About
I studied Maths at Oxbridge and Imperial. Then I worked in the financial industry as a…
Experience
Education
Publications
-
Climate Change Impact on Agricultural Land Suitability: An Interpretable Machine Learning-Based Eurasia Case Study
with Valeriy Shevchenko, Daria Taniushkina, Aleksander Lukashevich, Aleksandr Bulkin, Kirill Kovalev, Veronika Narozhnaia, Nazar Sotiriadi, Alexander Krenke, Yury Maximov
The United Nations has identified improving food security and reducing hunger as essential components of its sustainable development goals. As of 2021, approximately 828 million people worldwide are experiencing hunger and malnutrition, with numerous fatalities reported. Climate change significantly impacts agricultural…with Valeriy Shevchenko, Daria Taniushkina, Aleksander Lukashevich, Aleksandr Bulkin, Kirill Kovalev, Veronika Narozhnaia, Nazar Sotiriadi, Alexander Krenke, Yury Maximov
The United Nations has identified improving food security and reducing hunger as essential components of its sustainable development goals. As of 2021, approximately 828 million people worldwide are experiencing hunger and malnutrition, with numerous fatalities reported. Climate change significantly impacts agricultural land suitability, potentially leading to severe food shortages and subsequent social and political conflicts. To address this pressing issue, we have developed a machine learning-based approach to predict the risk of substantial land suitability degradation and changes in irrigation patterns. Our study focuses on Central Eurasia, a region burdened with economic and social challenges.
This study represents a pioneering effort in utilizing machine learning methods to assess the impact of climate change on agricultural land suitability under various carbon emissions scenarios. Through comprehensive feature importance analysis, we unveil specific climate and terrain characteristics that exert influence on land suitability. Our approach achieves remarkable accuracy, offering policymakers invaluable insights to facilitate informed decisions aimed at averting a humanitarian crisis, including strategies such as the provision of additional water and fertilizers. This research underscores the tremendous potential of machine learning in addressing global challenges, with a particular emphasis on mitigating hunger and malnutrition. -
Accessing Convective Hazards Frequency Shift with Climate Change using Physics-Informed Machine Learning
with Mikhail Mozikov, Ilya Makarov, Alexandr Bulkin, Daria Taniushkina, Yury Maximov.
In this paper we discuss and address the challenges of predicting extreme atmospheric events like intense rainfall, hail, and strong winds. These events can cause significant damage and have become more frequent due to climate change. Integrating climate projections with machine learning techniques helps improve forecasting accuracy and identify regions where these events become most frequent and dangerous.…with Mikhail Mozikov, Ilya Makarov, Alexandr Bulkin, Daria Taniushkina, Yury Maximov.
In this paper we discuss and address the challenges of predicting extreme atmospheric events like intense rainfall, hail, and strong winds. These events can cause significant damage and have become more frequent due to climate change. Integrating climate projections with machine learning techniques helps improve forecasting accuracy and identify regions where these events become most frequent and dangerous. To achieve reliable and accurate prediction, we propose a robust neural network architecture that outperforms multiple baselines in accuracy and reliability. Our physics-informed algorithm heavily utilizes the whole range of problem-specific physics, including a specific set of features and climate projections data. The analysis also emphasizes the landscape impact on the frequency distribution of these events, providing valuable insights for effective adaptation strategies in response to climate change. -
Climate Change and Future Food Security: Predicting the Extent of Cropland Gain or Degradation
with Daria Tanushkina, Valeriy Shevchenko, Aleksander Lukashevich, Aleksandr Bulkin, Kirill Kovalev, Veronika Narozhnaia, Nazar Sotiriadi, Alexander Krenke, Yury Maximov
Agriculture is crucial in sustaining human life and civilization that relies heavily on natural resources. This industry faces new challenges, such as climate change, a growing global population, and new models for managing food security and water resources. Through a machine learning framework, we estimate the future…with Daria Tanushkina, Valeriy Shevchenko, Aleksander Lukashevich, Aleksandr Bulkin, Kirill Kovalev, Veronika Narozhnaia, Nazar Sotiriadi, Alexander Krenke, Yury Maximov
Agriculture is crucial in sustaining human life and civilization that relies heavily on natural resources. This industry faces new challenges, such as climate change, a growing global population, and new models for managing food security and water resources. Through a machine learning framework, we estimate the future productivity of croplands based on CMIP5 climate projections on moderate carbon emission scenario. We demonstrate that Vietnam and Thailand are at risk with a 10\% and 14\% drop in rice production, respectively, whereas the Philippines is expected to increase its output by 11\% by 2026 compared with 2018. We urge proactive international collaboration between regions facing crop land gain and degradation to mitigate the climate change and population growth impacts reducing our society's vulnerability. Our study provides critical information on the effects of climate change and human activities on land productivity and uses that may assist such collaboration. -
Importance Sampling Approach for Dynamic Stochastic Optimal Power Flow Control
with Aleksander Lukashevich, Aleksander Bulkin, Ilya Makarov, Yury Maximov
