Uncategorized

Researcher “Geoprocessing workflow modelling using large language models” — AcademicTransfer


Recently, there has been a significant breakthrough in artificial intelligence (AI) with the development of Large Language Models (LLMs). Trained on vast datasets (encompassing a wide range of knowledge from diverse sources), LLMs have shown an impressive capability to elaborate context-sensitive human-like text and respond to complex queries coherently. Moreover, LLMs have shown surprising emergent abilities in complex tasks, like instruction following, arithmetic calculations, logical reasoning, and code generation/debugging. These specialised applications of LLMs are revolutionising industries by providing accurate, timely, and context-aware solutions, promising a future where AI seamlessly integrates into various professional domains, including spatial analysis and modelling.

You will work on an innovative project entitled “IntelliGeo: Laying the Groundwork for Integrating Large Language Models into GIS.” This project aims to improve geographical modelling by integrating LLMs with open-source GIS platforms. Our goal is to enable AI and human authorities to collaboratively design intricate models to address challenges such as flood detection, crop yield estimation, and prediction of environmental changes. By joining our team, you will contribute to cutting-edge research at the intersection of Geospatial Information Science (GIScience) and AI, advancing both fields and championing a European vision of human-centric AI.

The work spans from developing the basic functionalities of a QGIS plugin to prompt engineering and fine-tuning of a selected LLM based on the user-generated data gathered by the plugin. Specifically, you will be collaborating closely with the Principal Investigator (PI) and a Research Engineer (RE) to develop IntelliGeo, a plugin for QGIS that leverages LLMs for enhancing geoprocessing workflow modelling. You will also be contributing to generating a fine-tuning dataset for GIS tasks, engaging in the preliminary fine-tuning of LLMs using the generated dataset, and contributing to assessing the efficacy of the fine-tuned LLMs for GIS tasks. You will be participating in workshops and conferences to introduce IntelliGeo to the GIS community and gather feedback and will be collaborating with partners, including the Barcelona Supercomputing Center, to implement and refine LLMs.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *