About

Short Bio

I am a PhD researcher at the University of Bonn, working within the AID4Crops unit under the supervision of Prof. Dr. Ribana Roscher. My research explores the intersection of Uncertainty Quantification (UQ) and Explainable Machine Learning (XAI) for crop monitoring, with the goal of building more robust and interpretable data-driven agricultural systems. I have a background in deep learning architectures, self-supervised learning, and statistical modelling, and I apply these methods to precision agriculture and geospatial challenges. Alongside my research, I mentor BSc and MSc students, contribute to course organisation, and collaborate on interdisciplinary projects across institutions including Fraunhofer, DLR, and Ruhr-Universität Bochum.

Career

Positions

PhD Student & Graduate Research/Teaching Assistant
University of Bonn — Institute of Geodesy and Geoinformation
July 2023 — present
Visiting Researcher
Ruhr-Universität Bochum (RUB)
July 2022 — Sept 2022
Assistant Lecturer
German University in Cairo (GUC)
Aug 2022 — Jan 2023
Teaching Assistant
German University in Cairo (GUC)
Sept 2018 — Aug 2022
MSc Electronics Engineering — GPA 0.7 (German scale)
German University in Cairo (GUC)
Dec 2020 — May 2022
MSc Electrical Power Engineering — GPA 3.73
Ain Shams University, Cairo
March 2019 — Dec 2020
BSc Energy and Renewable Energy Engineering — GPA 3.82
Ain Shams University, Cairo
Sept 2013 — June 2018
Updates

News

Feb 2026 I am co-organizing the CVPPA workshop this year in ECCV2026!.
Jan 2026 Our paper on "Your Paper Title Here" was accepted at a top venue.
Nov 2025 Organizing the Workshop on Your Topic at a major conference, coming April 2026.
Research

Selected 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, 110559, 2025 Journal · IF 8.9 · Q1
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 Journal · IF 4.0 · Q1
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 Journal · 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
Computer Vision – ECCV 2024 Workshops. LNCS vol. 15625. Springer Workshop
Self-Supervised and Unsupervised Multispectral Anomaly Detection for Unknown Substance and Surface Defect Identification
C. Beyaz, M. Farag, P. Schütt, T. Hecking, J. Grzesiak, C. Geiß, R. Roscher
Northern Lights Deep Learning Conference (NLDL), PMLR 307:27–38, 2026 Workshop
Inductive Conformal Prediction for Harvest-Readiness Classification of Cauliflower Plants: A Comparative Study of Uncertainty Quantification Methods
M. Farag, J. Kierdorf, R. Roscher
IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, pp. 651–659, 2023 Workshop
View all publications on Google Scholar →
Teaching

Courses

University of Bonn
Explainable Machine Learning Uni Bonn
Erfassung, Analyse und Modellierung von Phänotypen Uni Bonn
Fortgeschrittene Verfahren zur Erfassung, Analyse und Modellierung von Heterogenität und Phänotypen Uni Bonn
German University in Cairo
Circuits I & II GUC
Power Electronics GUC
Software

Apps & Projects

Conformal Prediction Toolkit ↗
Inductive conformal prediction methods for classification and dense prediction in agricultural remote sensing.
XAI for Crop Monitoring ↗
GradCAM, attention maps, and integrated gradients applied to deep learning models for crop analysis.
Self-Supervised Agriculture ↗
DINO, BarlowTwins, and SwAV implementations for representation learning in precision agriculture.
Anomaly Detection (Multispectral) ↗
Unsupervised and self-supervised anomaly detection for unknown substances and surface defects.