Practical AI cases for solving ESG challenges

E Burnaev, E Mironov, A Shpilman, M Mironenko… - Sustainability, 2023 - mdpi.com
Artificial intelligence (AI) is a rapidly advancing area of research that encompasses
numerical methods to solve various prediction, optimization, and classification/clustering …

MineralImage5k: A benchmark for zero-shot raw mineral visual recognition and description

S Nesteruk, J Agafonova, I Pavlov, M Gerasimov… - Computers & …, 2023 - Elsevier
Mineral image recognition is a challenging computer vision problem. Without external tools,
even a human expert cannot distinguish some mineral species accurately. Previous …

Advancing forest carbon stocks' map** using a hierarchical approach with machine learning and satellite imagery

S Illarionova, P Tregubova, I Shukhratov, D Shadrin… - Scientific Reports, 2024 - nature.com
Remote sensing of forests is a powerful tool for monitoring the biodiversity of ecosystems,
maintaining general planning, and accounting for resources. Various sensors bring together …

Pseudo-labeling approach for land cover classification through remote sensing observations with noisy labels

I Mirpulatov, S Illarionova, D Shadrin, E Burnaev - IEEE Access, 2023 - ieeexplore.ieee.org
Satellite data allows us to solve a wide range of challenging tasks remotely, including
monitoring changing environmental conditions, assessing resources, and evaluating …

Flood extent and volume estimation using remote sensing data

G Popandopulo, S Illarionova, D Shadrin, K Evteeva… - Remote Sensing, 2023 - mdpi.com
Floods are natural events that can have a significant impacts on the economy and society of
affected regions. To mitigate their effects, it is crucial to conduct a rapid and accurate …

Enabling multi-part plant segmentation with instance-level augmentation using weak annotations

S Mukhamadiev, S Nesteruk, S Illarionova, A Somov - Information, 2023 - mdpi.com
Plant segmentation is a challenging computer vision task due to plant images complexity.
For many practical problems, we have to solve even more difficult tasks. We need to …

PseudoAugment: Enabling Smart Checkout Adoption for New Classes Without Human Annotation

S Nesteruk, S Illarionova, I Zherebzov, C Traweek… - IEEE …, 2023 - ieeexplore.ieee.org
Increasingly, automation helps to minimize human involvement in many mundane aspects of
life, especially retail. During the pandemic it became clear that shop automation helps not …

Wildfire spreading prediction using multimodal data and deep neural network approach

D Shadrin, S Illarionova, F Gubanov, K Evteeva… - Scientific Reports, 2024 - nature.com
Predicting wildfire spread behavior is an extremely important task for many countries. On a
small scale, it is possible to ensure constant monitoring of the natural landscape through …

Cisa: Context substitution for image semantics augmentation

S Nesteruk, I Zherebtsov, S Illarionova, D Shadrin… - Mathematics, 2023 - mdpi.com
Large datasets catalyze the rapid expansion of deep learning and computer vision. At the
same time, in many domains, there is a lack of training data, which may become an obstacle …