About

Short Bio

Mohamed Farag is a PhD researcher at the University of Bonn, working within the AID4Crops unit on Uncertainty Quantification and Explainable Machine Learning for crop monitoring. His research focuses on developing robust, data-driven agricultural systems by combining conformal prediction, explainability methods, and deep learning to support decision-making in precision agriculture. He has published in leading journals and workshops including Computers and Electronics in Agriculture, IEEE Geoscience and Remote Sensing Letters, and ICCV/ECCV workshops.

Journey

Academic Journey

Study & Work Conferences
Career

Positions

PhD Student & Graduate R/T Assistant
University of Bonn — AID4Crops
2023 — present
Assistant Lecturer
German University in Cairo (GUC)
2022 — 2023
Visiting Researcher
Ruhr-Universität Bochum (RUB)
Jul — Sep 2022
Teaching Assistant
German University in Cairo (GUC)
2018 — 2022
Developer
Ain Shams University
2017 — 2018
Research

Publications

Journals
Enhancing Decision Support in Crop Production: Analyzing Conformal Prediction for Uncertainty Quantification
M. Farag, A. Emam, J. Leonhardt, R. Roscher
Computers and Electronics in Agriculture, 237, Part B, 2025 IF: 8.9
Confident Naturalness Explanation (CNE): A Framework to Explain and Assess Patterns Forming Naturalness
A. Emam, M. Farag, R. Roscher
IEEE Geoscience and Remote Sensing Letters IF: 4.0
Automatic Severity Classification of Diabetic Retinopathy Based on DenseNet and Convolutional Block Attention Module
M. M. Farag, M. Fouad, A. T. Abdel-Hamid
IEEE Access, vol. 10 IF: 3.6
Workshops
A Framework for Enhanced Decision Support in Digital Agriculture Using Explainable Machine Learning
A. Emam, M. Farag, J. Kierdorf, L. Klingbeil, U. Rascher, R. Roscher
ECCV 2024 Workshops, LNCS vol. 15625, Springer
Inductive Conformal Prediction for Harvest-Readiness Classification of Cauliflower Plants: A Comparative Study of Uncertainty Quantification Methods
M. Farag, J. Kierdorf, R. Roscher
ICCV 2023 Workshops, pp. 651–659
View all publications →
Teaching

Courses

University of Bonn
Explainable Machine Learning
Erfassung, Analyse und Modellierung von Phänotypen
Fortgeschrittene Verfahren zur Erfassung, Analyse und Modellierung von Heterogenität und Phänotypen
German University in Cairo
Teaching Assistant — Various courses (2018–2022)
Supervision

Student Supervision

MSc: Exploring the Sensitivity of Model Uncertainty to Hyperparameter Variations: A Systematic Analysis In collaboration with Fraunhofer
MSc: Exploring Deep Learning for Hazardous Material Detection: A Study in Anomalous Object Identification In collaboration with DLR
MSc: Investigating Optimal Data Dimensionality and Model Architecture for Naturalness Investigation Erasmus programme
BSc: Two external students supervised in collaboration with the German University in Cairo (GUC), on topics related to model uncertainty sensitivity in semantic segmentation and multi-class classification.