Mehak Khan
Field of work
I am an AI and Data Science professional with expertise in machine learning, deep learning, and data-driven solutions across both industry and academia. My work spans time series analysis, graph neural networks (GNNs), computer vision, explainable AI (XAI), and Earth observation, with a strong focus on developing AI models that deliver real-world impact through intelligent, human-centered design.
I hold a Ph.D. in Computer Science and Technology from the Harbin Institute of Technology, where I specialized in end-to-end deep learning techniques for time series classification. My research has been published in leading scientific journals and contributes to advancements in modern AI methodologies.
Currently, I serve as an Associate Professor of Computer Science at the Western Norway University of Applied Sciences (HVL), where I teach, supervise, and lead research in applied artificial intelligence.
Prior to this, I worked as a Postdoctoral Fellow at HVL, contributing to the ESA-funded GridEyeS project, which focused on intelligent power grid monitoring using satellite imagery and machine learning.
Before joining HVL, I was a Senior Researcher at Oslo Metropolitan University, where I contributed to the EU-funded REFSA project. My work involved developing AI-powered tools for knowledge discovery in the food safety domain, designing graph neural networks for citation network analysis, and automating systematic literature reviews using NLP and graph-based methods.
Beyond academic research, I have hands-on experience in building, deploying, and optimizing scalable AI solutions. My technical expertise includes end-to-end machine learning development, MLOps, and large-scale AI systems using Python, Kubernetes, Docker, and cloud platforms.
My approach to AI development is grounded in the principles of soft engineering and systems thinking, ensuring that intelligent systems are not only technically robust but also explainable, sustainable, and aligned with human and organizational needs.
I actively contribute to the AI research community as a reviewer for top-tier machine learning journals and conferences, mentor students and early-career researchers, and engage in collaborative interdisciplinary projects.
I am passionate about solving complex real-world problems through AI, driving innovation, and applying advanced machine learning and soft engineering techniques across diverse domains.
Publications
-
SARMoistX: temporal forecasting of vegetation moisture using SAR imagery
-
Forecasting day-ahead electric power prices with functional data analysis
-
T2SR: Super-Resolution in Smart Meter Data Using a Transformer-Based Framework
-
Semantically aware tree height estimator for infrastructure monitoring using multimodal satellite images
-
Transformer-based land use and land cover classification with explainability using satellite imagery