Read how IIASA works with research partners across the globe to deliver world-class research.
Science and policy must work together to achieve a sustainable future for humanity.
Artem Baklanov joined IIASA as a Postdoctoral Research Scholar in September 2014. He is affiliated with both the Ecosystems Services and Management Program (ESM) as well as the Advanced Systems Analysis Program (ASA), and has been working on the application of control theory, game theory, and machine learning to inform environmental decision making.
Environmental decision making needs to be informed in many ways, also depending on the scale:
- At the scale of a global economy, it is important to develop tools for a trade-off analysis in Integrated Assessment Models (IAMs);
- At the scale of countries, one has to take into account strategic interactions when designing institutions to deal with the environment as common good;
- At the level of citizens, an emerging area of citizen science (including crowd-sourced science, civic science, volunteer monitoring) calls for new robust methods to deal with the results of the crowdsourcing campaigns, in particular, methods for vote aggregation and data pre-processing.
Namely, nonlinearities in IAMs escalate the issue of consistency between short-term actions and long-term targets. Dr. Baklanov applies the attainable set approach to circumscribe possible short-term actions that are consistent with a specified long-term target, as well as to reveal which long-term targets are still attainable depending on a chosen short-term policy.
To analyze global socioeconomic problems, it is helpful to study models formulated as repeated games and use the concept of the strategic equilibrium to describe a rational outcome of multi-agent interactions. Dr. Baklanov focuses on strategies with restricted memory representing bounded rationality and explores how a small change in the complexity of strategies, which can be interpreted as a change in the boundedness of rationality, influences some important properties of the Nash equilibrium.
Public participation in scientific research is a new global trend helping to improve existing monitoring tools. To improve the quality of data collected at crowdsourcing campaigns, Dr. Baklanov uses vote aggregation procedures based on state-of-the-art machine learning algorithms and performs data pre-processing using computer vision algorithms to exclude ambiguous and low-quality images from visual inspection by volunteers.
Last update: 16-JAN-2019
Folberth C, Baklanov A, Balkovic J, Skalsky R, Khabarov N, & Obersteiner M (2019). Spatio-temporal downscaling of gridded crop model yield estimates based on machine learning. Agricultural and Forest Meteorology 264: 1-15. DOI:10.1016/j.agrformet.2018.09.021.
Baklanov A, Khachay M, & Pasynkov M (2019). Fully Convolutional Neural Networks for Mapping Oil Palm Plantations in Kalimantan. In: Learning and Intelligent Optimization. Eds. Battiti, R., Brunato, M., Kotsireas, I. & Pardalos, P., pp. 427-432 Cham, Switzerland: Springer. ISBN 978-3-030-05347-510.1007/978-3-030-05348-2_35.
Folberth C, Baklanov A, Balkovic J, Skalsky R, Khabarov N, & Obersteiner M (2018). Supplementary Datasets S1 and S2 for the paper “Spatio-temporal downscaling of gridded crop model yield estimates based on machine learning”.
Baklanov A, Khachay M, & Pasynkov M (2018). Application of fully convolutional neural networks to mapping industrial oil palm plantations. In: Analysis of Images, Social Networks and Texts. Eds. van der Aalst, W., Batagelj, V., Glavas, G., Ignatov, D., Khachay, M., Kuznetsov, S., Koltsova, O., Lomazova, I., Loukachevitch, N., Napoli, A. et al., pp. 145-158 Switzerland: Springer. ISBN 978-3-030-11027-710.1007/978-3-030-11027-7_16.
Baklanov A (2017). On a density property of weakly absolutely continuous measures. General case. Izvestiya Instituta Matematiki i Informatiki 2 (50): 3-12.
Chentsov A, Baklanov A, & Savenkov I (2017). On Control Problem with Constraints of Asymptotic Character. In: 8th International Conference on Physics and Control (PhysCon 2017). International Physics and Control Society (IPACS).
