Research

The research scope of this group covers the areas of Artificial Intelligence research for smart environmental sensing and related applications, such as smart cities, smart space, and renewable energies. Whether you are a student, researcher, or simply interested in the field, our Scope section is the ideal starting point for exploring the exciting world of AI technology for environmental monitoring analytics at our university.

IRON develops some data science methods to assist scientists in performing data analysis to enhance scientific discoveries. For example, mutual information methods have been further enhanced to be used by atmospheric scientists to discover rapidly and accurately relationships between large measurements in SMEAR stations. The examples of research activities are presented in the below list of publications.

P. Su, J. Joutsensaari, L. Dada, M.A. Zaidan, T. Nieminen, X. Li, Y. Wu, S. Decesari, S. Tarkoma, T. Petäjä, M. Kulmala, and P. Pellikka. New particle formation event detection with Mask R-CNN. Atmospheric Chemistry and Physics, 22(2):1293–1309, 2022.

P. Laarne, E. Amnell, M.A. Zaidan, S. Mikkonen, and T. Nieminen. Exploring non-linear dependencies in atmospheric data with mutual information. Atmosphere, 13(7), 2022.

P. Laarne, M.A. Zaidan, and T. Nieminen. ennemi: Easy-to-use nearest neighbor estimation of Mutual Information. SoftwareX, 14:100686, 2021.

M.A. Zaidan, V. Haapasilta, R. Relan, P. Paasonen, V.-M. Kerminen, H. Junninen, M. Kulmala, and A. S. Foster. Exploring non-linear associations between atmospheric new-particle formation and ambient variables: a mutual information approach. Atmospheric Chemistry and Physics, 18(17):12699–12714, 2018.

M.A. Zaidan, V. Haapasilta, R. Relan, H. Junninen, P.P. Aalto, M. Kulmala, L. Laurson, and A.S. Foster. Predicting atmospheric particle formation days by Bayesian classification of the time series features. Tellus B: Chemical and Physical Meteorology, 70(1):1–10, 2018.

M. Stocker, P. Paasonen, M. Fiebig, M.A. Zaidan, and A. Hardisty. Curating scientific information in knowledge infrastructures. Data Science Journal 17 (2018), 2018.

IRON is interested in performing environmental sensing for various variables, including ambient air aerosol concentrations (e.g., particle number concentration, particulate matters), trace gases concentration (e.g., CO, NO2, O3, SO2), and meteorological and radiation variables. In addition, IRON is also exploring measurements for vibration, noise, lights, etc. IRON is using mainly low-cost sensor devices (with a cost is approximately under $500). In order to support the quality of our measurements, IRON also involves reference instruments (in collaboration with INAR) to validate the generated data.

Sensors deployments: chamber and field experiments

The examples of research activities are presented in the below list of publications.

N.H. Motlagh, M.A. Zaidan, P.L. Fung, Y. Matsumi, T. Petäjä, M. Kulmala, S. Tarkoma, and T. Hussein. Low-cost air quality sensing process: Validation by indoor-outdoor measurements. In 2020 15th IEEE Conference on Industrial Electronics and Applications (ICIEA), pages 223–228, 2020.

Sensor validations: low-cost sensors vs reference instruments

The examples of research activities are presented in the below list of publications.

E. Lagerspetz, N.H. Motlagh, M.A. Zaidan, P.L. Fung, J. Mineraud, S. Varjonen, M. Siekkinen, P. Nurmi, Y. Matsumi, S. Tarkoma, and T. Hussein. Megasense: Feasibility of low-cost sensors for pollution hot-spot detection. In 2019 IEEE 17th International Conference on Industrial Informatics (INDIN), volume 1, pages 1083–1090, 2019.

Wireless networks are fundamental in establishing sensor networks and transmitting sensor data to edge-cloud servers. Within this research topic, IRON aims to explore reliable data networking as well as enhanced computing mechanisms for environmental monitoring sensing systems. While different environments such as indoor and outdoor may require different resources from the network, the use cases using the services of the network may demand a specific amount of computing resources.

The examples of research activities are presented in the below list of publications.

