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

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- cyclones-hurricanes-typhoons
- hxl
- rwa
pretty_name: "Rwanda: IBTrACS Storm Tracks"
dataset_info:
splits:
- name: train
num_examples: 10507
- name: test
num_examples: 2626
---

# Rwanda: IBTrACS Storm Tracks

**Publisher:** HDX · **Source:** [HDX](https://data.humdata.org/dataset/rwa-ibtracs-tropical-storm-tracks) · **License:** `cc-by-igo` · **Updated:** 2026-02-10

---

## 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: **RWA**.

*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)** | 13,134 |
| **Columns** | 12 (3 numeric, 8 categorical, 1 datetime) |
| **Train split** | 10,507 rows |
| **Test split** | 2,626 rows |
| **Geographic scope** | RWA |
| **Publisher** | HDX |
| **HDX last updated** | 2026-02-10 |

---

## Variables

**Geographic** — `iso_time`, `lat` (range -42.1–19.0), `lon` (range 18.7–119.1).

**Outcome / Measurement** — `number` (range 1.0–127.0).

**Identifier / Metadata** — `sid` (2023036S12117, 2000032S11116, 1976312S09090), `esa_source` (HDX), `esa_processed` (2026-04-07).

**Other** — `basin` (South Indian, North India, ), `subbasin` (Missing, Arabian Sea, Western Australia), `nature` (Tropical, Not reported, Mixture(contradicting report from different agencies)), `wmo_wind` ( , 20, 25), `wmo_pres` ( , 1000, 1005).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-rwa-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% | 2023036S12117, 2000032S11116, 1976312S09090 |
| `number` | float64 | 0.0% | 1.0 – 127.0 (mean 38.6139) |
| `basin` | object | 0.0% | South Indian, North India, |
| `subbasin` | object | 0.0% | Missing, Arabian Sea, Western Australia |
| `iso_time` | datetime64[ns] | 0.0% | |
| `nature` | object | 0.0% | Tropical, Not reported, Mixture(contradicting report from different agencies) |
| `lat` | float64 | 0.0% | -42.1 – 19.0 (mean -14.973) |
| `lon` | float64 | 0.0% | 18.7 – 119.1 (mean 50.4857) |
| `wmo_wind` | object | 0.0% | , 20, 25 |
| `wmo_pres` | object | 0.0% | , 1000, 1005 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-07 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `number` | 1.0 | 127.0 | 38.6139 | 19.0 |
| `lat` | -42.1 | 19.0 | -14.973 | -14.8 |
| `lon` | 18.7 | 119.1 | 50.4857 | 47.0 |

---

## 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/rwa-ibtracs-tropical-storm-tracks) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_rwa_ibtracs_tropical_storm_tracks,
title = {Rwanda: IBTrACS Storm Tracks},
author = {HDX},
year = {2026},
url = {https://data.humdata.org/dataset/rwa-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（no-annotation）
language_creators:
- 获取式（found）
language:
- 英语（en）
license: CC BY 4.0
multilinguality:
- 单语言（monolingual）
size_categories:
- 10K<n<100K
source_datasets:
- 原始数据集（original）
task_categories:
- 其他（other）
task_ids:
- 无
tags:
- 非洲（africa）
- 人道主义（humanitarian）
- HDX（Humanitarian Data Exchange, HDX）
- electric-sheep-africa（Electric Sheep Africa, ESA）
- 气旋-飓风-台风（cyclones-hurricanes-typhoons）
- HXL（Humanitarian Exchange Language, HXL）
- RWA（卢旺达国家代码，RWA）
pretty_name: "卢旺达：IBTrACS风暴路径"

# 卢旺达：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/rwa-ibtracs-tropical-storm-tracks) · **许可证：** `cc-by-igo` · **更新时间：** 2026-02-10

---

## 摘要

国际最佳路径档案气候管理（International Best Track Archive for Climate Stewardship, IBTrACS）项目是目前可用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，以创建统一的、公开可用的最佳路径数据集，助力跨机构比对工作。

可用字段：
SID：IBTrACS算法分配的唯一风暴标识符（SID）
ISO_TIME：采用ISO格式的观测时间（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次级洋盆
NATURE：风暴类型（整合了各来源提供的多种类型）
NUMBER：当年的风暴编号（每年从1重新开始计数）
LAT：平均位置纬度（整合各来源提供的位置数据）
LON：平均位置经度（整合各来源提供的位置数据）
WMO_WIND：由世界气象组织（World Meteorological Organization, WMO）责任机构指定的最大持续风速
WMO_PRES：由世界气象组织责任机构指定的最低中心气压

