electricsheepafrica/africa-ssd-ibtracs-tropical-storm-tracks

--- annotations_creators: - no-annotation language_creators: - found language: - en license: cc-by-4.0 multilinguality: - monolingual size_categories: - 1K<n<10K source_datasets: - original task_categories: - other task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - cyclones-hurricanes-typhoons - hxl - ssd pretty_name: "South Sudan: IBTrACS Storm Tracks" dataset_info: splits: - name: train num_examples: 3815 - name: test num_examples: 953 --- # South Sudan: IBTrACS Storm Tracks **Publisher:** HDX · **Source:** [HDX](https://data.humdata.org/dataset/ssd-ibtracs-tropical-storm-tracks) · **License:** `cc-by-igo` · **Updated:** 2025-05-23 --- ## Abstract The International Best Track Archive for Climate Stewardship (IBTrACS) project is the most complete global collection of tropical cyclones available. It merges recent and historical tropical cyclone data from multiple agencies to create a unified, publicly available, best-track dataset that improves inter-agency comparisons. Fields available: SID: A unique storm identifier (SID) assigned by IBTrACS algorithm. ISO_TIME: Time of the observation in ISO format (YYYY-MM-DD hh:mm:ss) BASIN: Basin of the current storm position SUBBASIN: Sub-basin of the current storm position NATURE: Type of storm (a combination of the various types from the available sources) NUMBER: Number of the storm for the year (restarts at 1 for each year LAT: Mean position - latitude (a combination of the available positions) LON: Mean position - longitude (a combination of the available positions) WMO_WIND: Maximum sustained wind speed assigned by the responsible WMO agency WMO_PRES: Minimum central pressure assigned by the responsible WMO agency. Each row in this dataset represents geolocated point observations. Temporal coverage is indicated by the `iso_time` column(s). Geographic scope: **SSD**. *Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).* --- ## Dataset Characteristics | | | |---|---| | **Domain** | Climate and environment | | **Unit of observation** | Geolocated point observations | | **Rows (total)** | 4,769 | | **Columns** | 12 (3 numeric, 8 categorical, 1 datetime) | | **Train split** | 3,815 rows | | **Test split** | 953 rows | | **Geographic scope** | SSD | | **Publisher** | HDX | | **HDX last updated** | 2025-05-23 | --- ## Variables **Geographic** — `iso_time`, `lat` (range -26.1–20.5), `lon` (range 34.3–93.0). **Outcome / Measurement** — `number` (range 2.0–142.0). **Identifier / Metadata** — `sid` (1996288N09092, 2016102S12074, 1992331S11082), `esa_source` (HDX), `esa_processed` (2026-04-08). **Other** — `basin` (North India, South Indian, ), `subbasin` (Missing, Arabian Sea, Bay of Bengal), `nature` (Tropical, Not reported, Disturbance), `wmo_wind` ( , 25, 30), `wmo_pres` ( , 1000, 1002). --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-ssd-ibtracs-tropical-storm-tracks") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() ``` --- ## Schema | Column | Type | Null % | Range / Sample Values | |---|---|---|---| | `sid` | object | 0.0% | 1996288N09092, 2016102S12074, 1992331S11082 | | `number` | float64 | 0.0% | 2.0 – 142.0 (mean 72.4566) | | `basin` | object | 0.0% | North India, South Indian, | | `subbasin` | object | 0.0% | Missing, Arabian Sea, Bay of Bengal | | `iso_time` | datetime64[ns] | 0.0% | | | `nature` | object | 0.0% | Tropical, Not reported, Disturbance | | `lat` | float64 | 0.0% | -26.1 – 20.5 (mean 0.497) | | `lon` | float64 | 0.0% | 34.3 – 93.0 (mean 57.7845) | | `wmo_wind` | object | 0.0% | , 25, 30 | | `wmo_pres` | object | 0.0% | , 1000, 1002 | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-08 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `number` | 2.0 | 142.0 | 72.4566 | 89.0 | | `lat` | -26.1 | 20.5 | 0.497 | 0.9 | | `lon` | 34.3 | 93.0 | 57.7845 | 56.3 | --- ## Curation Raw data was downloaded from HDX via the CKAN API and converted to Parquet. Column names were lowercased and standardised to snake_case. Common missing-value markers (`N/A`, `null`, `none`, `-`, `unknown`, `no data`, `#N/A`) were unified to `NaN`. 