I am a researcher dedicated to developing and refining explainable prediction algorithms, particularly for applications in environmental monitoring, healthcare, and transportation. My primary focus is on creating transparent, interpretable models that offer actionable insights across critical areas.My work in environmental monitoring includes building low-cost IoT devices for air quality analysis, with a particular emphasis on identifying pollution sources and understanding their dynamics. I use explainable machine learning algorithms to generate interpretable predictions, helping policymakers and stakeholders make informed decisions to improve air quality. In addition to environmental applications, I apply algorithms in healthcare to support preliminary disease diagnosis through image analysis. My research portfolio also includes transportation, where I use machine learning to improve travel time predictions. During my research assistancy in Japan, I worked on prediction models for both travel time and PM2.5 level forecasting. This experience deepened my understanding of spatio-temporal modelling and complex, data-driven predictions.Currently, I leverage advanced techniques like Graph Neural Networks (GNNs) for spatio-temporal predictions and making explainable predictions more accessible to decision-makers. I am eager to connect with professionals and collaborators who share an interest in explainable AI, IOT-ML and its applications in solving real-world challenges.