Renewable energy sources (RES) has become common in modern power systems, helping to address decarbonization and energy security goals. Despite being attractive, RES such as solar and have low inertia and high uncertainty, thus compromising power grid stability and increasing the risk of energy blackouts. Stochastic (chance-constrained) optimization and other state-of-the-art algorithms to optimize and control power…with Aleksander Lukashevich, Aleksander Bulkin, Ilya Makarov, Yury Maximov
Renewable energy sources (RES) has become common in modern power systems, helping to address decarbonization and energy security goals. Despite being attractive, RES such as solar and have low inertia and high uncertainty, thus compromising power grid stability and increasing the risk of energy blackouts. Stochastic (chance-constrained) optimization and other state-of-the-art algorithms to optimize and control power generation under uncertainty either explicitly assume the distribution of renewables, or use data-driven approximations. The latter becomes time-consuming and inaccurate, esp. when optimizing over multiple time steps. This paper considers a discrete-time chance-constraint direct current optimal power flow control problem for minimizing power generation costs subjected to power balance and security constraints. We propose an importance-sampling-based data-driven approximation for the optimal automated generation control, which allows to improve accuracy and reduce data requirements compared to state-of-the-art methods. We support the proposed approach theoretically and empirically. The results demonstrate the approach superior performance in handling generation uncertainty, enhancing the stability of renewable-integrated power systems, and facilitating the transition to clean energy. -
Adjoint Sensitivity Method for Kohn-Sham Equations
We study the discrete adjoint to Roothan equations and develop a fast approach to calculate the total derivative of KS-DFT electronic energy with respect to parameters of exchange-correlation functional, proving it both theoretically and computationally correct.
Other authors -
-
Are Cryptocurrency Markets Running Behind the Fed? A Significant Shift in Crypto Markets Microstructure
SSRN
In this research we show that 2021 became a year when crypto markets significantly adjusted behavioural patterns, showing an increased institutional influence.
We have come to two key conclusions that might indicate significant changes in the cryptocurrency market microstructure.
Firstly, in contrast to recent research, we note that BTC/USD was sensitive to major Fed policy announcements in Q2-Q3 2021 similar to main asset classes.
Secondly, OTC Liquidity Providers tend to provide…In this research we show that 2021 became a year when crypto markets significantly adjusted behavioural patterns, showing an increased institutional influence.
We have come to two key conclusions that might indicate significant changes in the cryptocurrency market microstructure.
Firstly, in contrast to recent research, we note that BTC/USD was sensitive to major Fed policy announcements in Q2-Q3 2021 similar to main asset classes.
Secondly, OTC Liquidity Providers tend to provide twice as narrow spreads in comparison to Centralised Crypto Exchanges during market volatility related to macroeconomic news.Other authorsSee publication -
Differentiable programming for particle physics simulations
JETP
We describe how to apply adjoint sensitivity methods to backward Monte Carlo schemes arising from simulations of particles passing through matter. Relying on this, we demonstrate derivative based techniques for solving inverse problems for such systems without approximations to underlying transport dynamics. We are implementing those algorithms for various scenarios within a general purpose differentiable programming C++17 library NOA (github.com/grinisrit/noa).
-
On the soliton resolution conjecture for wave maps
Oxford DPhil thesis
Broadly speaking, the research presented in this thesis is centered around the study of the Soliton Resolution Conjecture (SRC) for the wave maps equation in dimension 2+1, which is rooted in a belief held by the physics community since the 1970's predicting that for a large class of non-linear dispersive/hyperbolic evolution equations in mathematical physics (of which wave maps are an example), the solution should decompose into a decoupled sum of rescaled solitons plus a regular term, up to…
Broadly speaking, the research presented in this thesis is centered around the study of the Soliton Resolution Conjecture (SRC) for the wave maps equation in dimension 2+1, which is rooted in a belief held by the physics community since the 1970's predicting that for a large class of non-linear dispersive/hyperbolic evolution equations in mathematical physics (of which wave maps are an example), the solution should decompose into a decoupled sum of rescaled solitons plus a regular term, up to an error of asymptotically vanishing energy, as one evolves towards its maximal time of existence.
To be more precise, we consider large energy wave maps as in the resolution of the threshold conjecture by Sterbenz and Tataru, but more specifically into the unit round sphere (although parts of our argument work for general targets). We prove that, on a suitably chosen sequence of time slices approaching maximal existence, there is a decomposition of the map, up to an error with asymptotically vanishing energy, into a decoupled sum of rescaled solitons concentrating in the interior of the light cone and a term having asymptotically vanishing energy dispersion norm. For the latter, we further describe it as a linear gauge co-variant wave, concentrating on the null boundary and converging to a constant locally in the interior of the cone, in the energy space.
