:
🌊 Florida Keys Coral Reef Health Analysis & Prediction 🐠 This project aims to analyze and predict the health of the coral reefs in the Florida Keys. Using a dataset that includes information about coral cover, species richness, and environmental conditions, we apply data analysis, machine learning, and time series forecasting to understand trends and predict future reef conditions.
📊 Project Overview The health of coral reefs is a critical indicator of marine ecosystem stability. This project focuses on analyzing coral cover and species richness over time, exploring factors influencing coral health (such as environmental data), and creating predictive models to forecast future coral reef conditions.
The main objectives of this project are:
📈 Analyze historical trends in coral cover and species richness.
🌍 Visualize data using heatmaps, plots, and other charts.
🔍 Identify factors influencing coral health.
🤖 Predict future coral reef health using time series and machine learning models.
📂 Dataset The dataset used in this project includes various columns such as coral species data, site information, environmental conditions, and survey results. Key columns include:
Year: Year of the survey.
Subregion: Specific area within the Florida Keys.
Coral Species: Data on various coral species (e.g., Acropora_cervicornis, Porites_porites).
Environmental Factors: Temperature, nutrients, pollution, etc.
Coral Cover: Percentage of coral cover at the surveyed site.
Species Richness: Count of coral species present.
🛠️ Technologies Used Python 🐍: For data manipulation, visualization, and modeling.
Libraries:
Pandas: Data manipulation and analysis.
Matplotlib & Seaborn: Data visualization.
Scikit-learn: Machine learning models and evaluation.
📝 Steps in the Project
- Data Preprocessing 🧹 Clean and preprocess the data, handling missing values and converting data types.
Focus on essential columns like Year, Subregion, and total_coral_cover.
- Data Exploration & Visualization 📉 Analyze trends in coral cover and species richness over time.
Create heatmaps to visualize coral cover and species richness by region.
Explore correlations between environmental factors (temperature, nutrients) and coral health.
- Predictive Modeling 🤖 Model Selection: Use Random Forest, XGBoost, and Linear Regression for coral cover prediction.
Time Series Forecasting: Use Prophet for predicting future coral cover trends.
Model Evaluation: Evaluate models using metrics like RMSE.
- Model Interpretation & Insights 🧐 Plot actual vs predicted coral cover values to visually assess model accuracy.
Use feature importance from Random Forest and XGBoost to identify key predictors of coral health.
Data Visualizations: Trend lines, heatmaps, and scatter plots to understand coral health over time.
Predictive Models: Forecasts for future coral cover, model accuracy metrics, and insights on coral health.
📧 Contact For any questions or feedback, feel free to open an issue in the repository or contact me at:
Email: bhavnanahar245@gmail.com 📧 👏 Acknowledgments Thanks to the creators of the dataset and any libraries used in this project.
Special thanks to the open-source community for providing tools and frameworks that made this analysis possible.