https://github.com/vlad1343/cropwise-uk

CropWise UK is an AI-driven platform that recommends the most suitable crops for UK cities using soil, climate, and pollution data. It combines machine learning, rule-based reasoning, and geospatial analytics to provide accurate, actionable, and sustainable planting insights for farmers, researchers, and policymakers.
https://github.com/vlad1343/cropwise-uk

agritech-project ai crop-recommendation-system docker docker-compose environment fastapi geospatial-analysis machine-learning python react typescript

Last synced: 3 months ago
JSON representation

CropWise UK is an AI-driven platform that recommends the most suitable crops for UK cities using soil, climate, and pollution data. It combines machine learning, rule-based reasoning, and geospatial analytics to provide accurate, actionable, and sustainable planting insights for farmers, researchers, and policymakers.

• Host: GitHub
• URL: https://github.com/vlad1343/cropwise-uk
• Owner: Vlad1343
• Created: 2025-10-15T10:38:30.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2025-10-19T12:22:07.000Z (8 months ago)
• Last Synced: 2025-10-19T21:52:33.011Z (8 months ago)
• Topics: agritech-project, ai, crop-recommendation-system, docker, docker-compose, environment, fastapi, geospatial-analysis, machine-learning, python, react, typescript
• Language: TypeScript
• Homepage:
• Size: 12.2 MB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🌾 CropWise UK — AI-Powered Crop Recommendation System

![System Architecture](photos/photo1.png)

## 🧭 Executive Summary

**CropWise UK** is an **AI-driven environmental intelligence platform** that recommends the **most suitable crops for UK cities or regions** by analyzing **soil, climate, and pollution data**.  

Key highlights:

- **Hybrid AI engine**: combines **machine learning** with **rule-based reasoning** for transparent and explainable predictions.  

- **Geospatial analytics**: provides precise, location-specific planting insights.  

- **Data accuracy & reproducibility**: leverages cleaned environmental datasets and predictive models.  

- **Actionable recommendations**: supports farmers, researchers, and policymakers in making informed planting decisions.  

- **Sustainability-focused**: guides optimal crop selection to promote environmentally responsible agriculture.

---

## 🛠️ Technology Badges

![React](https://img.shields.io/badge/React-18.2.0-61dafb?logo=react)

![TypeScript](https://img.shields.io/badge/TypeScript-5.5-blue?logo=typescript)

![Python](https://img.shields.io/badge/Python-3.11-3776ab?logo=python)

![FastAPI](https://img.shields.io/badge/FastAPI-0.111.0-009688?logo=fastapi)

![Vite](https://img.shields.io/badge/Vite-5.2.0-646cff?logo=vite)

![Docker](https://img.shields.io/badge/Docker-25.0-2496ed?logo=docker)

## ⚡ Data Precision & Features

![System Architecture](photos/photo2.png)

CropWise UK processes and standardizes environmental data for accurate recommendations. Key features include:

- **Temperature** (mean, seasonal)

- **Precipitation** (annual and monthly)

- **Soil Moisture Index**

- **pH**

- **Nutrients**: Nitrogen (N), Phosphorus (P), Potassium (K)

- **Soil Texture**: Sand ratio, Clay ratio, Silt ratio

- **Derived metrics**: Normalized ratios, soil moisture balance, and texture consistency

---

## 🛠️ Tech Stack

### **Frontend**

- **React + TypeScript**: Modular components with custom hooks.  

- **Vite**: Fast bundling and optimized HMR.  

- **Leaflet & Recharts**: Interactive maps and visual analytics.  

- **PWA-ready** for offline support and responsive experience.

### **Backend**

- **FastAPI + Uvicorn**: Async, high-performance APIs (<200ms latency).  

- **Circuit breaker & fallback** for resilience under external API downtime.  

### **Data & AI**

- **Hybrid ML + Rule-based scoring** for explainable crop recommendations.  

- **Scikit-learn pipelines + Joblib** for persistent, reproducible models.  

- **Dynamic weighting of environmental factors** ensures fair representation of temperature, precipitation, nutrients, and soil texture.  

### **Infrastructure**

- **Dockerized architecture** with Docker Compose.  

- **CI/CD pipelines** with automated testing, linting, and monitoring.

---

## 🧠 Professional Impact

![System Architecture](photos/photo3.png)

- **Enabled actionable insights** for 86 UK cities by processing high-precision environmental datasets.  

- **Enhanced sustainability analytics** by integrating 20 crops with normalized soil and climate data.  

- **Reduced inference latency** to sub-200ms via optimized async pipelines.  

- **Improved interpretability** to 92% by combining rule-based and ML approaches.  

- **Ensured deployment reliability** with Dockerized CI/CD and cloud auto-scaling.  

---

## 💡 Advanced Capabilities

![System Architecture](photos/photo5.png)

- Data sourced from **Open-Meteo API** for accurate and up-to-date environmental insights.

- **Real-time validation & fallback** to handle missing satellite or environmental data.

- **Interactive, map-driven analytics** with tooltips and dynamic charting.

---

## 🪴 Project Disclosure

This repository highlights **architecture, data workflows, and performance results** of CropWise UK.  

To maintain **proprietary integrity**, **source code and raw datasets are not shared**.  

Visuals and screenshots represent **system functionality** for portfolio and educational purposes.

---

## 📫 Contact & Collaboration

For collaborations, research partnerships, or technical inquiries:  

📧 **[vladshutkevych@gmail.com](mailto:vladshutkevych@gmail.com)**  

📍 Manchester, United Kingdom  

---

![System Architecture](photos/photo4.png)

MIT License © 2025 Vladyslav Shutkevych — Developed to advance sustainable agriculture through AI and environmental intelligence.