publications

2025

1. 

   AAAI

   Hybrid phenology modeling for predicting temperature effects on tree dormancy

   Ron Van Bree, Diego Marcos , and Ioannis N Athanasiadis

   In Proceedings of the AAAI Conference on Artificial Intelligence , 2025

   Abs Bib Code

   We present a hybrid approach combining deep learning with phenological modeling to predict temperature effects on tree dormancy. Our method integrates domain knowledge from traditional phenology models with the flexibility of neural networks, demonstrating improved accuracy in predicting bud break timing under varying temperature conditions.

   @inproceedings{van2025hybrid,
     title = {Hybrid phenology modeling for predicting temperature effects on tree dormancy},
     author = {Van Bree, Ron and Marcos, Diego and Athanasiadis, Ioannis N},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     volume = {39},
     number = {27},
     pages = {28458--28466},
     year = {2025},
   }

2. 

   ONE

   Transdisciplinary coordination is essential for advancing agricultural modeling with machine learning

   Lily-belle Sweet , Ioannis N Athanasiadis , Ron Van Bree, Andres Castellano , and 4 more authors

   One Earth, 2025

   Abs Bib

   This perspective paper discusses the importance of transdisciplinary coordination in advancing agricultural modeling through machine learning. We identify key challenges and opportunities in combining domain expertise with modern ML approaches.

   @article{sweet2025transdisciplinary,
     title = {Transdisciplinary coordination is essential for advancing agricultural modeling with machine learning},
     author = {Sweet, Lily-belle and Athanasiadis, Ioannis N and Van Bree, Ron and Castellano, Andres and Martre, Pierre and Paudel, Dilli and Ruane, Alex C and Zscheischler, Jakob},
     journal = {One Earth},
     volume = {8},
     number = {4},
     year = {2025},
     publisher = {Elsevier},
   }

3. arXiv

   From General to Specialized: The Need for Foundational Models in Agriculture

   Vishal Nedungadi , Xingguo Xiong , Aike Potze , Ron Van Bree, and 3 more authors

   arXiv preprint arXiv:2507.05390, 2025

   Abs arXiv Bib

   This paper discusses the potential and challenges of adapting general-purpose foundational models for specialized agricultural applications, highlighting the unique requirements and opportunities in the agricultural domain.

   @article{nedungadi2025general,
     title = {From General to Specialized: The Need for Foundational Models in Agriculture},
     author = {Nedungadi, Vishal and Xiong, Xingguo and Potze, Aike and Van Bree, Ron and Lin, Tao and Ru{\ss}wurm, Marc and Athanasiadis, Ioannis N},
     journal = {arXiv preprint arXiv:2507.05390},
     year = {2025},
   }

2023

1. EDS

   Nitrogen management with reinforcement learning and crop growth models

   Michiel GJ Kallenberg , Hiske Overweg , Ron Van Bree, and Ioannis N Athanasiadis

   Environmental Data Science, 2023

   Abs Bib

   This paper presents a reinforcement learning approach for optimizing nitrogen management in agriculture, combining crop growth models with modern RL techniques to improve fertilization strategies.

   @article{kallenberg2023nitrogen,
     title = {Nitrogen management with reinforcement learning and crop growth models},
     author = {Kallenberg, Michiel GJ and Overweg, Hiske and Van Bree, Ron and Athanasiadis, Ioannis N},
     journal = {Environmental Data Science},
     volume = {2},
     pages = {e34},
     year = {2023},
     publisher = {Cambridge University Press},
   }

2. arXiv

   Integrating processed-based models and machine learning for crop yield prediction

   Michiel GJ Kallenberg , Bernardo Maestrini , Ron Van Bree, Paul Ravensbergen , and 3 more authors

   arXiv preprint arXiv:2307.13466, 2023

   Abs arXiv Bib

   We present a novel approach for integrating process-based models with machine learning techniques to improve crop yield predictions, combining the interpretability of mechanistic models with the flexibility of data-driven approaches.

   @article{kallenberg2023integrating,
     title = {Integrating processed-based models and machine learning for crop yield prediction},
     author = {Kallenberg, Michiel GJ and Maestrini, Bernardo and Van Bree, Ron and Ravensbergen, Paul and Pylianidis, Christos and van Evert, Frits and Athanasiadis, Ioannis N},
     journal = {arXiv preprint arXiv:2307.13466},
     year = {2023},
   }

2021

1. 

   CVPR

   Neural prototype trees for interpretable fine-grained image recognition

   Meike Nauta , Ron Van Bree, and Christin Seifert

   In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , 2021

   Abs Bib PDF Code

   We propose Neural Prototype Trees (ProtoTrees), a novel interpretable deep learning architecture for fine-grained image recognition. Our model combines prototype learning with decision trees, enabling both accurate and interpretable predictions.

   @inproceedings{nauta2021neural,
     title = {Neural prototype trees for interpretable fine-grained image recognition},
     author = {Nauta, Meike and Van Bree, Ron and Seifert, Christin},
     booktitle = {Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
     pages = {14933--14943},
     year = {2021},
   }