Research

The Spatiotemporal Data Analysis (SDA) research group does research on machine learning methods for forming and analyzing spatiotemporal data to advance sustainability science. Research aims at methodological advances in machine learning, including uncertainty-aware learning, flow matching, representation learning, and multi-objective (hierarchical) reinforcement learning. These methods are designed to address the challenges of data efficiency, generalization, and interpretability, especially in high-stakes domains such as GNSS and network resilience, vision and sensor systems, and sustainable urban planning.
Multi-Objective Hierarchical Reinforcement Learning for Large-Scale Decision-Making

Our research develops multi-objective hierarchical reinforcement learning methodologies for scalable decision-making in complex, evolving environments. By combining hierarchical coordination, Pareto optimization, and adaptive learning, the framework supports continuous adaptation across multiple temporal scales while balancing conflicting objectives.

Selected publications

  1. Singh, N., Beimuk, V., Leinonen, M., & Ruotsalainen, L. (2026). Contextual intelligence based Multi-objective Hierarchical Reinforcement Learning.
  2.  Bochenina, K., Beimuk, V., & Ruotsalainen, L. (2026). A Performance Model for Deadline-Aware Off-Policy Reinforcement Learning with Vectorized Environments. International Joint Conference on Neural Networks IJCNN. IEEE.

Sustanable Smart Cities as a Use Case

In the fight against climate change and coping with the pressures arising from urbanisation, cities worldwide make solutions modifying pollutant emissions and thermal comfort. At present, road transport contributes a significant amount to the total carbon dioxide emissions in the EU. Thus, cities look for practical strategies to make their transport system more efficient and sustainable, and SDA Group is developing novel reinforcement learning methods to aid in this goal while maximising the air quality and minimising the carbon dioxide emissions.

Selected publications

  1. Bochenina, K., & Ruotsalainen, L. (2024, June). A reinforcement learning-based metaheuristic algorithm for on-demand ride-pooling. In 2024 International Conference on Intelligent Environments (IE) (pp. 117-123). IEEE.
  2. Matti Leinonen, Ahmed Al-Tachmeesschi, Banu Turkmen, Nahid Atashi, Laura Ruotsalainen (2024). Long Short Term Memory Based Traffic Prediction Using Multi-Source Data. International Journal of Intelligent Transportation Systems Research .
  3. Klavdiia Bochenina, Anton Taleiko, Laura Ruotsalainen: Simulation-based origin-destination matrix reduction: a case study of Helsinki city area, SUMO User Conference 2023.
  4. Joanne C. Demmler, Ákos Gosztonyi, Yaxing Du, Matti Leinonen, Laura Ruotsalainen, Leena Järvi, Sanna Ala-Mantila (2021): PLOS ONE,

Projects

  1. . This project was funded by the Research Council of Finland for 2020-2024.
  2. AI-based optimisation tool for sustainable urban planning (AIOSut). This project is funded by the Research Council of Finland for 2025-2026.
  3. . This project has received funding from the European Union – NextGenerationEU instrument and was funded by the Research Council of Finland for 2022-2024.
Computer vision and sensor fusion

Computer vision provides essential information for reliable visual localization, navigation, situational awareness, and precise 3D scene understanding. The SDA group develops next-generation machine learning and computer vision methodologies, including flow matching for visual odometry, diffusion models for 3D object pose estimation, Neural Radiance Fields (NeRFs) for high-precision medical reconstruction, and Gaussian Splatting for efficient industrial 3D scene representation. We advance robust visual perception for autonomous systems operating in challenging environments, with a particular focus on industrial and medical applications involving non-Lambertian surfaces, sparse visual features, dynamic scenes, occlusions, and adverse indoor and low-light conditions.

Publications

  1. Joswig, N., & Ruotsalainen, L. (2025). Geometric Edge Modelling in Self‐Supervised Learning for Enhanced Indoor Depth Estimation. IET Computer Vision, 19(1), e70026.
  2. Pyykölä, S., Joswig, N., & Ruotsalainen, L. (2024). Non-Lambertian surfaces and their challenges for visual SLAM. IEEE open journal of the Computer Society, 5, 430 - 445.
  3. Pajula, I. A., Joswig, N., Morrison, A., Sokolova, N., & Ruotsalainen, L. (2023). A Novel Cross-Attention-Based Pedestrian Visual–Inertial Odometry With Analyses Demonstrating Challenges in Dense Optical Flow. IEEE journal of indoor and seamless positioning and navigation, 2.
  4. Niclas Joswig, Juuso Autiosalo, Laura Ruotsalainen (2023): Machine Vision and Applications, 
  5. Laura Ruotsalainen, Aiden Morrison, Maija Mäkelä, Jesperi Rantanen, Nadezda Sokolova (2021): IEEE Sensors Journal,

Projects

  1. - Donation from Konecranes, read more:

Selected Mas­ter's theses

  1. (2026).
  2. (2025).
  3.  (2021).
  4.  (2021)
  5.  (2022).

