黑料福利网

Topic 

Introductory Workshop on Machine Learning for Spatial Analysis in ArcGIS Pro

Abstract

Geospatial data is growing rapidly in both volume and complexity, making traditional analytical approaches less effective in capturing patterns, relationships, and dynamics. Machine learning provides powerful methods to understand geospatial associations, improve predictive accuracy, and generate insights into spatial processes. For example, it can be applied to predict urban heat islands, classify land cover from satellite imagery, or assess spatial health risks using data such as census records, satellite images, or GPS-based mobility traces.

This workshop introduces participants to the use of machine learning techniques for spatial analysis within ArcGIS Pro. It will cover key tools such as Geographically Weighted Regression, classification and regression methods, and SHAP (a game-theoretic approach to explain model outputs). Applications will include exploring spatial associations within datasets and performing image-based spatial analysis.

The workshop is designed as an accessible introduction and does not require prior experience. Through hands-on exercises, participants will gain a foundational understanding of how machine learning can be applied to spatial problems, providing a basis for deeper exploration beyond the workshop.

About the speaker

Bardia Mashhoodi is an Associate Professor in Urban Environment at the School of Computing and Mathematical Sciences, Faculty of Engineering and Science, University of Greenwich. At present, his role is to develop multidisciplinary studies in collaboration with colleagues from mathematical sciences, mechanical engineering, evacuation engineering, and fire safety. Bardia has a multidisciplinary background, having trained in four different disciplines: industrial engineering (BSc), architecture engineering (BSc), spatial planning (MSc), and human geography (PhD). He has more than 40 scientific publications on (1) household energy consumption and poverty, (2) environmental inequalities, (3) electric vehicle infrastructure, (4) spatial morphology, (5) citizens鈥� views on the EU, and (6) drone-based logistics.

Bardia has led several large-scale, transdisciplinary Dutch and Sino-European research projects as the Principal Investigator (PI), focusing on energy transition, mobility, and the built environment.

Between 2010 and 2021, he contributed to six municipal, Dutch, and European projects in various roles. Additionally, between July 2021 and January 2024, he served as Assistant Professor of Digital Landscape at Wageningen University and Research (WUR), where he was Research Coordinator and Member of the Daily Board at the Landscape and Spatial Planning Group.

Since 2016, Bardia has taught various urban geography and planning courses at WUR, Delft University of Technology (TU Delft), and Erasmus University in the Netherlands. His teaching contributions include:

• Founder and coordinator of the Geographic AI course at WIMEK PhD school (2023-2024).
• Lecturer and coordinator of the MSc Planning for Urban Quality of Life studio and the BSc Mobility and Network Infrastructures course (2020-2024) at WUR.
• Instructor for the Regional Technology course (2016-2019) at TU Delft, teaching post-master (EMU) students.

Since 2025, Bardia is a member of the Quantitative Geography Committee at the Royal Geographic Society, UK, and serves as the 鈥淒issertation Prize Officer鈥�.

Your host

Gamze Dane, Assistant Professor at the department of the Built Environment.

Registration is required but free of charge.