Zahra Farahzadi
Doctoral Student
Anomaly detection and diagnosis in smart greenhouses
Develops a probabilistic framework for detecting and diagnosing anomalies in greenhouses, combining physics-informed modelling, uncertainty quantification and causal reasoning — so that sensor drift can be told apart from an actual equipment failure.
Research project
Anomaly detection and diagnosis in smart greenhouses
Uncertainty-aware probabilistic AI framework for detecting and diagnosing anomalies in smart greenhouse energy systems.
Learn more →Publications (1)
- Context-Aware Deep Learning–Based Probabilistic Detection of Energy Anomalies in Smart Greenhouses Under Uncertainty — 2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET) Conference