2025-10-04 –, Talks I
This project aims to combine AI‐generated building predictions from fAIr with crowdsourced validation and conflation workflows in MapSwipe, ultimately pushing high‐confidence conflated map data into OpenStreetMap (OSM).
fAIr is an AI‐powered mapping assistant by HOT that helps users map smarter, faster, and more accurately.
MapSwipe is a crowdsourcing app that lets volunteers validate or identify features (e.g. buildings) quickly on satellite imagery.
Objectives
- Automate the creation of MapSwipe projects from fAIr (with building predictions, TMS layers, etc.).
- Validate AI‐predicted features via MapSwipe’s volunteer workflow via redundancy.
- Conflate validated features with existing OSM data.
- Upload conflated data back to OSM in a controlled, conflict‐aware manner.
- Provide feedback to improve fAIr's AI models based on volunteer validation results and possibly task the tasking manager to manually map the parts that are difficult to validate via MapSwipe.
An integration between 2 community applications
Omran NAJJAR is the AI Product Owner in Humanitarian OpenStreetMap Team with +17 year experience in software engineering, advanced data management and artificial intelligence. Omran holds a MSc Computer Science, Turkey (2020) and a MSc in Data Analytics and ISM, Germany (2023) with research focus on spatial and temporal analysis on OSM - Nepal. Omran has been working in humanitarian and development context since 2014, specialized in monitoring and evaluation and AI for social good. Currently, Omran uses that experience to pursue justice, ethical and open source tech to amplify the connection between human[itarian] needs and open map data.