Logo Lanfrica

patience-2510789/maize_yield_prediction

Domaine:

agriculture

Type de record:

model
Créateur:
pat
HĂ´te:
ML model to predict maize harvest in Uasin Gishu County, Kenya # 🌽 Maize Yield Prediction — Uasin Gishu County, Kenya A machine learning web application that predicts maize harvest yields in Uasin Gishu County using historical climate, satellite, soil, and seed variety data. 🔗 **Live App:** maizeyieldprediction-kujsee… --- ## 📌 Project Summary | Item | Detail | |------|--------| | **Location** | Uasin Gishu County, Kenya | | **Target** | Maize Yield (Tonnes/Hectare) | | **Data Range** | 2005–2024 (20 years) | | **Model** | Linear Regression (R² = 0.76, MAE = ±0.30 t/ha) | | **Institution** | KCA University | --- ## 🗂 Project Structure ``` maize-prediction/ ├── app.py # Main Streamlit app (Predictor) ├── requirements.txt # Python dependencies ├── pages/ │ ├── 01_dashboard.py # Charts & insights dashboard │ └── 02_methodology.py # Full methodology & documentation ├── notebooks/ │ ├── 01_weather_download.ipynb # NASA POWER weather data │ ├── 02_soil_data.ipynb # ISRIC soil data │ ├── 03_ndvi_satellite.ipynb # MODIS NDVI satellite data │ ├── 04_yield_and_seeds.ipynb # Yield & seed variety data │ ├── 05_master_merge.ipynb # Merge all datasets │ └── 06_modelling.ipynb # Model training & evaluation ├── data/ │ ├── raw/ # Raw downloaded files │ └── processed/ # Cleaned, merged datasets └── outputs/ # Charts and saved model ``` --- ## 📂 Data Sources | Data Type | Source | Years | |-----------|--------|-------| | Weather & Climate | NASA POWER | 2005–2024 | | Satellite NDVI | NASA MODIS via ORNL | 2005–2024 | | Soil Properties | ISRIC SoilGrids | Static | | Maize Yield | Uasin Gishu County Agriculture Office | 2012–2023 | | Seed Varieties | KEPHIS + CIMMYT | 2005–2024 | --- ## 🤖 Model Performance | Model | MAE | RMSE | R² | |-------|-----|------|----| | **Linear Regression** ✅ | **0.300** | **0.364** | **0.763** …