Maruf Ahmed
I am a young researcher and engineer passionate about climate change impact assessment, ecosystem service assessment, disaster resilience, and environmental sustainability. With a strong academic foundation in Civil Engineering (BSc), Humanitarian Engineering (MSc), and Environmental Economics (MEcon), I bring an interdisciplinary approach to solving complex environmental and societal challenges. My work integrates hydrological modeling, GIS-based analysis, machine learning, and multi-criteria decision analysis (MCDA) to assess climate risks and develop sustainable solutions.
Session
This study introduces a behavior-dependent, unsupervised machine learning approach to assess the intrinsic quality of OpenStreetMap (OSM) data in Dhaka, which is both data-starved and urbanizing rapidly urbanizing area. Leveraging enriched contributor metadata and Principal Component Analysis (PCA), latent behavioral patterns and segmented contributors identified using KMeans and HDBSCAN. The silhouette score for PCA-based clustering was 0.951. The results show superior interpretability of KMeans over HDBSCAN. This repeatable methodology provides a scalable and reference-free solution to take quality assurance of VGI datasets to the front-line, in cases of limited or no authoritative data.