[
  {
    "name": "rsf-24-12-20016-thermoelectric-heuslers",
    "url": "https://github.com/Danil-phy-cmp-120/rsf-24-12-20016-thermoelectric-heuslers",
    "kind_ru": "Данные и модели для термоэлектрических double half-Heuslers",
    "kind_en": "Data and models for thermoelectric double half-Heuslers",
    "description_ru": "Наборы данных CHGNet, train/validation/test split, checkpoint модели, ноутбуки fine-tuning и оценки, а также данные электронного показателя добротности.",
    "description_en": "CHGNet datasets, train/validation/test split, fine-tuned checkpoint, fine-tuning/evaluation notebooks and electronic figure-of-merit data.",
    "image": "assets/it/thermoelectric-dataset.svg",
    "image_alt_ru": "Тепловая шкала и точки датасета CHGNet",
    "image_alt_en": "Thermal scale and CHGNet dataset points",
    "tags": [
      "CHGNet",
      "dataset",
      "thermoelectrics",
      "Jupyter"
    ],
    "language": "Jupyter Notebook",
    "updated_at": "2026-03-23T06:33:39Z"
  },
  {
    "name": "all-d_heusler-evolutionary-optimizer",
    "url": "https://github.com/Danil-phy-cmp-120/all-d_heusler-evolutionary-optimizer",
    "kind_ru": "Генетический алгоритм и Random Forest для all-d-metal сплавов Гейслера",
    "kind_en": "Genetic algorithm and Random Forest for all-d-metal Heusler alloys",
    "description_ru": "Оптимизация конфигураций материалов с помощью GA и surrogate-моделей Random Forest, обученных на DFT-данных; код связан со статьёй в Journal of Applied Physics, 2024.",
    "description_en": "Optimization of material configurations using a GA and Random Forest surrogate models trained on DFT data; the code is associated with a 2024 Journal of Applied Physics article.",
    "image": "assets/it/heusler-optimizer.svg",
    "image_alt_ru": "Оптимизационная кривая и узлы моделей GA, RF, DFT и ML",
    "image_alt_en": "Optimization curve with GA, RF, DFT and ML model nodes",
    "tags": [
      "Python",
      "Random Forest",
      "DFT",
      "Genetic Algorithm",
      "Heusler"
    ],
    "language": "Python",
    "updated_at": "2025-12-09T13:06:19Z"
  },
  {
    "name": "Monte_Carlo",
    "url": "https://github.com/Danil-phy-cmp-120/Monte_Carlo",
    "kind_ru": "Python + C++ Monte Carlo framework",
    "kind_en": "Python + C++ Monte Carlo framework",
    "description_ru": "Гибридная среда для исследования конфигурационного пространства материалов: C++ ядро симуляции, Python-интерфейс, чтение/запись структур и сценарий запуска.",
    "description_en": "A hybrid environment for exploring configurational space in materials: C++ simulation engine, Python interface, structure input/output and a launch script.",
    "image": "assets/it/monte-carlo.svg",
    "image_alt_ru": "Решётка атомов для моделирования Монте-Карло",
    "image_alt_en": "Atomic lattice for Monte Carlo modelling",
    "tags": [
      "C++",
      "Python",
      "Monte Carlo",
      "materials"
    ],
    "language": "C++",
    "updated_at": "2025-04-09T13:28:57Z"
  },
  {
    "name": "Elast",
    "url": "https://github.com/Danil-phy-cmp-120/Elast",
    "kind_ru": "Workflow для расчёта упругого тензора в VASP",
    "kind_en": "VASP elastic tensor workflow",
    "description_ru": "Генерация деформированных структур, запуск VASP-задач на кластере и парсер выходных файлов для извлечения упругих постоянных.",
    "description_en": "Generation of strained structures, VASP cluster job submission and output parsing for extracting elastic constants.",
    "image": "assets/it/elastic-tensor.svg",
    "image_alt_ru": "Кристаллическая ячейка и строки упругого тензора",
    "image_alt_en": "Crystal cell and elastic tensor rows",
    "tags": [
      "VASP",
      "elasticity",
      "Python",
      "HPC"
    ],
    "language": "Python",
    "updated_at": "2025-04-09T13:19:22Z"
  },
  {
    "name": "VASP_scripts",
    "url": "https://github.com/Danil-phy-cmp-120/VASP_scripts",
    "kind_ru": "Коллекция Python-скриптов для VASP",
    "kind_en": "Python scripts collection for VASP",
    "description_ru": "Инструменты для генерации структур, анализа зонной структуры и DOS, термодинамических расчётов, магнитных моментов, BoltzTraP, Wannier90 и шаблонов SLURM/qsub.",
    "description_en": "Tools for structure generation, band structure and DOS analysis, thermodynamic calculations, magnetic moments, BoltzTraP workflows, Wannier90 post-processing and SLURM/qsub templates.",
    "image": "assets/it/vasp-workflows.svg",
    "image_alt_ru": "Схема вычислительного workflow VASP и HPC",
    "image_alt_en": "VASP and HPC workflow diagram",
    "tags": [
      "Python",
      "VASP",
      "Wannier90",
      "BoltzTraP",
      "SLURM"
    ],
    "language": "Python",
    "updated_at": "2025-04-09T13:14:25Z"
  },
  {
    "name": "double_half_heusler_optimization",
    "url": "https://github.com/Danil-phy-cmp-120/double_half_heusler_optimization",
    "kind_ru": "GNN для прогнозирования термоэлектрических свойств",
    "kind_en": "GNN for thermoelectric property prediction",
    "description_ru": "Модель графовой нейронной сети для прогнозирования свойств по кристаллическим структурам и составам; цель — ускорение поиска эффективных термоэлектриков.",
    "description_en": "A graph neural network model for predicting properties from crystal structures and compositions, aimed at accelerating the discovery of efficient thermoelectric materials.",
    "image": "assets/it/gnn-materials.svg",
    "image_alt_ru": "Графовая нейронная сеть для скрининга материалов",
    "image_alt_en": "Graph neural network for materials screening",
    "tags": [
      "GNN",
      "PyTorch",
      "CGCNN",
      "thermoelectrics"
    ],
    "language": "Jupyter Notebook",
    "updated_at": "2025-04-09T12:55:12Z"
  }
]