Baklanov A, Chentsov A, & Savenkov I (2017). On reachable sets for one-pulse controls under constraints of asymptotic character. Cybernetics and Physics 6 (4): 166-173.
Rekabsaz N, Lupu M, Baklanov A, Hanbury A, Duer A, & Anderson L (2017). Volatility Prediction using Financial Disclosures Sentiments with Word Embedding-based IR Models. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. pp. 1712-1721 Vancouver, Canada: Association for Computational Linguistics. 10.18653/v1/P17-1157.
Subkhankulova D, Baklanov A, & McCollum D (2017). Demand Side Management: A Case for Disruptive Behaviour. In: Advanced Computational Methods for Knowledge Engineering. Eds. Le, Nguyen-Thinh, van Do, Tien, Nguyen, Ngoc Thanh & Thi, Hoai An Le, pp. 47-59 Cham, Switzerland: Springer International Publishing AG. ISBN 978-3-319-61911-810.1007/978-3-319-61911-8_5.
Baklanov A (2016). On density properties of weakly absolutely continuous measures. Modern Problems in Mathematics and its Applications 1662: 62-72.
Baklanov A, Fritz S, Khachay M, Nurmukhametov O, Salk C, See L, & Shchepashchenko D (2016). Improved Vote Aggregation Techniques for the Geo-Wiki Cropland Capture Crowdsourcing Game. In: European Geosciences Union (EGU) General Assembly 2016, 17–22 April 2016, Vienna, Austria.
Baklanov A, Fritz S, Khachay M, Nurmukhametov O, Salk C, & Shchepashchenko D (2016). Votes Aggregation Techniques in Geo-Wiki Crowdsourcing Game: a Case Study. In: Proceedings of the 5th International Conference on Analysis of Images, Social Networks and Texts, AIST 2016, Yekaterinburg, Russia, April 7-9, 2016, Revised Selected Papers. pp. 50-60 Springer. (Submitted)
Baklanov A, Fritz S, Khachay M, Nurmukhametov O, & See L (2016). The Cropland Capture Game: good annotators versus vote aggregation methods. In: Advanced Computational Methods for Knowledge Engineering - Proceedings of the 4th International Conference on Computer Science, Applied Mathematics and Applications, ICCSAMA 2016, 2-3 May, 2016, Vienna, Austria. pp. 167-180 Cham, Switzerland: Springer International Publishing. ISBN 978-3-319-38884-710.1007/978-3-319-38884-7_13.
Nurmukhametov OR & Baklanov A (2016). A method for increasing the accuracy of image annotating in crowd-sourcing. Modern Problems in Mathematics and its Applications 1662: 206-214.
Chentsov AG & Baklanov AP (2015). On the question of construction of an attraction set under constraints of asymptotic nature. Proceedings of the Steklov Institute of Mathematics 291 (S1): 40-55. DOI:10.1134/S0081543815090035.
Nurmukhametov O, Baklanov A, Fritz S, Khachay M, Salk C, See L, & Shchepashchenko D (2015). How to Increase the Accuracy of Crowdsourcing Campaigns? In: Systems Analysis 2015 - A Conference in Celebration of Howard Raiffa, 11 -13 November, 2015, Laxenburg, Austria.
Chentsov AG & Baklanov A (2015). On an asymptotic analysis problem related to the construction of an attainability domain. Proceedings of the Steklov Institute of Mathematics 291 (1): 279-298. DOI:10.1134/S0081543815080222.
Chentsov AG & Baklanov Artem (2015). On an asymptotic analysis problem related to the construction of an attainability domain. Proceedings of the Steklov Institute of Mathematics 291: 292-311. DOI:10.1134/S0371968515040226.
Chentsov AG & Baklanov A (2014). A problem related to asymptotic attainability in the mean. Doklady Mathematics 90 (3): 762-765. DOI:10.1134/S1064562414070333.
International Institute for Applied Systems Analysis (IIASA)
Schlossplatz 1, A-2361 Laxenburg, Austria
Phone: (+43 2236) 807 0 Fax:(+43 2236) 71 313