Mr. Francisco Mena | Machine Learning | Best Researcher Award

PhD Candidate at University of Kaiserslautern-Landau, Germany

Francisco Mena is a PhD candidate in Computer Science at the University of Kaiserslautern-Landau (RPTU), Germany, with a strong academic and research background in deep learning, multi-view learning, and unsupervised learning. His work focuses on developing scalable and generalizable machine learning models, particularly in complex real-world domains like Earth observation and astroinformatics, where missing data and multi-source fusion are major challenges. Francisco’s research emphasizes minimizing human intervention and domain dependency, aiming for methods that are more robust, adaptable, and explainable.

Publication Profile 

Orcid

Educational Background 🎓

• PhD in Computer Science
  University of Kaiserslautern-Landau (RPTU), Germany
  Jan. 2022 – Present
  Thesis: Data Fusion in Multi-view Learning for Earth Observation Applications with Missing Views

• Magíster en Ciencias de la Ingeniería Informática (Equivalent to M.Sc. in Computer Engineering)
  Federico Santa María Technical University (UTFSM), Valparaíso, Chile
  Mar. 2018 – Sep. 2020
  Thesis: Mixture Models for Learning in Crowdsourcing Scenarios
  GPA: 94%

• Ingeniería Civil en Informática (Equivalent to Computer Engineering)
  UTFSM, Santiago, Chile
  Mar. 2013 – Sep. 2020
  GPA: 80% | Rank: Top 10% – 4th of 66 students

• Licenciado en Ciencias de la Ingeniería Informática
  UTFSM, Santiago, Chile
  Mar. 2013 – Nov. 2017

• High School
  New Little College, Santiago, Chile
  Mar. 2008 – Dec. 2012

Professional Experience 💼

• Student Research Assistant – German Research Centre for Artificial Intelligence (DFKI), Germany
  Mar. 2022 – Present
  Working on Earth observation data for crop yield prediction using Python, QGIS, and Slurm.

• Lecturer – University of Kaiserslautern-Landau (RPTU), Germany
  Oct. 2024 – Apr. 2025
  Teaching: Machine Learning for Earth Observation within a broader Data Science course.

• Visiting PhD Researcher – Inria Montpellier, France
  Nov. 2024 – Jan. 2025
  Research in multi-modal co-learning, mutual distillation, and multi-task learning.

• Academic Roles – Federico Santa María Technical University (UTFSM), Chile
  2014 – 2021
  Lecturer & Assistant roles in:

  • Computational Statistics

  • Artificial Neural Networks

  • Machine Learning

  • Operations Research

  • Mathematics Lab

• Research Assistant – Chilean Virtual Observatory (ChiVO)
  Jul. 2017 – May 2018
  Astroinformatics projects involving ALMA/ESO datasets and Python-based data reduction.

• Developer Intern – Farmacia Las Rosas S.A., Chile
  Jan. 2017 – Mar. 2017
  Desktop software automation using Python and QT.

Research Interests 🔬

• Machine Learning Foundations:
  Deep Learning, Variational Autoencoders, Neural Networks, Representation Learning, Deep Clustering

• Methodologies:
  Multi-view Learning, Data Fusion, Latent Variable Modeling, Dimensionality Reduction, Unsupervised Learning

• Applications:
  Earth Observation, Remote Sensing, Vegetation Monitoring, Crowdsourcing, Neural Information Retrieval, Astroinformatics

Awards and Honors🏆✨

• PhD Scholarship – RPTU, Germany (2022–present)

• Scientific Initiation Award (PIIC) – UTFSM, Chile (2019–2020)

• Master Program Scholarship – UTFSM, Chile (2018–2020)

• Honor Roll – UTFSM, Chile (2013)

Conclusion🌟

Francisco Mena is a dedicated machine learning researcher whose work blends theoretical rigor with impactful real-world applications. His interdisciplinary approach spans remote sensing, astroinformatics, and crowdsourcing, focusing on creating models that are resilient to missing data, efficient at scale, and minimally reliant on labeled supervision. With a growing publication record, international experience, and teaching background, he is well-positioned to make significant contributions to both academia and applied AI research.

Publications 📚

1. 📄 Missing data as augmentation in the Earth Observation domain: A multi-view learning approach
   Neurocomputing, 2025-07
   DOI: 10.1016/j.neucom.2025.130175
   👥 Francisco Mena, Diego Arenas, Andreas Dengel

   ---

2. 🌾 Adaptive fusion of multi-modal remote sensing data for optimal sub-field crop yield prediction
   Remote Sensing of Environment, 2025-03
   DOI: 10.1016/j.rse.2024.114547
   👥 Francisco Mena et al.

   ---

3. 🛰️ Common Practices and Taxonomy in Deep Multiview Fusion for Remote Sensing Applications
   IEEE JSTARS, 2024
   DOI: 10.1109/JSTARS.2024.3361556
   👥 Francisco Mena, Diego Arenas, Marlon Nuske, Andreas Dengel

   ---

4. 📉 Impact Assessment of Missing Data in Model Predictions for Earth Observation Applications
   IGARSS Proceedings, 2024
   DOI: 10.1109/IGARSS53475.2024.10640375
   👥 Francisco Mena et al.

   ---

5. 🛰️ Assessment of Sentinel-2 Spatial and Temporal Coverage Based on the Scene Classification Layer
   IGARSS 2024, 2024-07-07
   DOI: 10.1109/igarss53475.2024.10642213
   👥 Cristhian Sanchez, Francisco Mena et al.

   ---

6. 🌽 Crop Yield Prediction: An Operational Approach to Crop Yield Modeling on Field and Subfield Level with ML Models
   IGARSS 2023
   DOI: 10.1109/IGARSS52108.2023.10283302
   👥 Francisco Mena et al.

   ---

7. 🧩 Feature Attribution Methods for Multivariate Time-Series Explainability in Remote Sensing
   IGARSS 2023
   DOI: 10.1109/IGARSS52108.2023.10282120
   👥 Francisco Mena et al.

   ---

8. 🧹 Influence of Data Cleaning Techniques on Sub-Field Yield Predictions
   IGARSS 2023
   DOI: 10.1109/IGARSS52108.2023.10282955
   👥 Francisco Mena et al.

   ---

9. 🗂️ A Comparative Assessment of Multi-View Fusion Learning For Crop Classification
   IGARSS 2023, 2023-07-16
   DOI: 10.1109/igarss52108.2023.10282138
   👥 Francisco Mena, Diego Arenas, Marlon Nuske, Andreas Dengel

   ---

10. 📊 Predicting Crop Yield with Machine Learning: Input Modalities and Models on Field and Sub-Field Level
    IGARSS 2023, 2023-07-16
    DOI: 10.1109/igarss52108.2023.10282318
    👥 Francisco Mena et al.

    ---