electricsheepafrica/african-crop-suitability-shift

---
title: African Crop Suitability Shift Dataset
emoji: 🌾
colorFrom: green
colorTo: yellow
sdk: other
pinned: true
license: cc-by-4.0
language:
- en
tags:
- climate-change
- agriculture
- africa
- crop-suitability
- food-security
- ipcc-ar6
- cgiar
- fao
- rcp-scenarios
- yield-impact
configs:
- config_name: rcp45_moderate
data_files: rcp45_moderate.csv
description: "RCP 4.5 moderate emissions pathway - intermediate climate forcing scenario with ~1.5°C warming by 2050"
- config_name: rcp85_high
data_files: rcp85_high.csv
description: "RCP 8.5 high emissions pathway - worst-case climate forcing scenario with ~2.8°C warming by 2050"
- config_name: adaptation_success
data_files: adaptation_success.csv
description: "RCP 4.5 with successful adaptation measures - enhanced resilience through climate-smart agriculture interventions"
---

# African Crop Suitability Shift Dataset

A comprehensive dataset projecting climate change impacts on crop suitability across 20 African nations under three climate scenarios through 2040-2060.

## Dataset Overview

| Metric | Value |
|--------|-------|
| Total Records | 32,000 |
| Countries | 20 |
| Crops | 10 |
| Scenarios | 3 |
| Time Slice | 2040-2060 |
| Baseline Period | 1981-2010 |

## Scenario Configurations

### `rcp45_moderate`
- **Emissions pathway**: RCP 4.5 (intermediate)
- **Projected warming**: ~1.5°C by 2050
- **Records**: ~10,667
- **File**: `rcp45_moderate.csv`

### `rcp85_high`
- **Emissions pathway**: RCP 8.5 (high emissions)
- **Projected warming**: ~2.8°C by 2050
- **Records**: ~10,667
- **File**: `rcp85_high.csv`

### `adaptation_success`
- **Emissions pathway**: RCP 4.5 + successful adaptation
- **Projected warming**: ~1.5°C with enhanced resilience
- **Records**: ~10,667
- **File**: `adaptation_success.csv`

## Countries Covered

South Africa, Nigeria, Kenya, Egypt, Morocco, Ghana, Ethiopia, Tanzania, Uganda, Ivory Coast, Senegal, Mali, Burkina Faso, Niger, Zambia, Zimbabwe, Mozambique, Cameroon, Malawi, Rwanda

## Crops Tracked

| Crop | Type | Climate Sensitivity |
|------|------|-------------------|
| Maize | Cereal (C4) | High (-6.0%/°C) |
| Sorghum | Cereal (C4) | Moderate (-3.5%/°C) |
| Millet | Cereal (C4) | Low (-3.0%/°C) |
| Rice | Cereal (C3) | Moderate (-3.2%/°C) |
| Wheat | Cereal (C3) | High (-6.0%/°C) |
| Cassava | Root/Tuber (C3) | Low (-2.5%/°C) |
| Teff | Cereal (C3) | Moderate (-4.0%/°C) |
| Coffee | Perennial (C3) | Very High (-8.0%/°C) |
| Cocoa | Perennial (C3) | High (-5.0%/°C) |
| Cotton | Fiber (C3) | Moderate (-4.5%/°C) |

## Columns

### Identification
- `record_id` — Unique identifier (format: ACSS-{SCENARIO}-{ID})
- `scenario` — Climate scenario name
- `country` — Country name
- `crop` — Crop name
- `latitude` / `longitude` — Geographic coordinates
- `elevation_m` — Elevation in meters
- `agro_ecological_zone` — GAEZ agro-ecological classification
- `region` — African sub-region

### Baseline Climate (1981-2010)
- `baseline_temp_c` — Mean annual temperature (°C)
- `baseline_rainfall_mm` — Mean annual rainfall (mm)
- `baseline_rainfall_cv` — Rainfall coefficient of variation
- `baseline_growing_season_days` — Growing season length (days)
- `baseline_frost_days` — Annual frost days
- `baseline_extreme_events_per_decade` — Drought/flood frequency

### Projected Climate (2040-2060)
- `projected_temp_c` — Projected mean annual temperature (°C)
- `temp_change_c` — Temperature change (°C)
- `projected_rainfall_mm` — Projected mean annual rainfall (mm)
- `rainfall_change_pct` — Rainfall change (%)
- `rainfall_variability_increase_pct` — Rainfall CV increase (percentage points)
- `projected_rainfall_reliability` — Rainfall reliability index (0-1)

