This presentation introduces an innovative project designed to enhance the precision of urban nuclei mapping using advanced artificial intelligence techniques. The focus is on improving the urban nuclei layer managed by the Institut Cartogràfic i Geològic de Catalunya (ICGC) through the application of convolutional neural networks (CNNs). The project involves training a CNN model on a curated collection of images featuring diverse urban nuclei. This training process enables the model to learn intricate patterns and characteristics unique to urban areas. Once the model is adequately trained, it can autonomously detect and categorize urban nuclei in new images with high accuracy.

In the ever-evolving realm of geospatial technology, developing QGIS plugins that are both reliable and adaptable for web environments is essential. This talk will provide practical insights into creating QGIS plugins that perform well across both QGIS desktop and QGIS Web Client (QWC2).

Key areas of focus include:

• Database-Driven Design: Explore how a database-driven approach can enhance both the functionality and user interface of QGIS plugins. This method simplifies development by allowing dynamic configuration and management of plugin features and UI elements based on backend data, ensuring seamless integration with various data sources and use cases.

• Qt Forms as a Service: Learn how to implement Qt Forms as a service, where forms are dynamically generated and customized according to backend configurations. This approach facilitates the creation of adaptable and maintainable user interfaces that respond efficiently to different data inputs and user needs.

Through the Giswater plugin case study, this talk will showcase these concepts with practical examples. Attendees will gain valuable insights into building web-ready QGIS plugins that are robust, flexible, and user-friendly across diverse platforms.