PostDoc
Group for Theoretical Ecology
Faculty of Biology and Pre-Clinical Medicine
University of Regensburg
Universit?tsstra?e 31
93053 Regensburg
email: maximilian.pichler @ biologie.uni-regensburg.de
room: E4._2.103
Phone: +49-941 943-4335
Research Interests
My research focuses on using tools from Artificial Intelligence (machine learning and deep learning) to answer ecological questions:
- Inference of complex ecological effects with Machine Learning and Deep learning
- Using Machine Learning and Deep Learning to infer trait-matching in ecological networks
- (Deep) Joint Species Distribution Models (jSDM)
- Automatic Species Recognition
I am developing R packages that combine statistical modeling with deep learning and machine learning:
- Statistical inference with Deep Neural Networks: cito - Building and training neural networks in R (CRAN)
- (deep)jSDM for big/novel community data: s-jSDM (fast and scalable JSDM based on PyTorch) (CRAN)
- ML and DL for trait-matching: TraitMatching (Using Machine Learning to predict species interactions)
See my Google Scholar (externer Link, ?ffnet neues Fenster) profile for a current list of publications.
See also
Projects:
- bayklif2: bavariance Artificial Intelligence for insect monitoring (bAImo), 2026-2030
Curriculum Vitae
| 2024- | PostDoc at University of Regensburg, Germany |
| 2018-2024 | PhD studies at University of Regensburg, Germany |
Education
| 18/07/2024 | Promotion Dr. rer. nat |
| 09/2018 | Master of Science in Biology at University of Regensburg, Germany |
| 2016 | Bachelor of Science in Biology at University of Regensburg, Germany |
Publications
- Pichler, M., & Hartig, F. (2023). Can predictive models be used for causal inference?. arXiv preprint arXiv:2306.10551. [preprint]
- Pichler, M., & Hartig, F. (2023). Machine learning and deep learning—A review for ecologists. Methods in Ecology and Evolution, 14(4), 994-1016. [journal]
- Pichler, M., & Hartig, F. (2021). A new joint species distribution model for faster and more accurate inference of species associations from big community data. Methods in Ecology and Evolution.[journal]
- Oberpriller, J., de Souza Leite, M., & Pichler, M. (2021). Fixed or random? On the reliability of mixed-effect models for a small number of levels in grouping variables. bioRxiv.[journal]
- Pichler, M., Boreux, V., Klein, A. M., Schleuning, M., & Hartig, F. (2020). Machine learning algorithms to infer trait‐matching and predict species interactions in ecological networks. Methods in Ecology and Evolution, 11(2), 281-293. [journal]