4 column(s) were cast from string to numeric or datetime based on parse-success rate (>85% threshold). The dataset was split 80/20 into train and test partitions using a fixed random seed (42) and saved as Snappy-compressed Parquet. --- ## Limitations - Data originates from HDX and has not been independently validated by ESA. - Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection. - Refer to the [original HDX dataset page](https://data.humdata.org/dataset/ssd-ibtracs-tropical-storm-tracks) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_ssd_ibtracs_tropical_storm_tracks, title = {South Sudan: IBTrACS Storm Tracks}, author = {HDX}, year = {2025}, url = {https://data.humdata.org/dataset/ssd-ibtracs-tropical-storm-tracks}, note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)} } ``` --- *[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — Africa's ML dataset infrastructure. Lagos, Nigeria.*annotations_creators: - 无注释 language_creators: - 公开资源采集 language: - 英语 license: cc-by-4.0 multilinguality: - 单语言 size_categories: - 1000 < n < 10000 source_datasets: - 原始数据集 task_categories: - 其他 task_ids: [] tags: - 非洲 - 人道主义 - HDX - electric-sheep-africa - 气旋、飓风与台风 - HXL - SSD pretty_name: "南苏丹：IBTrACS风暴路径" dataset_info: splits: - name: 训练集 num_examples: 3815 - name: 测试集 num_examples: 953 --- # 南苏丹：IBTrACS风暴路径 **发布方：人道主义数据交换（Humanitarian Data Exchange, HDX） · 来源：[HDX](https://data.humdata.org/dataset/ssd-ibtracs-tropical-storm-tracks) · 许可证：`cc-by-igo` · 更新日期：2025-05-23** --- ## 摘要 国际最佳路径档案气候管理（International Best Track Archive for Climate Stewardship, IBTrACS）项目是目前已公开的最完整的全球热带气旋数据集集合。该项目整合了多机构的最新及历史热带气旋数据，构建了统一的公开最佳路径数据集，可提升不同机构间的比对效率。 可用字段如下： SID：IBTrACS算法分配的唯一风暴标识符（SID）。 ISO_TIME：采用ISO 8601格式的观测时间（格式为YYYY-MM-DD hh:mm:ss）。 BASIN：当前风暴位置所属的洋盆。 SUBBASIN：当前风暴位置所属的子洋盆。 NATURE：风暴类型（整合了各来源提供的多种分类）。 NUMBER：当年的风暴编号（每年从1重新开始计数）。 LAT：风暴平均位置的纬度（整合各来源提供的位置数据）。 LON：风暴平均位置的经度（整合各来源提供的位置数据）。 WMO_WIND：由指定世界气象组织（World Meteorological Organization, WMO）机构分配的最大持续风速。 WMO_PRES：由指定WMO机构分配的最低中心气压。 本数据集的每一行均代表一条带地理定位的点观测数据。时间覆盖范围由`iso_time`列标注。地理覆盖范围：**SSD（南苏丹国家代码）**。 *本数据集已由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适用于机器学习的Parquet格式。* --- ## 数据集特征 | | | |---|---| | **领域** | 气候与环境 | | **观测单元** | 带地理定位的点观测数据 | | **总行数** | 4769 | | **列数** | 12（3个数值型列、8个分类型列、1个日期时间型列） | | **训练集划分** | 3815行 | | **测试集划分** | 953行 | | **地理覆盖范围** | SSD | | **发布方** | HDX | | **HDX最后更新时间** | 2025-05-23 | --- ## 变量分类 ### 地理相关字段 `iso_time`、`lat`（取值范围：-26.1~20.5）、`lon`（取值范围：34.3~93.0）。 ### 结果/测量字段 `number`（取值范围：2.0~142.0）。 ### 标识符/元数据字段 `sid`（示例值：1996288N09092、2016102S12074、1992331S11082）、`esa_source`（HDX）、`esa_processed`（2026-04-08）。 ### 其他字段 `basin`（北印度洋、南印度洋等）、`subbasin`（缺失、阿拉伯海、孟加拉湾）、`nature`（热带气旋、未报告、大气扰动）、`wmo_wind`（空值、25、30）、`wmo_pres`（空值、1000、1002）。 --- ## 快速入门 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-ssd-ibtracs-tropical-storm-tracks") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() --- ## 数据结构 | 列名 | 数据类型 | 空值占比 | 取值范围/示例值 | |---|---|---|---| | `sid` | object | 0.0% | 1996288N09092、2016102S12074、1992331S11082 | | `number` | float64 | 0.0% | 2.0 – 142.0（均值：72.4566） | | `basin` | object | 0.0% | 北印度洋、南印度洋等 | | `subbasin` | object | 0.0% | 缺失、阿拉伯海、孟加拉湾 | | `iso_time` | datetime64[ns] | 0.0% | - | | `nature` | object | 0.0% | 热带气旋、未报告、大气扰动 | | `lat` | float64 | 0.0% | -26.1 – 20.5（均值：0.497） | | `lon` | float64 | 0.0% | 34.3 – 93.0（均值：57.7845） | | `wmo_wind` | object | 0.0% | 空值、25、30 | | `wmo_pres` | object | 0.0% | 空值、1000、1002 | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-08 | --- ## 数值汇总统计 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `number` | 2.0 | 142.0 | 72.4566 | 89.0 | | `lat` | -26.1 | 20.5 | 0.497 | 0.9 | | `lon` | 34.3 | 93.0 | 57.7845 | 56.3 | --- ## 数据整理流程 原始数据通过综合知识档案网（Comprehensive Knowledge Archive Network, CKAN）API从HDX下载，并转换为Parquet格式。所有列名被转换为小写并统一为蛇形命名规范。常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。根据解析成功率（阈值>85%），将4列从字符串类型转换为数值型或日期时间型。本数据集以固定随机种子（42）按80/20的比例划分为训练集与测试集，并保存为Snappy压缩的Parquet格式。 --- ## 局限性说明 - 本数据集源自HDX，未经过Electric Sheep Africa的独立验证。 - 自动化清洗流程无法修正原始数据集中的错报值、定义不一致或采样偏差问题。 - 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/ssd-ibtracs-tropical-storm-tracks)获取发布方提供的方法说明与注意事项。 --- ## 引用格式 bibtex @dataset{hdx_africa_ssd_ibtracs_tropical_storm_tracks, title = {South Sudan: IBTrACS Storm Tracks}, author = {HDX}, year = {2025}, url = {https://data.humdata.org/dataset/ssd-ibtracs-tropical-storm-tracks}, note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)} } --- *[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)——非洲机器学习数据集基础设施，尼日利亚拉各斯。*