### Growing Season
- `projected_growing_season_days` — Projected growing season length
- `growing_season_change_days` — Change in growing season (days)
- `temperature_stress_days_increase` — Additional days >35°C
- `projected_frost_days` — Projected annual frost days

### Water & Irrigation
- `baseline_irrigation_pct` — Baseline irrigated area (%)
- `projected_irrigation_pct` — Projected irrigated area (%)
- `irrigation_requirement_change_pct` — Irrigation demand change (%)
- `baseline_soil_moisture_deficit_days` — Baseline moisture deficit days
- `projected_soil_moisture_deficit_days` — Projected moisture deficit days
- `baseline_crop_water_requirement_mm` — Baseline crop water need (mm/season)
- `projected_crop_water_requirement_mm` — Projected crop water need (mm/season)

### Suitability & Yield
- `baseline_suitability_index` — Baseline crop suitability (0-1)
- `projected_suitability_index` — Projected crop suitability (0-1)
- `suitability_change` — Suitability index change
- `baseline_yield_t_ha` — Baseline yield (tonnes/ha)
- `projected_yield_t_ha` — Projected yield (tonnes/ha)
- `yield_change_pct` — Yield change (%)

### Pest & Disease
- `baseline_pest_pressure_index` — Baseline pest/disease pressure (0-1)
- `projected_pest_pressure_index` — Projected pest/disease pressure (0-1)
- `pest_pressure_change` — Pest pressure index change

### Extreme Events & Adaptation
- `projected_extreme_events_per_decade` — Projected extreme event frequency
- `adaptation_potential_score` — Country-level adaptation capacity (0-1)
- `market_access_index` — Market access indicator (0-1)

### Metadata
- `time_slice` — Projection period (2040-2060)
- `baseline_period` — Reference period (1981-2010)
- `data_source` — Source attribution
- `generation_date` — Generation date (YYYY-MM-DD)

## Parameter Calibration

All parameters are calibrated against peer-reviewed literature:

| Parameter | Source |
|-----------|--------|
| Temperature sensitivity | Zhao et al. (2017) *Nature*; IPCC AR6 Table 5.3 |
| Rainfall sensitivity | FAO GAEZ v4; CGIAR CCAFS crop modeling |
| CO2 fertilization | Deryng et al. (2016); Webber et al. (2018) |
| Baseline yields | FAOSTAT 2020-2023; CGIAR yield gap analyses |
| Suitability indices | GAEZ v4; FAO Ecocrop |
| Pest pressure | Deutsch et al. (2018) *Science*; IPCC AR6 Ch.5 |
| Adaptation potential | ND-GAIN Index; CGIAR adaptation assessments |
| Growing season changes | IPCC AR6 WGII Ch.5, Ch.9 |

## Key References

1. **IPCC AR6 WGII Chapter 5** — Food, Fibre, and other Ecosystem Products
2. **IPCC AR6 WGII Chapter 9** — Africa
3. **Zhao et al. (2017)** — Temperature effects on global crop yields. *Nature* 547:73-77
4. **Lobell et al. (2011)** — Climate trends and crop yields. *Science* 333:616-620
5. **Schlenker & Lobell (2010)** — African crop responses. *PNAS* 107:10661-10666
6. **Deutsch et al. (2018)** — Insect metabolism and pest pressure. *Science* 361:916-919
7. **FAO GAEZ v4** — Global Agro-Ecological Zones
8. **CGIAR CCAFS** — Climate Change, Agriculture and Food Security
9. **Deryng et al. (2016)** — CO2 fertilization and crop yields. *Nature Climate Change* 6:799-804
10. **Webber et al. (2018)** — CO2 effects on wheat. *Nature Climate Change* 8:323-328

## Usage

```python
from datasets import load_dataset

# Load specific scenario
ds = load_dataset("electricsheepafrica/african-crop-suitability-shift", "rcp45_moderate")
df = ds["train"].to_pandas()

# Load all scenarios
ds = load_dataset("electricsheepafrica/african-crop-suitability-shift")
for config in ds.keys():
df = ds[config].to_pandas()
print(f"{config}: {len(df)} records")
```

## License

CC-BY-4.0

## Citation

```bibtex
@dataset{african_crop_suitability_shift_2026,
title={African Crop Suitability Shift Dataset},
author={Electric Sheep Africa},
year={2026},
publisher={Hugging Face},
url={https://huggingface.co/datasets/electricsheepafrica/african-crop-suitability-shift},
note={Calibrated against IPCC AR6, CGIAR, FAO GAEZ, and peer-reviewed crop modeling literature}
}
```