{
  "model_name": "Earthformer",
  "model_type": "earthformer",
  "architectures": [
    "Earthformer"
  ],
  "framework": "PyTorch",
  "domain": "climate-and-atmosphere",
  "task": "spatiotemporal-forecasting",
  "implementation": {
    "entry_point": "model/earthformer.py",
    "scope": "two-level hierarchical Cuboid Attention space-time Transformer with BTHWC input and output"
  },
  "architecture": {
    "family": "hierarchical space-time Transformer with Cuboid Attention",
    "attention_mechanism": "cuboid-window attention with optional global vectors",
    "input_format": "BTHWC",
    "encoder": {
      "levels": 2,
      "stem": "Conv2d 3x3 stride 2",
      "downsample": "Conv2d 3x3 stride 2",
      "cuboid_pattern": [
        [
          2,
          4,
          4
        ]
      ]
    },
    "decoder": {
      "cuboid_pattern": "axial",
      "cross_attention": "CuboidCross(T,1,1): future queries attend to history at each spatial site",
      "prediction": "learned future query with per-frame up-projection and encoder skip connection"
    },
    "activation": "GELU",
    "normalization": "LayerNorm",
    "repository_default_config": {
      "purpose": "CPU smoke verification with synthetic SEVIR data",
      "dims": [
        4,
        8
      ],
      "depths": [
        1,
        1
      ],
      "heads": 1,
      "num_global_vectors": 1,
      "ff_ratio": 2.0,
      "dropout": 0.0
    }
  },
  "data": {
    "dataset": "SEVIR",
    "variable": "vertically_integrated_liquid",
    "frame_interval_minutes": 5,
    "input_length": 13,
    "output_length": 12,
    "channels": 1,
    "official_spatial_size": [
      384,
      384
    ],
    "official_sampling": "sequent with stride 12",
    "default_smoke_spatial_size": [
      32,
      32
    ],
    "normalization": "unit"
  },
  "configuration_sources": [
    "conf/config.yaml",
    "model/earthformer.py",
    "script/data_loader.py",
    "configuration.json"
  ]
}