Soil Erosion Risk Analyzer (SERA) 🌍

A predictive modeling tool for identifying and quantifying soil erosion risks in varied terrains, with a focus on the geological challenges faced in Ghanaian communities.

---

Table of Contents

• Overview
• Key Features
• Tech Stack
• The Geological Model
• Installation & Usage
• Sample Output
• Author

---

Overview

SERA analyzes the relationship between environmental factors — Rainfall (Erosivity) and Slope (Erodibility) — to predict soil loss in tons per hectare, using Multiple Linear Regression. Study areas include the Akwapim-Togo Range and coastal belts of Ghana.

It serves as a Decision Support System (DSS) for geological engineers and local planning authorities, providing quantitative evidence for soil conservation strategies.

---

Key Features

• Predictive Modeling — Uses Scikit-learn to calculate erosion trends from historical geological data
• Dynamic Risk Assessment — Categorizes results into Low, Moderate, and High risk zones
• Automated Recommendations — Suggests engineering interventions (Bench Terracing, Check Dams, Reforestation) based on output severity
• Data Visualization — Generates Matplotlib graphs showing the regression trend line and specific risk coordinates

---

Tech Stack

Component	Technology
Language	Python 3.14
Data Analysis	Pandas, NumPy
Machine Learning	Scikit-learn (Linear Regression)
Visualization	Matplotlib

---

The Geological Model

SERA operates on the following derived regression equation:

Erosion = 0.018(Rainfall) + 0.429(Slope) - 2.036

Key insight: The coefficient on Slope (0.429) is significantly larger than that of Rainfall (0.018), confirming that slope gradient is the primary driver of land degradation in the study area. This provides a quantitative basis for prioritizing slope-stabilization interventions.

---

Installation & Usage

1. Clone the repository

git clone https://github.com/Kyeremeh-Cosmos/soil-erosion-analyzer.git
cd soil-erosion-analyzer

2. Set up a virtual environment

python -m venv .venv
source .venv/Scripts/activate    # Windows
# source .venv/bin/activate      # macOS / Linux

3. Install dependencies

pip install pandas numpy matplotlib scikit-learn

4. Run the application

python main.py

---

Sample Output

The visual output includes:

• 📈 Historical Trend Line — regression fit across the training data
• ⭐ Risk Coordinate (Gold Star) — plots the input scenario on the trend, allowing non-technical stakeholders to immediately visualize the impact of environmental changes on their land

---

Author

Kyeremeh Cosmos Computer Engineering & Engineering Student