🌍 Climate Trends & Exoplanet Discoveries: A Data-Driven Analysis

Overview

This project presents a comprehensive data-driven analysis of two critical scientific domains: climate change trends and exoplanet discoveries. By leveraging Python-based data analysis and visualization techniques, this study aims to uncover insights into global temperature variations and the rapid expansion of exoplanet detections.

The key areas of analysis include:

• 📈 Historical Global Temperature Trends (1900-2021) – Investigating long-term warming patterns.
• 🪐 Exoplanet Discoveries & Discovery Methods (1990-2021) – Analyzing detection rates and techniques.
• 📊 Advanced Statistical Analysis & Visualizations – Applying statistical methods to interpret trends.
• 🔬 Machine Learning Applications (Future Work) – Exploring predictive modeling potential.

Project Scope

1. Climate Change Data Analysis

Global temperature data from 1900 to 2023 is examined to identify long-term climate trends. The dataset contains yearly maximum, minimum, and average temperatures. Various statistical techniques are applied, including polynomial regression, to detect the extent of global warming.

Key objectives:

• Extract and process historical temperature records.
• Identify warming trends using regression analysis.
• Visualize temperature variations over time.

2. Exoplanet Discovery Analysis

Exoplanet discovery data from 1990 to 2021 is analyzed to explore the growth of detected exoplanets and their discovery methods. The dataset contains details about planets detected using techniques such as the transit method, radial velocity, and direct imaging.

Key objectives:

• Investigate yearly exoplanet detection rates.
• Analyze dominant discovery techniques.
• Apply statistical modeling to understand discovery trends.

Notebooks Overview

1. Exoplanet Detection Analysis (exoplanet_detection.ipynb)

• Loads and processes exoplanet discovery data.
• Analyzes detection trends and methods.
• Visualizes detection statistics over time.

2. Hybrid CNN-Radial Basis Function Model (hybrid_cnn_radial.ipynb)

• Explores the application of hybrid neural networks for classification.
• Implements a Convolutional Neural Network (CNN) with a radial basis function layer.
• Evaluates performance on relevant datasets.

3. Stellar Seismic Detection (steller_seismic_detection.ipynb)

• Investigates seismic activities of stars using astrophysical datasets.
• Applies machine learning techniques to classify seismic events.
• Provides insights into stellar oscillation patterns.

Key Findings

🚀 Major Insights:

• Exoplanet discoveries have exponentially increased since 1990, with the transit method emerging as the most effective detection approach.
• Advanced statistical techniques such as polynomial regression and Poisson modeling provide deeper insights into trends.
• Future implementation of machine learning may enhance predictive capabilities in both climate and exoplanetary research.

Technologies & Tools

• Programming Language: Python
• Key Libraries:
  • 📈 pandas – Data processing and analysis.
  • 📁 matplotlib & seaborn – Data visualization.
  • 🔢 numpy – Statistical computations.

This project offers a data-centric approach to understanding two of the most pressing scientific inquiries of our time: the impact of climate change and the search for worlds beyond our own.