Similar and stronger results have been recently obtained in the equivariant setting by several authors, where better control on the dispersive term concentrating on the null boundary of the cone is provided and in some cases the asymptotic decomposition is shown to hold for all time. Here however, we do not impose any symmetry condition on the map itself and our strategy follows the one from bubbling analysis of harmonic maps into spheres in the supercritical regime due to Lin and Rivière, which we make work here in the hyperbolic context of. A large part of the work presented in this thesis has appeared in author's. -
Quantization of time-like energy for wave maps into spheres
Communications in Mathematical Physics
In this article we consider large energy wave maps in dimension 2+1, as in the resolution of the threshold conjecture by Sterbenz and Tataru (Commun. Math. Phys. 298(1):139–230, 2010; Commun. Math. Phys. 298(1):231–264, 2010), but more specifically into the unit Euclidean sphere 𝕊𝑛−1⊂ℝ𝑛 with 𝑛≥2, and study further the dynamics of the sequence of wave maps that are obtained in Sterbenz and Tataru (Commun. Math. Phys. 298(1):231–264, 2010) at the final rescaling for a first, finite or…
In this article we consider large energy wave maps in dimension 2+1, as in the resolution of the threshold conjecture by Sterbenz and Tataru (Commun. Math. Phys. 298(1):139–230, 2010; Commun. Math. Phys. 298(1):231–264, 2010), but more specifically into the unit Euclidean sphere 𝕊𝑛−1⊂ℝ𝑛 with 𝑛≥2, and study further the dynamics of the sequence of wave maps that are obtained in Sterbenz and Tataru (Commun. Math. Phys. 298(1):231–264, 2010) at the final rescaling for a first, finite or infinite, time singularity. We prove that, on a suitably chosen sequence of time slices at this scaling, there is a decomposition of the map, up to an error with asymptotically vanishing energy, into a decoupled sum of rescaled solitons concentrating in the interior of the light cone and a term having asymptotically vanishing energy dispersion norm, concentrating on the null boundary and converging to a constant locally in the interior of the cone, in the energy space. Similar and stronger results have been recently obtained in the equivariant setting by several authors (Côte, Commun. Pure Appl. Math. 68(11):1946–2004, 2015; Côte, Commun. Pure Appl. Math. 69(4):609–612, 2016; Côte, Am. J. Math. 137(1):139–207, 2015; Côte et al., Am. J. Math. 137(1):209–250, 2015; Krieger, Commun. Math. Phys. 250(3):507–580, 2004), where better control on the dispersive term concentrating on the null boundary of the cone is provided, and in some cases the asymptotic decomposition is shown to hold for all time. Here, however, we do not impose any symmetry condition on the map itself and our strategy follows the one from bubbling analysis of harmonic maps into spheres in the supercritical regime due to Lin and Rivière (Ann. Math. 149(2):785–829, 1999; Duke Math. J. 111:177–193, 2002), which we make work here in the hyperbolic context of Sterbenz and Tataru (Commun. Math. Phys. 298(1), 231–264, 2010).
-
Normal forms of convex lattice polytopes
We describe an algorithm for determining whether two convex polytopes P and Q, embedded in a lattice, are isomorphic with respect to a lattice automorphism. We extend this to a method for determining if P and Q are equivalent, i.e. whether there exists an affine lattice automorphism that sends P to Q. Methods for calculating the automorphism group and affine automorphism group of P are also described.
An alternative strategy is to determine a normal form such that P and Q are isomorphic if…We describe an algorithm for determining whether two convex polytopes P and Q, embedded in a lattice, are isomorphic with respect to a lattice automorphism. We extend this to a method for determining if P and Q are equivalent, i.e. whether there exists an affine lattice automorphism that sends P to Q. Methods for calculating the automorphism group and affine automorphism group of P are also described.
An alternative strategy is to determine a normal form such that P and Q are isomorphic if and only if their normal forms are equal. This is the approach adopted by Kreuzer and Skarke in their PALP software. We describe the Kreuzer-Skarke method in detail, and give an improved algorithm when P has many symmetries. Numerous examples, plus two appendices containing detailed pseudo-code, should help with any future reimplementations of these techniques. We conclude by explaining how to define and calculate the normal form of a Laurent polynomial.Other authorsSee publication
Honors & Awards
-
EPSRC Research Studentship
University of Oxford
-
Trinity College Examination Prize
Trinity College Cambridge
-
Scholar of Trinity College Cambridge
Trinity College Cambridge
-
Governors' Prize, Best BSc student in Mathematics
Imperial College London
-
Institute of Mathematics and its Applications Prize
Imperial College London
-
Gloucester Research Ltd Prize
Imperial College London - G Research
-
The Ken Allen Prize
Imperial College London - Ken Allen
-
Computing Entrance Scholarship
Imperial College London
Languages
-
English
Full professional proficiency
-
French
Native or bilingual proficiency
-
Russian
Native or bilingual proficiency
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More