本数据集的每一行均代表一个带地理定位的点观测数据。时间覆盖范围由`iso_time`字段标注。地理覆盖范围：**卢旺达（RWA）**。

*由[Electric Sheep Africa（ESA）](https://huggingface.co/electricsheepafrica)整理为适配机器学习的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 |
| **总样本行数** | 13134 |
| **字段数** | 12（3个数值型、8个分类型、1个日期时间型） |
| **训练集划分** | 10507行 |
| **测试集划分** | 2626行 |
| **地理覆盖范围** | 卢旺达（RWA） |
| **发布方** | 人道主义数据交换（HDX） |
| **HDX最后更新时间** | 2026-02-10 |

---

## 字段说明

**地理相关字段** — `iso_time`、`lat`（取值范围-42.1–19.0）、`lon`（取值范围18.7–119.1）。
**结果/测量字段** — `number`（取值范围1.0–127.0）。
**标识符/元数据字段** — `sid`（示例值：2023036S12117、2000032S11116、1976312S09090）、`esa_source`（示例值：HDX）、`esa_processed`（示例值：2026-04-07）。
**其他字段** — `basin`（示例值：南印度洋、北印度洋）、`subbasin`（示例值：缺失、阿拉伯海、西澳大利亚海域）、`nature`（示例值：热带气旋、未报告、混合型（不同机构报告存在矛盾））、`wmo_wind`（示例值：空值、20、25）、`wmo_pres`（示例值：空值、1000、1005）。

---

## 快速上手

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-rwa-ibtracs-tropical-storm-tracks")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据结构

| 字段名 | 数据类型 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `sid` | 对象型（object） | 0.0% | 2023036S12117、2000032S11116、1976312S09090 |
| `number` | 浮点型（float64） | 0.0% | 1.0 – 127.0（均值38.6139） |
| `basin` | 对象型（object） | 0.0% | 南印度洋、北印度洋 |
| `subbasin` | 对象型（object） | 0.0% | 缺失、阿拉伯海、西澳大利亚海域 |
| `iso_time` | 日期时间型（datetime64[ns]） | 0.0% | 无示例 |
| `nature` | 对象型（object） | 0.0% | 热带气旋、未报告、混合型（不同机构报告存在矛盾） |
| `lat` | 浮点型（float64） | 0.0% | -42.1 – 19.0（均值-14.973） |
| `lon` | 浮点型（float64） | 0.0% | 18.7 – 119.1（均值50.4857） |
| `wmo_wind` | 对象型（object） | 0.0% | 空值、20、25 |
| `wmo_pres` | 对象型（object） | 0.0% | 空值、1000、1005 |
| `esa_source` | 对象型（object） | 0.0% | HDX |
| `esa_processed` | 对象型（object） | 0.0% | 2026-04-07 |

---

## 数值统计摘要

| 字段名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `number` | 1.0 | 127.0 | 38.6139 | 19.0 |
| `lat` | -42.1 | 19.0 | -14.973 | -14.8 |
| `lon` | 18.7 | 119.1 | 50.4857 | 47.0 |

---

## 数据整理流程

原始数据通过CKAN应用程序编程接口（Application Programming Interface, API）从HDX下载，并转换为Parquet格式。字段名称全部转为小写，并统一采用蛇形命名法（snake_case）。将常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。根据解析成功率（阈值>85%），将4个字段从字符串类型转换为数值型或日期时间型。本数据集采用固定随机种子（42）以80/20的比例划分为训练集与测试集，并保存为Snappy压缩的Parquet格式文件。

---

## 数据集局限性

- 数据源自HDX，未经过Electric Sheep Africa（ESA）的独立验证。
- 自动化清洗无法修正原始数据集中的错报、定义不一致或采样偏差问题。
- 有关发布方的方法论说明与免责条款，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/rwa-ibtracs-tropical-storm-tracks)。

---

## 引用格式

bibtex
@dataset{hdx_africa_rwa_ibtracs_tropical_storm_tracks,
title = {Rwanda: IBTrACS Storm Tracks},
author = {HDX},
year = {2026},
url = {https://data.humdata.org/dataset/rwa-ibtracs-tropical-storm-tracks},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}

---

*[Electric Sheep Africa（ESA）](https://huggingface.co/electricsheepafrica) — 非洲机器学习数据集基础设施平台，尼日利亚拉各斯。*