Core-S2L2A

# Core-S2L2A

Contains a global coverage of Sentinel-2 (Level 2A) patches, each of size 1,068 x 1,068 pixels.

| Source | Sensing Type | Number of Patches | Patch Size | Total Pixels |
|--------|--------------|-------------------|------------|--------------|
|Sentinel-2 Level-2A |Optical Multispectral|2,245,886|1,068 x 1,068 (10 m) | > 2.564 Trillion |

## Content

| Column | Details | Resolution |
|--------|---------|------------|
| B01 | Coastal aerosol, 442.7 nm (S2A), 442.3 nm (S2B) | 60m |
| B02 | Blue, 492.4 nm (S2A), 492.1 nm (S2B) | 10m |
| B03 | Green, 559.8 nm (S2A), 559.0 nm (S2B) | 10m |
| B04 | Red, 664.6 nm (S2A), 665.0 nm (S2B) | 10m |
| B05 | Vegetation red edge, 704.1 nm (S2A), 703.8 nm (S2B) | 20m |
| B06 | Vegetation red edge, 740.5 nm (S2A), 739.1 nm (S2B) | 20m |
| B07 | Vegetation red edge, 782.8 nm (S2A), 779.7 nm (S2B) | 20m |
| B08 | NIR, 832.8 nm (S2A), 833.0 nm (S2B) | 10m |
| B8A | Narrow NIR, 864.7 nm (S2A), 864.0 nm (S2B) | 20m |
| B09 | Water vapour, 945.1 nm (S2A), 943.2 nm (S2B) | 60m |
| B11 | SWIR, 1613.7 nm (S2A), 1610.4 nm (S2B) | 20m |
| B12 | SWIR, 2202.4 nm (S2A), 2185.7 nm (S2B) | 20m |
| cloud_mask | Cloud Mask produced by SEnSeI | 10m |
| thumbnail | RGB composite [B04, B03, B02] saved as png | 10m |

## Spatial Coverage
This is a global monotemporal dataset. Nearly every piece of Earth captured by Sentinel-2 is contained at least once in this dataset (and only once, excluding some marginal overlaps).

The following figure demonstrates the spatial coverage (only black pixels are absent):

## Example Use

Interface scripts are available at https://github.com/ESA-PhiLab/Major-TOM

Here's a sneak peek with a thumbnail image:
```python
from fsspec.parquet import open_parquet_file
import pyarrow.parquet as pq
from io import BytesIO
from PIL import Image

PARQUET_FILE = 'part_03900' # parquet number
ROW_INDEX = 42 # row number (about 500 per parquet)

url = "https://huggingface.co/datasets/Major-TOM/Core-S2L2A/resolve/main/images/{}.parquet".format(PARQUET_FILE)
with open_parquet_file(url,columns = ["thumbnail"]) as f:
with pq.ParquetFile(f) as pf:
first_row_group = pf.read_row_group(ROW_INDEX, columns=['thumbnail'])

stream = BytesIO(first_row_group['thumbnail'][0].as_py())
image = Image.open(stream)
```

## Cite
[](https://arxiv.org/abs/2402.12095/)
```latex
@inproceedings{Major_TOM,
title={Major TOM: Expandable Datasets for Earth Observation},
author={Alistair Francis and Mikolaj Czerkawski},
year={2024},
booktitle={IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium},
eprint={2402.12095},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```

Powered by [Φ-lab, European Space Agency (ESA) 🛰️](https://huggingface.co/ESA-philab)

# Core-S2L2A
本数据集包含覆盖全球的哨兵2号（Sentinel-2）L2A级影像块，单块尺寸为1068×1068像素。

| 数据源 | 传感类型 | 影像块数量 | 影像块尺寸 | 总像素数 |
|--------|--------------|-------------------|------------|--------------|
| 哨兵2号L2A级载荷 | 光学多光谱 | 2,245,886 | 1068×1068（10米地面采样距离） | > 2.564万亿 |

## 数据内容
| 波段 | 详细说明 | 空间分辨率 |
|--------|---------|------------|
| B01 | 海岸气溶胶波段，S2A对应波长442.7nm、S2B对应波长442.3nm | 60m |
| B02 | 蓝波段，S2A对应波长492.4nm、S2B对应波长492.1nm | 10m |
| B03 | 绿波段，S2A对应波长559.8nm、S2B对应波长559.0nm | 10m |
| B04 | 红波段，S2A对应波长664.6nm、S2B对应波长665.0nm | 10m |
| B05 | 植被红边波段，S2A对应波长704.1nm、S2B对应波长703.8nm | 20m |
| B06 | 植被红边波段，S2A对应波长740.5nm、S2B对应波长739.1nm | 20m |
| B07 | 植被红边波段，S2A对应波长782.8nm、S2B对应波长779.7nm | 20m |
| B08 | 近红外（NIR）波段，S2A对应波长832.8nm、S2B对应波长833.0nm | 10m |
| B8A | 窄带近红外波段，S2A对应波长864.7nm、S2B对应波长864.0nm | 20m |
| B09 | 水汽波段，S2A对应波长945.1nm、S2B对应波长943.2nm | 60m |
| B11 | 短波红外（SWIR）波段，S2A对应波长1613.7nm、S2B对应波长1610.4nm | 20m |
| B12 | 短波红外（SWIR）波段，S2A对应波长2202.4nm、S2B对应波长2185.7nm | 20m |
| cloud_mask | 由SEnSeI工具生成的云掩膜产品 | 10m |
| thumbnail | 以PNG格式存储的[B04, B03, B02]RGB合成缩略图 | 10m |

## 空间覆盖范围
本数据集为全球单时相数据集，哨兵2号捕获的几乎所有地球地表区域均至少在此数据集中出现一次（仅存在少量边缘重叠区域，且每个区域仅包含一次观测）。

下图展示了该数据集的空间覆盖范围（仅黑色像素区域为无数据区域）：

## 示例应用
相关接口脚本可访问：https://github.com/ESA-PhiLab/Major-TOM
以下为缩略图预览示例代码：
python
from fsspec.parquet import open_parquet_file
import pyarrow.parquet as pq
from io import BytesIO
from PIL import Image

PARQUET_FILE = 'part_03900' # parquet number
ROW_INDEX = 42 # row number (about 500 per parquet)

url = "https://huggingface.co/datasets/Major-TOM/Core-S2L2A/resolve/main/images/{}.parquet".format(PARQUET_FILE)
with open_parquet_file(url,columns = ["thumbnail"]) as f:
with pq.ParquetFile(f) as pf:
first_row_group = pf.read_row_group(ROW_INDEX, columns=['thumbnail'])

stream = BytesIO(first_row_group['thumbnail'][0].as_py())
image = Image.open(stream)

## 引用
[![arxiv]("https://img.shields.io/badge/Open_Access-arxiv:2402.12095-b31b1b")]("https://arxiv.org/abs/2402.12095/")
latex
@inproceedings{Major_TOM,
title={Major TOM: Expandable Datasets for Earth Observation},
author={Alistair Francis and Mikolaj Czerkawski},
year={2024},
booktitle={IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium},
eprint={2402.12095},
archivePrefix={arXiv},
primaryClass={cs.CV}
}

由欧洲空间局（ESA）Φ实验室提供技术支持 🛰️