arXiv subjects

Timofey Grigoryev

Publications and source records attributed to Timofey Grigoryev.

6 recordsLinked to original sources

arXiv2026

Borey: A High-Resolution Regional Atmosphere-Ocean-Sea Ice-Wave Forecasting System and Hindcast Dataset for the Barents and Kara Seas

Borey is a high-resolution regional modeling and operational forecasting system for the Barents and Kara Seas. It combines WRF for the atmosphere, NEMO-SI3 for the ocean and sea ice, and WW3 for waves on approximately 3--6\,km grids, and generates daily forecasts to 72 hours. We describe the model chain and production workflow and present an accompanying hourly hindcast of surface conditions from August 2015 to August 2023. The archive provides aligned atmosphere, ocean, sea ice, and wave fields for regional marine studies and a baseline for evaluating the operational system. Comparisons with observations and observation-based products show that Borey captures much of the variability in near-surface atmospheric conditions and ocean temperature. Skill in the evaluated WRF, NEMO, and SI3 forecasts changes only modestly across the three-day window. The main limitations are persistent rather than rapidly growing errors: sea surface temperature is generally too cold, sea ice concentration and occurrence are overestimated during seasonal retreat, and significant wave height is underestimated. Borey should therefore complement observation-constrained products. The planned public release will provide hourly surface fields, native grids, provenance information, and validation outputs for regional analysis, model development, and carefully evaluated data-driven forecasting and data-assimilation research.

physics.ao-ph↗

arXiv2024

Data-Driven Uncertainty-Aware Forecasting of Sea Ice Conditions in the Gulf of Ob Based on Satellite Radar Imagery

The increase in Arctic marine activity due to rapid warming and significant sea ice loss necessitates highly reliable, short-term sea ice forecasts to ensure maritime safety and operational efficiency. In this work, we present a novel data-driven approach for sea ice condition forecasting in the Gulf of Ob, leveraging sequences of radar images from Sentinel-1, weather observations, and GLORYS forecasts. Our approach integrates advanced video prediction models, originally developed for vision tasks, with domain-specific data preprocessing and augmentation techniques tailored to the unique challenges of Arctic sea ice dynamics. Central to our methodology is the use of uncertainty quantification to assess the reliability of predictions, ensuring robust decision-making in safety-critical applications. Furthermore, we propose a confidence-based model mixture mechanism that enhances forecast accuracy and model robustness, crucial for reliable operations in volatile Arctic environments. Our results demonstrate substantial improvements over baseline approaches, underscoring the importance of uncertainty quantification and specialized data handling for effective and safe operations and reliable forecasting.

cs.CV↗

arXiv2022

Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting

Global warming made the Arctic available for marine operations and created demand for reliable operational sea ice forecasts to make them safe. While ocean-ice numerical models are highly computationally intensive, relatively lightweight ML-based methods may be more efficient in this task. Many works have exploited different deep learning models alongside classical approaches for predicting sea ice concentration in the Arctic. However, only a few focus on daily operational forecasts and consider the real-time availability of data they need for operation. In this work, we aim to close this gap and investigate the performance of the U-Net model trained in two regimes for predicting sea ice for up to the next 10 days. We show that this deep learning model can outperform simple baselines by a significant margin and improve its quality by using additional weather data and training on multiple regions, ensuring its generalization abilities. As a practical outcome, we build a fast and flexible tool that produces operational sea ice forecasts in the Barents Sea, the Labrador Sea, and the Laptev Sea regions.

cs.LG↗

arXiv2022

When, Why, and Which Pretrained GANs Are Useful?

The literature has proposed several methods to finetune pretrained GANs on new datasets, which typically results in higher performance compared to training from scratch, especially in the limited-data regime. However, despite the apparent empirical benefits of GAN pretraining, its inner mechanisms were not analyzed in-depth, and understanding of its role is not entirely clear. Moreover, the essential practical details, e.g., selecting a proper pretrained GAN checkpoint, currently do not have rigorous grounding and are typically determined by trial and error. This work aims to dissect the process of GAN finetuning. First, we show that initializing the GAN training process by a pretrained checkpoint primarily affects the model's coverage rather than the fidelity of individual samples. Second, we explicitly describe how pretrained generators and discriminators contribute to the finetuning process and explain the previous evidence on the importance of pretraining both of them. Finally, as an immediate practical benefit of our analysis, we describe a simple recipe to choose an appropriate GAN checkpoint that is the most suitable for finetuning to a particular target task. Importantly, for most of the target tasks, Imagenet-pretrained GAN, despite having poor visual quality, appears to be an excellent starting point for finetuning, resembling the typical pretraining scenario of discriminative computer vision models.

cs.LG↗

arXiv2020

Category-Learning with Context-Augmented Autoencoder

Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised artificial neural networks either struggle to do it or require fine tuning for each task individually. We associate this with the fact that a biological brain learns in the context of the relationships between observations, while an artificial network does not. We also notice that, though a naive data augmentation technique can be very useful for supervised learning problems, autoencoders typically fail to generalize transformations from data augmentations. Thus, we believe that providing additional knowledge about relationships between data samples will improve model's capability of finding useful inner data representation. More formally, we consider a dataset not as a manifold, but as a category, where the examples are objects. Two these objects are connected by a morphism, if they actually represent different transformations of the same entity. Following this formalism, we propose a novel method of using data augmentations when training autoencoders. We train a Variational Autoencoder in such a way, that it makes transformation outcome predictable by auxiliary network in terms of the hidden representation. We believe that the classification accuracy of a linear classifier on the learned representation is a good metric to measure its interpretability. In our experiments, present approach outperforms $\beta$-VAE and is comparable with Gaussian-mixture VAE.

cs.LG↗

arXiv2019

An analogue of the Perelomov-Popov formula for the Lie superalgebra Q(N)

In this short note we study the center of the universal enveloping algebra of the strange Lie superalgebra Q(N). We obtain an analogue of the well known Perelomov-Popov formula (1968) for central elements of this algebra - an expression of the central characters through the highest weight parameters.

math.RT↗