As low- and medium-cost sensors (and instrumentations) usually encounter accuracy issues, IRON attempts to calibrate low-cost sensor devices based on reference instruments using Artificial intelligence (AI) techniques. In addition, due to the cost, size, and complexity, many low- and medium-cost sensor devices are not capable of measuring some complex pollutants, such as black carbon, lung-deposited surface area (LDSA), and sulfuric acid. IRON also attempts to develop virtual sensors based on AI techniques using data gathered from reference instruments in our research stations (tiny ML). 

Intelligent sensor calibration and diagnostics

The examples of research activities are presented in the below list of publications.

M.A. Zaidan, N.H. Motlagh, P.L. Fung, A.S. Khalaf, Y. Matsumi, A. Ding, S. Tarkoma, T. Petäjä, M. Kulmala, and T. Hussein. Intelligent air pollution sensors calibration for extreme events and drifts monitoring. IEEE Transactions on Industrial Informatics, 19(2):1366–1379, 2023.

M.A. Zaidan, Y. Xie, N.H. Motlagh, B. Wang, W. Nie, P. Nurmi, S. Tarkoma, T. Petäjä, A. Ding, and M. Kulmala. Dense air quality sensor networks: Validation, analysis, and benefits. IEEE Sensors Journal, 22(23):23507–23520, 2022.

Virtual Sensors

The examples of research activities are presented in the below list of publications.

M.A. Zaidan, N.H. Motlagh, B.E. Boor, D. Lu, P. Nurmi, A. Ding, T. Petäjä, M. Kulmala, S. Tarkoma, and T. Hussein. Virtual sensors: Toward high-resolution air pollution monitoring using AI and IoT. IEEE Internet of Things Magazine, 6(1):76–81, 2023.

P.L. Fung, M.A. Zaidan, J. Niemi, E. Saukko, H. Timonen, A. Kousa, J. Kuula, T. Rönkkö, A. Karppinen, S. Tarkoma, M. Kulmala, T. Petäjä, and T. Hussein. Input-adaptive linear mixed-effects model for estimating alveolar lung-deposited surface area (LDSA) using multipollutant datasets. Atmospheric Chemistry and Physics, 22(3):1861–1882, 2022.

P.L. Fung, M.A. Zaidan, O. Surakhi, S. Tarkoma, T. Petäjä, and T. Hussein. Data imputation in in situ-measured particle size distributions by means of neural networks. Atmospheric Measurement Techniques, 14(8):5535–5554, 2021.

M.A. Zaidan, N.H. Motlagh, P.L. Fung, D. Lu, H. Timonen, J. Kuula, Jarkko V. Niemi, S. Tarkoma, T. Petäjä, M. Kulmala, and T. Hussein. Intelligent calibration and virtual sensing for integrated low-cost air quality sensors. IEEE Sensors Journal, 20(22):13638–13652, 2020.

P.L. Fung, M.A. Zaidan, H. Timonen, J.K. Niemi, A. Kousa, J. Kuula, K. Luoma, S. Tarkoma, T. Petäjä, M. Kulmala, and T. Hussein. Evaluation of white-box versus black-box machine learning models in estimating ambient black carbon concentration. Journal of Aerosol Science,
152:105694, 2020.

IRON explores several use cases of the developed methodologies to be implemented in various applications to gain scientific and practical benefits. The applications include environmental analytics, smart space, ubiquitous air quality sensing, and renewable energies. 

Environmental Analytics

The examples of research activities are presented in the below list of publications.

P.L. Fung, M. Savadkoohi, M.A. Zaidan, J.V. Niemi, H. Timonen, M. Pandolfi, A. Alastuey, X. Querol, T. Hussein, and T. Petäjä. Constructing transferable and interpretable machine learning models for black carbon concentrations. Environment International, 184:108449, 2024.

P.L. Fung, S. Sillanpää, J.V. Niemi, A. Kousa, H. Timonen, M.A. Zaidan, E. Saukko, M. Kulmala, T. Petäjä, and T. Hussein. Improving the current air quality index with new particulate indicators using a statistical approach. Science of the Total Environment, 844:157099, 2022.

S. Sillapää, P. Fung, J.V. Niemi, A. Kousa, L. Kangas, M.A. Zaidan, H. Timonen, M. Kulmala, T. Petäjä, and T. Hussein. Long-term air quality trends of regulated pollutants in Helsinki metropolitan area in 1994-2019 and implications to air quality index. Boreal Environment Research, 27:61–79, 2022.