News

  1.  (15.1.2020, in Finnish)

Videos

 
Representation learning for high dimensional sensor systems

The goal of our research is to develop advanced methods in representation learning and neural ordinary differential equations (ODEs) to model and understand dynamic, high-dimensional real-world sensor systems. These systems, such as those found in autonomous vehicles, industrial infrastructure, or environmental monitoring networks, generate complex spatiotemporal data that evolve continuously over time. By combining structured representation learning with data-driven differential modeling, we aim to extract compact, interpretable, and predictive representations that capture the underlying dynamics of these systems, enabling more robust decision-making, forecasting, anomaly detection and failure prediction in real-world conditions.

 

Selected publications

  1. Sarapisto, T., Wei, H., Heljanko, K., Klami, A., Ruotsalainen, L. (2024). Subsystem Discovery in High-Dimensional Time-Series Using Masked Autoencoders. European Conference of Artificial Intelligence.
  2. Farahani, A. V., Leinonen, M., Ruotsalainen, L., Jokisalo, J., & Kosonen, R. (2025). Predicting summer indoor temperatures in Nordic apartments considering heatwaves forecasts. Energy and Buildings, 115630.
Resilient GNSS and Communication Networks

Reliable positioning, navigation, and timing (PNT) provided by GNSS are fundamental to modern society, enabling applications ranging from autonomous transportation and critical infrastructure to emergency response and sustainable mobility. However, increasingly complex radio environments, evolving communication networks, and emerging threats such as jamming, spoofing, and interference challenge the reliability and resilience of current systems. The SDA group develops novel machine learning methodologies for resilient GNSS and communication networks, combining signal representation learning, anomaly detection, uncertainty estimation, and continuous learning to enable robust adaptation to changing signal environments. Our research aims to advance trustworthy, adaptive, and intelligent positioning and communication systems capable of operating reliably under evolving, contested, and sometimes hostile real-world conditions.

Selected publications

  1. Yan, Z., & Ruotsalainen, L. (2025). GNSS jammer localization in urban areas based on prediction/optimization and ray-tracing. GPS Solutions, 29(1), 47.
  2. Mehr, I. E., Savolainen, O. M. M., Ruotsalainen, L., & Dovis, F. (2024). Dual-Stage Deep Learning Approach for Efficient Interference Detection and Classification in GNSS. In Proceedings of the 37th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2024) (pp. 3336-3347). Institute of Navigation.
  3. Savolainen, O., Elango, A., Morrison, A., Sokolova, N., & Ruotsalainen, L. (2024). GNSS Anomaly Detection with Complex-Valued LSTM Networks. In J. Nurmi, R. Berkvens, T. Janssen, R. Halili, E. De Poorter, & A. Ometov (Eds.), 2024 International Conference on Localization and GNSS, ICL-GNSS 2024 - Proceedings Institute of Electrical and Electronics Engineers Inc..
  4. A. Al-Tahmeesschi, J. Talvitie, M. López-Benítez, H. Ahmadi and L. Ruotsalainen, "Multi-Objective Deep Reinforcement Learning for 5G Base Station Placement to Support Localisation for Future Sustainable Traffic," 2024 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit), Antwerp, Belgium, 2024, pp. 493-498,. 
  5. Savolainen, O., Malmivirta, T., Yan, Z., Morrison, A., & Ruotsalainen, L. (2024). Towards Jammer Fingerprinting: The Effect of the Environment and the Receiver to a Jammer Classification. In J. Nurmi, R. Berkvens, T. Janssen, R. Halili, E. De Poorter, & A. Ometov (Eds.), 2024 International Conference on Localization and GNSS (ICL-GNSS) Institute of Electrical and Electronics Engineers Inc..
  6. Ahmed Al-Tahmeesschi, Jukka Talvitie, Miguel López–Benítez, Laura Ruotsalainen (2022): 2022 International Conference on Localization and GNSS (ICL-GNSS), 
  7. Arul Elango, Sahar Ujan, Laura Ruotsalainen (2022):
    2022 International Conference on Localization and GNSS (ICL-GNSS),
  8. Arul Elango, Ahmed Al-Tahmeesschi, Mikko Saukkoriipi, Titti Malmivirta, Laura Ruotsalainen (2022): 

Projects

Master's theses

  1.  (2022).

News

  1.  (9 Jan 2024, in Finnish).