Francisco Mena

PhD

I'm a researcher at the GFZ Helmholtz Centre for Geoscience working in the intersection of Artificial Intelligence and Earth Observation (AI4EO).

My current interests are Deep Learning, Multi-view Learning, Representation Learning, Model Robustness, and Earth Observation 🌎.

Contact me 📧 CV

News 📰

I sucessfully defended my PhD in Multi-view Learning for Earth Observation Applications with Missing Views .
I presented a poster at the REO workshop (EurIPS event) in Copenhagen, Denmark 🇩🇰.
I joined GFZ Helmholtz Centre for Geosciences to work at the GLM group in AI/ML applied to forestry monitoring.
I presented two papers at IGARSS (July) in Brisbane, Australia 🇦🇺.
I did a research stay at Inria in Montpellier 🇫🇷 with the Evergreen team ☘️ .
I gave a lecture about ML4EO in the Applications of Machine Learning and Data Science course at the TU Kaiserslautern
I presented a paper at ECML-PKDD workshop MACLEAN (September) in Vilnius, Lithuana.
I presented two papers at IGARSS (July) in Athens, Greece 🇬🇷.
I presented a paper at ICLR workshop ML4RS (April) in Vienna, Austria 🇦🇹.
I attended the PhD Forum at ECML-PKDD (September) in Torino, Italy 🇮🇹.
I attended the 3rd INRIA-DFKI Summer School on Artificial Intelligence (September) in Antibes, France 🇫🇷.
I presented a paper and chair a session at IGARSS (July) in Pasadena, US 🇺🇸.
I joined DFKI to work in the AI4EO Solution Factory 🛰️ .
I started a PhD in Computer Science at the TU Kaiserslautern under the guidance of Prof. Dengel.
I taught Computational Statistics and Artificial Neural Network courses at the TU Federico Santa Maria
I sucessfully defended my Master thesis (online) under the guidance of Prof. Ñanculef.

My Research Experience

Artificial Intelligence

My specialization area during Master and Doctorate. I have done various research projects and individual research works that have ended in publications, as well as an exhaustive learning around this topic. Furthermore, I have done some teaching lessons and been a teaching assistant for related courses in this topic.

Machine/Deep Learning, Multi-view Learning, Robustness, Data Fusion, Co-learning, Variational Auto-Encoders, Representation Learning.

Earth Observation

I'm researching this interesting domain to apply novel AI proposals based on multi-sensor Remote Sensing data. Besides, I'm currently exploring robust multi-sensor models to missing data in Agriculture and Forestry applications.

Agriculture/Vegetation, Forestry Monitoring, Land-cover Land-use, Remote sensing data, Multi-sensor, Missing data, Optical/Radar Image Time Series.

Crowdsourcing

I did my Master's thesis on this topic by proposing models to infer labels from the crowds, in addition to publishing works about my research.

Mixture Models, Hidden Variable Modeling, Image and Text Data, Classification.

Astroinformatics

I explored and published some works on the exoplanet identification task through light curves. The research is around the Kepler mission data.

Representation Learning, Machine/Deep Learning, Time Series Data, Classification.

Information Retrieval

I explored this topic out of curiosity based on the knowledge acquired in some text mining courses I took. The retrieval explored is an object-based similarity search. This ended up in publications and research collaborations.

Similarity Search, Dimensionality Reduction, Image and Text data, Hashing.

My Publications 📝

ORCID 0000-0002-5004-6571

An updated list of my publications could be found at ResearchGate or Google Scholar. A few relevant publications are:

Year	Title	Where?	Topic
2025	Multi-modal co-learning for Earth observation: enhancing single-modality models via modality collaboration	Machine Learning	Multi-modal data, Co-learning, Earth observation, Missing modalities
2025	In the search for optimal multi-view learning models for crop classification with global remote sensing data	International Journal of Applied Earth Observation and Geoinformation	Multi-view learning, Data fusion, Earth observation, Crop classification
2025	Multi-sensor model for Earth observation robust to missing data via sensor dropout and mutual distillation	IEEE Access	Multi-sensor model, Earth observation, Robustness to missing data, Multi-task learning, Mutual distillation
2025	Missing data as augmentation in the Earth Observation domain: A multi-view learning approach	Neurocomputing	Multi-view learning, Data augmentation, Robustness, Earth observation, Missing data
2025	Adaptive fusion of multi-modal remote sensing data for optimal sub-field crop yield prediction	Remote Sensing of Environment	Crop yield prediction, Multi-modal remote sensing data, Time series, Adaptive fusion
2024	Common practices and taxonomy in deep multi-view fusion for remote sensing applications	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing	Earth observation, Multi-view learning, Data fusion
2021	On the quality of deep representations for Kepler light curves using variational auto-encoders	Signals	Exoplanet analysis, time series, dimensionality reduction
2020	Collective annotation patterns in learning from crowds	Intelligent Data Analysis	Crowdsourcing, Hidden variable modeling, Mixture model
2020	Interpretable and effective hashing via Bernoulli variational auto-encoders	Intelligent Data Analysis	Information retrieval, Hashing learning, Unsupervised deep learning

About Me 👤

MSc & BSc in

Francisco Mena is a Master of Science (MSc) graduate from Federico Santa María Technical University (UTFSM, in Chile) where he also studied for his Bachelor of Science in the field of Computer Engineering specializing in Artificial Intelligence. Always interested in building automated systems that help society, he joined the Chilean Virtual Observatory (CHiVO) during his undergraduate studies in 2017. Later during the Master's program (from 2018) he explored three different areas using Artificial Intelligence: Crowdsourcing, Astroinformatics, and Information Retrieval (Similarity Search). Once he obtained his Master's degree he started working as a part-time lecturer at the same institution where he studied (UTFSM) in 2020, teaching the course Computational Statistics and Artificial Neural Networks.

Sunbelt Computer Software

PL/B Language Development and Support

Hi there 👋, I'm