdelillah Otmana Cherif - IHFR



Última modificación: martes, 25 de noviembre de 2025, 22:15