Projects
Ongoing Projects
2024 AI-based Power Production Models for Increased Wind Farm Efficiency
- Funded by:
- The Swedish Energy Agency.
- People: Maria Bånkestad, Aleksis Pirinen
2023 Data Efficient Machine Learning for Earth Observation
PhD project focusing on data efficient machine learning for earth observation.
- Partners:
- Publications:
- People: Martin Willbo, Olof Mogren, Aleksis Pirinen
2023 Agrifood TEF
The European Testing and Experimentation Facilities for Agrifood Innovation. To foster sustainable and efficient food production AgrifoodTEF empowers innovators with validation tools needed to bridge the gap between their brightest ideas and successful market products. Built as a network of physical and digital facilities across Europe, the project provides services that help assess and validate third party AI and Robotics solutions in real-world conditions aiming to maximise impact from digitalisation of the agricultural sector. More information: www.agrifoodtef.eu.
- People: Aleksis Pirinen
2021 AI-Based Soundscape Analysis
PhD project focusing on soundscape analysis for biodiversity monitoring.
- Partners:
- Funded by:
- Swedish Foundation for Strategic Research
- Publications:
- John Martinsson and Maria Sandsten. DMEL : The differentiable log-Mel spectrogram as a trainable layer in neural networks. In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.
- John Martinsson, Martin Willbo, Aleksis Pirinen, Olof Mogren, and Maria Sandsten. Few-shot bioacoustic event detection using an event-length adapted ensemble of prototypical networks. In The 7th Workshop on Detection and Classification of Acoustic Scenes and Events, number November, pages 2–6, 2022.
- People: John Martinsson, Olof Mogren
2021 Digital Earth Sweden
Digital Earth Sweden is a Swedish hub for stakeholders working with Earth observation data. Our ambition is to make space data accessible to everyone. More information: digitalearth.se.
- People: Aleksis Pirinen
Finished Projects
2023 Structural Causal Models for Distributional Shift in Federated Learning
- Funded by:
- Vinnova
- People: Edvin Listo Zec, Olof Mogren
2023 Towards efficient computational fluid dynamics simulations with physics-informed machine learning
- Funded by:
- Vinnova
- People: Maria Bånkestad, Aleksis Pirinen
2023 Active learning for ecological monitoring
- Funded by:
- Vinnova
- People: John Martinsson, Aleksis Pirinen
2023 ML for cloud optical thickness estimation
The work was published in the journal Remote Sensing (2024), got accepted as an oral at the 2nd ML-for-RS Workshop at ICLR 2024, and was presented as a poster at EUMETSAT 2023. Funded by Vinnova. One of the project deliverables was a developer event (Hackathon) for university students.
- Partners:
- Publications:
- Aleksis Pirinen, Nosheen Abid, Nuria Agues Paszkowsky, Thomas Ohlson Timoudas, Ronald Scheirer, Chiara Ceccobello, György Kovács, Anders Persson, Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI, Journal of Remote Sensing (2024)
- 2nd ML4RS Workshop 2024
- EUMETSTAT 2023
- People: Aleksis Pirinen
- Code: github.com/aleksispi/ml-cloud-opt-thick
2022 Machine Learning for Wetland Monitoring in Sweden
- People: Aleksis Pirinen
- Code: github.com
2022 Drug Influence Detection Using Computer Vision
Support in developing machine learning based solution for detecting drug influence from camera inputs.
- Partners:
Funded by Vinnova
- People: Aleksis Pirinen, Martin Willbo, Olof Mogren
2022 Dense Stream Flow Forecasting
In this work we propose a machine learning-based approach for predicting water flow intensities in inland watercourses based on the physical characteristics of the catchment areas, obtained from geospatial data in addition to temporal information about past rainfall quantities and temperature variations. We are the first to tackle the task of dense water flow intensity prediction; earlier works have considered predicting flow intensities at a sparse set of locations at a time.
- Publications:
- People: Aleksis Pirinen, Olof Mogren
- Code: github.com/aleksispi/fcn-water-flow
2021 AI for Porcelain Recognition
- Partners:
- Funded by:
- Riksantikvarieämbetet (RAÄ)
- Västra Götalandsregionen (VGR)
- People: Martin Willbo, Ebba Ekblom, Olof Mogren