Mahdi Farnaghi
I am an Assistant Professor at the University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC), Department of Geo-Information Processing (GIP), Enschede, The Netherlands.
My primary research interest has been in the intersection of artificial intelligence (AI) and geodata processing (or GeoAI, in short). During Ph.D., I worked on solutions based on semantic web concepts/technologies and AI to generate geodata processing workflows automatically. After the Ph.D., I extended my research further into the spatial data science and big data processing fields. I have been using machine learning (ML) for spatiotemporal modeling in different application areas, including environmental monitoring, analysis and assessment, disaster management, and spatial epidemiology. I exploited big data processing technologies and deep learning (DL) methods to extract information from the massive amount of spatial data collected for environmental phenomena. I have also been working on geospatial social media analysis using ML methods. I am interested in exploiting new technologies like blockchain and distributed ledgers to tackle the need for security and accountability in the geospatial domain.
Currently, I am working in the following directions:
- Spatial and spatiotemporal effects in modeling using ML/DL
- eXplainable Artificial Intelligence (XAI)
- Spatial data fusion
- MLOps and automation of geoprocessing workflows
Sessions
In a project funded by the Ai NED program, we are developing a plugin, named IntelliGeo, that integrates general-purpose Large Language Models (LLMs) into QGIS. The idea is to use the modelling power of LLMs to facilitate the generation of Geoprocessing workflows in the Model Designer of QGIS. In this plugin, an LLM plays the role of a modelling assistant that receives the user’s instructions and develops a Geoprocessing workflow based on the provided specification, accounting for the geoprocessing tools in QGIS and the loaded data in the table of contents. The plugin also helps the user to improve the model iteratively through verbal instructions.
The interactions between users and the LLM through the plugin are recorded. These records will be used afterwards to fine-tune the LLMs and improve their ability to solve GIS problems.
The first release of the plugin will be available in the coming months. In the workshop, we will introduce the plugin to the QGIS community, receive their requirements and opinions about the future direction of the plugin, and seek collaborators for the project. The program for the workshop will be as follows:
15:30 – 15:45 | Introduction to the IntelliGeo plugin
15:45 – 16:00 | Installation of the IntelliGeo plugin
16:00 – 16:30 | Interactive demonstration
16:30 – 16:45 | Individual testing
16:45 – 17:00 | Feedback
You can download the demo project from the resources.
IntelliGeo requirements:
- langchain_cohere >= 0.1.9
- langchain_openai >= 0.1.6
- pyperclip >= 1.3.0
- langchain >= 0.2.2
- requests >= 2.31.0
- psutil~=6.0.0