AI Meets Drones Summer Hackathon 2025
PagLab Hackathon: 2025
Abstract
This event is organized in conjunction with the Master’s course “Drone Remote Sensing Meets AI”, bringing together students and researchers to tackle real-world challenges at the intersection of drone remote sensing technology and artificial intelligence. Throughout the week, participants will work in teams to develop and test AI-powered solutions for processing drone-acquired imagery, addressing agricultural tasks such as object detection, classification of crop types or stress conditions, and regression-based trait prediction. The event fosters an interactive environment where cutting-edge UAV data meets machine learning workflows — encouraging innovation, collaboration, and critical thinking in precision agriculture.
The September 2025 hackathon “AI Meets Drones” challenged students to apply artificial intelligence and remote sensing techniques to real UAV-borne multispectral imagery of wheat. Participants worked with data from 216 plots across 18 varieties and three nitrogen treatments collected using a MicaSense RedEdge-MX Dual camera.
Over an intensive week, student teams performed reflectance extraction in QGIS, computed nitrogen- and biomass-responsive vegetation indices, and trained machine learning models for predicting crop nitrogen status and biomass. The hackathon concluded with four student presentations as well as reports.
Prof. Dr. Kang Yu
Professor of Precision Agriculture
My research interests include precision crop farming, hyperspectral remote sensing, and AI in agriculture.
Dr. Anirudh Belwalkar
Postdoctoral Researcher
My research interests include hyperspectral remote sensing of vegetation and precision agriculture.
Chenghao Lu
Research assistant & Joint Phd student
My research interests are Agricultural Digital Twin and Smart Breeding. My project focuses on the construction of a Digital Twin system for maize, aiming to fuse Genetic x Environmental x Management data to construct a high-precision and dynamically updated maize growth virtual twin. By introducing a DNA language model with a multimodal fusion approach, I hope to achieve accurate simulation of maize phenotypes and breeding to support sustainable agricultural development.