electricsheepafrica/africa-zmb-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
- zmb
pretty_name: "Zambia: IBTrACS Storm Tracks"
dataset_info:
splits:
- name: train
num_examples: 41720
- name: test
num_examples: 10430
---

# Zambia: IBTrACS Storm Tracks

**Publisher:** HDX · **Source:** [HDX](https://data.humdata.org/dataset/zmb-ibtracs-tropical-storm-tracks) · **License:** `cc-by-igo` · **Updated:** 2026-02-24

---

## 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: **ZMB**.

*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)** | 52,150 |
| **Columns** | 12 (3 numeric, 8 categorical, 1 datetime) |
| **Train split** | 41,720 rows |
| **Test split** | 10,430 rows |
| **Geographic scope** | ZMB |
| **Publisher** | HDX |
| **HDX last updated** | 2026-02-24 |

---

## Variables

**Geographic** — `iso_time`, `lat` (range -46.9–8.3), `lon` (range 11.3–119.1).

**Outcome / Measurement** — `number` (range 1.0–145.0).

**Identifier / Metadata** — `sid` (2023036S12117, 2000032S11116, 1951008S07074), `esa_source` (HDX), `esa_processed` (2026-04-06).

**Other** — `basin` (South Indian, North India, ), `subbasin` (Missing, Western Australia, Arabian Sea), `nature` (Tropical, Not reported, Mixture(contradicting report from different agencies)), `wmo_wind` ( , 20, 25), `wmo_pres` ( , 1000, 997).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-zmb-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, 1951008S07074 |
| `number` | float64 | 0.0% | 1.0 – 145.0 (mean 28.019) |
| `basin` | object | 0.0% | South Indian, North India, |
| `subbasin` | object | 0.0% | Missing, Western Australia, Arabian Sea |
| `iso_time` | datetime64[ns] | 0.0% | |
| `nature` | object | 0.0% | Tropical, Not reported, Mixture(contradicting report from different agencies) |
| `lat` | float64 | 0.0% | -46.9 – 8.3 (mean -18.4075) |
| `lon` | float64 | 0.0% | 11.3 – 119.1 (mean 52.8138) |
| `wmo_wind` | object | 0.0% | , 20, 25 |
| `wmo_pres` | object | 0.0% | , 1000, 997 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-06 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `number` | 1.0 | 145.0 | 28.019 | 13.0 |
| `lat` | -46.9 | 8.3 | -18.4075 | -17.9 |
| `lon` | 11.3 | 119.1 | 52.8138 | 51.9 |