N. Atashi, D. Rahimi, V. Sinclair, M.A. Zaidan, A. Rusanen, H. Vuollekoski, M. Kulmala, T. Vesala, and T. Hussein. Delineation of dew formation zones in Iran using long-term model simulations and cluster analysis. Hydrology and Earth System Sciences, 2021:1–28, 2021.

S. Xu, M.A. Zaidan, E. Honkavaara, T. Hakala, N. Viljanen, A. Porcar-Castell, and J. Atherton. On the estimation of the leaf angle distribution from drone based photogrametry. In IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, pages 4379–4382, 2020.

Smart Space: indoor environmental analytics and automatic decision making

The examples of research activities are presented in the below list of publications.

N.H. Motlagh, M.A. Zaidan, L. Loven, P.L. Fung, T. Hanninen, R. Morabito, P. Nurmi, and S. Tarkoma. Digital twins for smart spaces - beyond IoT analytics. IEEE Internet of Things Journal, 11(1):573–583, 2024.

N.H. Motlagh, P. Toivonen, M.A. Zaidan, E. Lagerspetz, E. Peltonen, E. Gilman, P. Nurmi, and S. Tarkoma. Monitoring social distancing in smart spaces using infrastructure-based sensors. In IEEE 7th World Forum on Internet of Things, pages 124–129, 2021.

N.H. Motlagh, M.A. Zaidan, E. Lagerspetz, S. Varjonen, J. Toivonen, J. Mineraud, A. Rebeiro-Hargrave, M. Siekkinen, T. Hussein, P. Nurmi, and S. Tarkoma. Indoor air quality monitoring using infrastructure-based motion detectors. In 2019 IEEE 17th International Conference on Industrial Informatics (INDIN), volume 1, pages 902–907, 2019.

Ubiquitous air quality sensing

The examples of research activities are presented in the below list of publications.

J. Zhao, P.L. Fung, M.A. Zaidan, B. Wehner, K. Weinhold, A. Wiedensohler, and T. Hussein. Indoor black carbon concentrations and their sources in residential environments: Validation of an input-adaptive proxy model. Aerosol and Air Quality Research, 24:230228, 2024.

N.H. Motlagh, M.A. Zaidan, P.L. Fung, H. Salminen, A. Rebeiro-Hargrave, M. Irjala, P. Nurmi, T. Hussein, T. Petäjä, M. Kulmala, and S. Tarkoma. In Proceedings of the 1st International Workshop on Advances in Environmental Sensing Systems for Smart Cities, EnvSys ’23, page 13–18, New York, NY, USA, 2023. Association for Computing Machinery.

P. Kortoçi, N.H. Motlagh, M.A. Zaidan, P.L. Fung, S. Varjonen, A. Rebeiro-Hargrave, J. Niemi, P. Nurmi, T. Hussein, T. Petajä, M. Kulmala, and S. Tarkoma. Air pollution exposure monitoring using portable low-cost air quality sensors. Smart Health, 23:100241, 2022.

N.H. Motlagh, M.A. Zaidan, P.L. Fung, E. Lagerspetz, K. Aula, S. Varjonen, M. Siekkinen, A. Rebeiro-Hargrave, T. Petajä, Y. Matsumi, M. Kulmala, T. Hussein, P. Nurmi, and S. Tarkoma. Transit pollution exposure monitoring using low-cost wearable sensors. Transportation Research Part D: Transport and Environment, 98:102981, 2021.

Optimizing renewable energy generation and management

The examples of research activities are presented in the below list of publications.

M.A. Zaidan, N.H. Motlagh, B. Zakeri, T. Petäjä, M. Kulmala, and S. Tarkoma. IrMaSet: Intelligent weather forecaster system for hyperlocal renewable energies. IEEE Consumer Electronics Magazine, 13(5):61–74, 2024.

S.A. Nabavi, N.H. Motlagh, M.A. Zaidan, A. Aslani, and B. Zakeri. Deep learning in energy modeling: Application in smart buildings with distributed energy generation. IEEE Access, 9:125439–125461, 2021.

S.A. Nabavi, A. Aslani, M.A. Zaidan, M. Zandi, S. Mohammadi, and N.H. Motlagh. Machine learning modellings for energy consumption for residential and commercial sectors. Energies, 13(19):5171, 2020.