🚢 Ship Fuel Consumption & CO₂ Emission Analysis

📌 Overview:

This project analyzes fuel consumption patterns and CO₂ emission levels for four ship types operating within Nigerian waterways. The goal is to uncover operational trends, environmental impact, and efficiency insights from a maritime perspective.

🛠️ Tools Used:

• Python

• Pandas

• Matplotlib

• Seaborn

• Tableau
  
  

📊 Skills Demonstrated:

• 🔧 Data Simulation: Created realistic datasets mimicking marine fuel usage and emissions profiles.
  
  

• 🔍 Exploratory Data Analysis (EDA): Investigated key metrics like fuel consumption rates, emission trends per ship type, and time-based usage patterns.
  
  

• 📈 Data Visualization: Built insightful charts and dashboards to communicate findings.
  
  

• 📐 Statistical Analysis: Applied summary statistics and distribution analysis to quantify patterns.

📊 Key Insights

This analysis uncovers critical patterns in fuel consumption and CO₂ emissions across Nigerian ship types, informing sustainability strategies:

• Tanker Ships as Primary Emitters: Tanker Ships exhibit the highest average fuel consumption (~10,735 liters/month) and CO₂ emissions (~29,600 kg/month), over 3-6x higher than other types. Statistical tests (ANOVA F=783.69, p<0.001; Tukey HSD) confirm significant differences, positioning tankers as top priorities for emission reductions in oil-heavy routes.

• Surfer Boats: Efficiency Leaders: Surfer Boats show the lowest consumption (~1,564 liters/month) and emissions (~4,300 kg/month), with tight variability. They serve as a benchmark for retrofitting other vessels, potentially cutting fleet-wide fuel use by 30-40%.

• Mid-Tier Similarity: Fishing Trawlers (~3,067 liters) and Oil Service Boats (~2,527 liters) have no significant pairwise differences (Tukey p>0.05), likely due to overlapping mid-range operations—ideal for shared efficiency initiatives like joint maintenance programs.

• Engine Efficiency Impact: Strong negative correlation (r ≈ -0.6) with fuel consumption; improving efficiency from ~70% to 90% could yield 20-30% savings, especially for variable types like Fishing Trawlers.

• Seasonal & Weather Influences: Peaks in stormy months (e.g., 15-25% higher consumption in Moderate/Stormy conditions) highlight opportunities for weather-based scheduling and route optimization.

• Direct Fuel-CO₂ Link: Near-perfect correlation (r=0.99) reinforces emissions as a fuel proxy, supporting policies like carbon pricing for high-impact ships.

These insights enable targeted interventions to reduce Nigeria's maritime carbon footprint while optimizing costs.

⚠️ Limitations

While the analysis provides robust insights using simulated realistic data, the following constraints should be noted:

• Simulated Data: The dataset is generated based on parameterized ranges (e.g., distances, efficiency)—real-world data from sources like NIMASA or vessel logs could introduce additional variability (e.g., cargo weights, actual delays) for greater accuracy.

• Scope Focus: Limited to four ship types, monthly aggregates, and Nigerian routes; excludes factors like crew operations, fuel prices, or international voyages.

• Variable Integration: Weather is categorical (Calm/Moderate/Stormy) without quantitative metrics (e.g., wind speed); engine efficiency is randomized but not modeled interactively with other variables in depth.

• Statistical Assumptions: ANOVA/Tukey assume normality and homogeneity, potential outliers (e.g., max fuel ~24,000 liters) may influence results; further tests (e.g., non-parametric alternatives) could validate.

• Descriptive Focus: Insights are primarily exploratory; predictive elements (e.g., forecasting peaks) are outlined but not implemented.

Future work could address these by incorporating real datasets, advanced modeling (e.g., regression with weather interactions), or predictive tools like ARIMA for emissions forecasting.

🔗 Call to Action:

Interested in the code, insights, or visual dashboards?

👉 Visit My GitHub Profile for full access to repositories, detailed notebooks, and Tableau dashboards.

👉 Download the cleaned Dataset on my kaggle page here

Power BI Dashboard

Ship Types Featured in the Project

Visualizations 

Thank you for your time