---

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

---

## Citation

```bibtex
@dataset{hdx_africa_zmb_ibtracs_tropical_storm_tracks,
title = {Zambia: IBTrACS Storm Tracks},
author = {HDX},
year = {2026},
url = {https://data.humdata.org/dataset/zmb-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:
- 现有数据
language:
- 英语
license: cc-by-4.0
multilinguality:
- 单语言
size_categories:
- 10000 < n < 100000
source_datasets:
- 原始数据集
task_categories:
- 其他
task_ids: []
tags:
- 非洲
- 人道主义
- HDX（人道主义数据交换，Humanitarian Data Exchange）
- Electric Sheep Africa
- 气旋-飓风-台风
- hxl
- ZMB（赞比亚）
pretty_name: "赞比亚：IBTrACS风暴路径数据集"
dataset_info:
splits:
- name: 训练集
num_examples: 41720
- name: 测试集
num_examples: 10430
---

# 赞比亚：IBTrACS风暴路径数据集

**发布方：** HDX（人道主义数据交换，Humanitarian Data Exchange） · **来源：** [HDX](https://data.humdata.org/dataset/zmb-ibtracs-tropical-storm-tracks) · **许可证：** `cc-by-igo` · **更新时间：** 2026-02-24

---

## 摘要

国际最佳路径档案气候管理计划（International Best Track Archive for Climate Stewardship, IBTrACS）项目是当前可获取的最完整的全球热带气旋数据集。该项目整合了多机构的近期及历史热带气旋数据，构建了一套统一的、公开可用的最佳路径数据集，以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
- ISO_TIME：采用ISO 8601格式的观测时间（格式为YYYY-MM-DD hh:mm:ss）
- BASIN：当前风暴所处的大洋域
- SUBBASIN：当前风暴所处的次级大洋域
- 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（每年重新从1开始计数）
- LAT：风暴平均位置的纬度（整合了各来源提供的位置数据）
- LON：风暴平均位置的经度（整合了各来源提供的位置数据）
- WMO_WIND：由世界气象组织（World Meteorological Organization, WMO）指定认定机构给出的最大持续风速
- WMO_PRES：由WMO指定认定机构给出的最低中心气压

本数据集的每一行均代表一条地理定位点观测数据。时间覆盖范围由`iso_time`列标注。地理覆盖范围：**ZMB（赞比亚）**。

*本数据集由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适配机器学习的Parquet格式。*

---

## 数据集特征

| 项 | 详情 |
|---|---|
| **领域** | 气候与环境 |
| **观测单元** | 地理定位点观测数据 |
| **总行数** | 52150 |
| **列数** | 12列（3列数值型、8列分类型、1列日期时间型） |
| **训练集划分** | 41720行 |
| **测试集划分** | 10430行 |
| **地理覆盖范围** | ZMB（赞比亚） |
| **发布方** | HDX |
| **HDX最后更新时间** | 2026-02-24 |

---

## 变量说明

**地理相关字段**：`iso_time`、`lat`（取值范围：-46.9~8.3）、`lon`（取值范围：11.3~119.1）。
**结果与测量字段**：`number`（取值范围：1.0~145.0）。
**标识符与元数据字段**：`sid`（示例值：2023036S12117、2000032S11116、1951008S07074）、`esa_source`（HDX）、`esa_processed`（2026-04-06）。
**其他字段**：`basin`（取值：南印度洋、北印度洋等）、`subbasin`（取值：缺失、西澳大利亚海域、阿拉伯海）、`nature`（取值：热带气旋、未报告、混合（不同机构报告存在矛盾））、`wmo_wind`（示例值：空、20、25）、`wmo_pres`（示例值：空、1000、997）。

---

## 快速入门

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-zmb-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% | 2023036S12117、2000032S11116、1951008S07074 |
| `number` | float64 | 0.0% | 1.0 ~ 145.0（均值：28.019） |
| `basin` | object | 0.0% | 南印度洋、北印度洋等 |
| `subbasin` | object | 0.0% | 缺失、西澳大利亚海域、阿拉伯海 |
| `iso_time` | datetime64[ns] | 0.0% | 无 |
| `nature` | object | 0.0% | 热带气旋、未报告、混合（不同机构报告存在矛盾） |
| `lat` | float64 | 0.0% | -46.9 ~ 8.3（均值：-18.4075） |
| `lon` | float64 | 0.0% | 11.3 ~ 119.1（均值：52.8138） |
| `wmo_wind` | object | 0.0% | 空、20、25 |
| `wmo_pres` | object | 0.0% | 空、1000、997 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-06 |

---

## 数值统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `number` | 1.0 | 145.0 | 28.019 | 13.0 |
| `lat` | -46.9 | 8.3 | -18.4075 | -17.9 |
| `lon` | 11.3 | 119.1 | 52.8138 | 51.9 |

---

## 数据整理流程

原始数据通过CKAN API从HDX下载，并转换为Parquet格式。列名被统一转换为小写蛇形命名法。常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。基于解析成功率（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，并以Snappy压缩格式的Parquet文件保存。

---

## 局限性说明

- 本数据源自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误报告值、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/zmb-ibtracs-tropical-storm-tracks)以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_zmb_ibtracs_tropical_storm_tracks,
title = {Zambia: IBTrACS Storm Tracks},
author = {HDX},
year = {2026},
url = {https://data.humdata.org/dataset/zmb-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提供商。尼日利亚拉各斯。*