I am a senior research scientist at RISE Research institutes of Sweden
heading The Deep Learning Research Group - Working on Foundational and Applied Machine Learning for the Earth.
I am a co-PI of CLIMES, The Swedish Centre for Impacts of Climate Extremes, and a co-funder of Climate AI Nordics. I have a PhD from Chalmers University of Technology, and I am the organizer of RISE Learning Machines Seminars.
Climate AI Nordics is an initiative tying together researchers in the Nordic countries working on problems related to climate change. Climate AI Nordics will be a platform that enables researchers in this area to connect and collaborate more. Initially, there will be a mailing list and some seminars with the hope that this can grow to something bigger in the near future. Head over to climateainordics.com and register yourself as an affiliate!
In my research, I develop and investigate machine learning based solutions to problems related to the environment and climate change. This includes stream flow forecasting, soundscape analysis for biodiversity monitoring, and AI for circular business models.
Read more about me, or about my research group.
Recent publications
Also, visit my Scholar page.
Martinsson, J., Virtanen, T., Sandsten, M., Mogren, O., The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Time, Transactions on Machine Learning Research, TMLR
Lindholm, R., Marklund, O., Mogren, O., Martinsson, J., Aggregation Strategies for Efficient Annotation of Bioacoustic Sound Events Using Active Learning, European Signal Processing Conference, EUSIPCO
Martinsson, J., Mogren, O., Sandsten, M., Virtanen, T., From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning, European Signal Processing Conference, EUSIPCO
Willbo, M., Pirinen, A., Martinsson, J., Listo Zec, E., Mogren, O., Nilsson, M., Impacts of Color and Texture Distortions on Earth Observation Data in Deep Learning, 2nd Machine Learning for Remote Sensing Workshop at ICLR, ML4RS
Listo Zec, E., Östman, J., Mogren, O., Gillblad, D., Efficient Node Selection in Private Personalized Decentralized Learning, Northern Lights Deep Learning Conference, NLDL
Toftås, M., Klefbom, E., Listo Zec, E., Willbo, M., Mogren, O., Concept-aware clustering for decentralized deep learning under temporal shift, Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities workshop at ICML, FL-ICML
Pirinen, A., Mogren, O., Västerdal, M., Fully Convolutional Networks for Dense Water Flow Intensity Prediction in Swedish Catchment Areas, 35th Annual Workshop of the Swedish Artificial Intelligence Society SAIS, SAIS
Lan, X., Taghia, J., Moradi, F., Ali Khoshkholghi, M., Listo Zec, E., Mogren, O., Mahmoodi, T., Johnsson, A., Federated learning for performance prediction in multi-operator environments, ITU Journal on Future and Evolving Technologies, ITUJ
Ekblom, E., Listo Zec, E., Mogren, O., EFFGAN: Ensembles of fine-tuned federated GANs, IEEE International Conference on Big Data, IEEE Big Data
Martinsson, J., Willbo, M., Pirinen, A., Mogren, O., Sandsten, M., Few-shot bioacoustic event detection using a prototypical network ensemble with adaptive embedding functions, Detection and Classification of Acoustic Scenes and Events, DCASE
Martinsson, J., Runefors, M., Frantzich, H., Glebe, D., McNamee, M., Mogren, O., A Novel Method for Smart Fire Detection Using Acoustic Measurements and Machine Learning: Proof of Concept, Journal of Fire Technology, Fire Technol.
View list of publications.
Recent talks in selection
Tutorial at EUREF 2023: AI for the environment, EUREF Symposium 2023, Chalmers University of Technology,
AI for environment at RISE, AI for climate and environmental research workshop, Lund University,
AI for chemistry and process industry, Royal Swedish Academy of Engineering Sciences,