Amir Mosavi

Amir Mosavi is an sassistant professor at Obuda University, and holds a visiting research position at Norwegian University of Science and Technology. He completed his graduate studies at London Kingston University and University of Waterloo in Sustainability Management and Engineering. He received his PhD in applied information technology and data science jointly from the University of Debrecen, University of Jyvaskyla, and the University of British Columbia. Operational research, decision science, time series prediction, climate change and sustainability science are Dr. Mosavi’s particular research interests.

Dr. Amir Mosavi, is recognized as a leading sustainability scientist, prized by the German Federal Minister of Education and Research, Professor Johanna Wanka, for his novelty in research and dedication to sustainable development. He is ranked among the top sustainability potentials who received the Green Talents Award, for his original research on the advancement of accurate prediction tools utilized to anticipate the climate change policies and disaster reduction. He believes that humanity requires accurate prediction and decision support tools to be able to analyze and reduce climate change impacts.

His further awards include; UNESCO Young Scientist Award, Alain Bensoussan Fellowship Award of European Research Consortium for Informatics and Mathematics, Australian Government Endeavour Research Fellowships Award, Green Talents Award, Austrian Government GO STYRIA-Karl-Franzens-Universitat Graz Award, TU-Darmstadt Future Talent Award, Finnish government CIMO Research Fellowship Award, IFAC Best Article Award, UNESCO-TWAS Award, Estonian Dora Fellowship Award, Estonian government Estophilus Award, Campus Hungary Fellowship Award, and Campus France Fellowship Award. In addition, Dr. Mosavi received a number of visiting fellowship awards from Simon Fraser University, Tallinn University of Technology, University of Oslo, University of Graz, University of Tartu, University of Bayreuth, Jonkoping University, and Leuphana University of Lüneburg.

Dr. Mosavi has a multidisciplinary and cross-disciplinary approach into science where he seeks simplified answers through artificial intelligence (AI) and machine learning (ML) models covering a wide range of applications. He, therefore, has investigated numerous applications areas and published in various peer-reviewed journals. Elsevier Journal of Solar Energy¹, Wiley Journal of Environmental Progress & Sustainable Energy², MDPI Journal of Energies³, Elsevier Journal of Physica Condensed Matter⁴, Computers Materials & Continua⁵, Elsevier Journal of Superlattices and Microstructures⁶, Acta Polytechnica Hungarica⁷, MDPI Journal of Energies⁸, Journal of Applied Mathematics⁹, and Journal of Artificial Intelligence & Data Mining¹⁰, are the examples of his recent research works. A list of his publications is available here.

Research Abstract  

Project 1. Sustainable Business Models for Biosphere Reserves. Managing the biosphere reserves is challenged with the uncertain economic, dynamic of the business environments and interrelationships which are highly effected by climate change, globalization, increasing complexity and information technologies. Through a collaboration with the International Coordinating Council of the Man and the Biosphere (MAB) Programme of UNESCO, Dr. Mosavi collaborates on the advancement of sustainable business models as an innovative tool for monitoring and assessment of sustainability in biosphere reserves. Sustainable Business Models contribute well in promoting sustainability, efficient management of natural resources, and improving national and international communication as well as efficient monitoring and training. In his research the social, environmental and economic state of Kiskunság Biosphere Reserve, and Pilis Biosphere Reserve in Hungary are monitored and predicted for a sustainable use where relationships between people and their environment is improved.

Project 2. Advancement in prediction models. Time series forecasting/prediction highly contributes to sustainability sciences and climate change risk reduction. Novel models of prediction based on ML, AI, and soft computing algorithms have recently shown great potential in dealing with uncertainty, and improving the generalization ability particularly in policy recommendations/analysis. Dr. Mosavi, during his visit to iASK, contributes to the advancement and investigation of such data-driven prediction models. “A hybrid machine learning approach for daily prediction of solar radiation, in Lecture Notes in Networks and Systems”, “a hybrid neuro-fuzzy algorithm for prediction of reference evapotranspiration, in Lecture Notes in Networks and Systems”, “prediction of fluid segregation by lattice Boltzmann method and ANFIS, in Canadian journal of chemistry”, “drought prediction with machine learning, a review, in Journal of Engineering Applications of Computational Fluid Mechanics”, “flood prediction using machine learning, literature review, in Journal of Engineering Applications of Computational Fluid Mechanics”, “energy consumption prediction using machine learning, in MDPI Journal of Energies”, and “energy demand prediction with machine learning in Journal of Energies”, are a number of his research manuscripts to contribute in providing a reliable platform for analyzing the what-if scenarios and policy recommendation.

Recent Publications

1. A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation – Conference paper was written by Amir Mosavi, Mehrnoosh Torabi, Pinar Ozturk, Annamaria Varkonyi-Koczy and Vajda Istvan – in Laukaitis G. (eds) Recent Advances in Technology Research and Education. 

2. A Hybrid Neuro-Fuzzy Algorithm for Prediction of Reference Evapotranspiration – Conference paper was written Amir Mosavi and Mohammad Edalatifar – in Laukaitis G. (eds) Recent Advances in Technology Research and Education

3. Modeling the time-dependent characteristics of perovskite solar cells. Solar Energy, (2018) 170, pp. 969-973.
4. ^{A Hybrid clustering and classification technique for forecasting short-term energy consumption. Environmental Progress & Sustainable Energy, (2018).}
5. Strategic Behavior of Retailers for Risk Reduction and Profit Increment via Distributed Generators and Demand Response Programs. Energies, (2018). 11(6), pp. 1-24.
6. Modeling the strain impact on refractive index and optical transmission rate. Physica B: Condensed Matter, (2018). 543, pp. 14-17.
7. Biodegradation of Medicinal Plants Waste in an Anaerobic Digestion Reactor for Biogas Production (2018).
8. Modeling the detection efficiency in photodetectors with temperature-dependent mobility and carrier lifetime. Superlattices and Microstructuresdoi (2018).
9. Dynamic Resource Allocation in Cloud Computing. Acta Polytechnica Hungarica, 14(4). (2017).
10. An Intelligent Artificial Neural Network-Response Surface Methodology Method for Accessing the Optimum Biodiesel and Diesel Fuel Blending Conditions in a Diesel Engine from the Viewpoint of Exergy and Energy Analysis. Energies, (2018). 11(4), p 860.
11. Reactive search optimization; application to multiobjective optimization problems. Applied Mathematics, (2012). 3(10), p 1572.
12. Mosavi, A. (2014). Data mining for decision making in engineering optimal design. Journal of AI and Data Mining, 2(1), pp. 7-14.