Our Research Portfolio
The SmAIL Research Group applies advanced artificial intelligence to solve critical challenges in agriculture, forestry, and energy systems. Our translational research is driven by a dynamic portfolio of internal initiatives and third-party funded projects executed with external collaborators, allowing us to bridge the gap between academic innovation and real-world application.
Internal Research Initiatives
Automated Weed Detection System
We are developing novel methods leveraging foundation models with the aim of reducing the need for training data while maintaining prediction performance and improving generalizability of weed detection models. Read more.
Automated Animal Monitoring System
We investigate computer vision and multimodal machine learning methods for AI-based automated animal monitoring, aiming to enhance animal welfare and biodiversity while reducing reliance on manual observation. Read more.
Genotype-Phenotype Relationship
We use deep learning to decode links between genetics and observable traits, fast-tracking the development of climate-adaptable, high-yield crop varieties. Read more.
Third-Party Funded Research Initiatives
PeroHop4.0: Prevention of Plant Diseases
We combine AI with automated smart traps to create a highly accurate early warning system for hop farmers to optimize fungicide applications and prevent crop loss. Read more.
smartBattery: Energy Storage Optimization
Our data-driven “smartBattery Toolbox” leverages machine learning to optimize energy dispatch, mitigate grid congestion, and accelerate renewable energy integration. Read more.
smartReForest: Resilient Reforestation
We develop AI-driven decision support systems synthesizing ecological data to ensure newly planted forests are optimized for climate resilience and long-term survival. Read more.