Part 1: Project Overview & Architecture

1. Project Overview

1.1 Welcome & Introduction

The primary goal of agriculture is to feed populations while maintaining resource efficiency and soil health. Traditional agricultural decisions—such as what crop to grow on a specific plot of land—are often based on historical guesswork. This can lead to crop failures, low yields, and resource waste.

OptiCrop is a data-driven Smart Agricultural Production Optimization Engine that uses machine learning to solve this problem. By assessing key soil nutrients (Nitrogen, Phosphorous, Potassium) and local weather metrics (temperature, humidity, pH, and rainfall), the system predicts the highest-yielding crop for any given plot.

1.2 System Architecture Flow Diagram

Here is how data and decisions flow through the application:

graph TD
    A[1. Crop_recommendation.csv Dataset] --> B[2. Data Cleaning & Jupyter EDA]
    B --> C[3. StandardScaler Scaling & train.py Comparison]
    C --> D[4. Save Models & Scalers as Joblib files]
    D --> E[5. Flask Web Server app.py]
    E --> F[6. HTML/CSS/JS Frontend Form UI]