Climate Change Detection System
Saurabh Gopal1, Aditya Landage2, Mayur Gawade3, Gyaneshwar Donakonda4 , Prof. Deepa Athawale5
1,2,3,4B.E student Department of Computer Engineering Bharat College of Engineering, Badlapur
5 Professor, Department of Computer Engineering, Bharat College of Engineering, Badlapur, Thane, Maharashtra - 421503
Abstract—
Climate change is one of the most pressing global challenges, with wide-ranging impacts on natural ecosystems, weather patterns, and human livelihoods. Timely and accurate detection of climate change signals is essential for informed decision-making and policy development. Traditional statistical approaches, while effective, often struggle with the complexity and scale of modern environmental datasets.This paper explores the application of machine learning (ML) techniques to climate change detection, with a specific focus on the Gradient Descent algorithm as a foundational optimization method. Machine learning enables the analysis of large, high- dimensional climate datasets, such as temperature records, CO₂ levels, and satellite imagery, uncovering hidden trends and anomalies that may not be evident through conventional methods. Gradient Descent plays a critical role in training predictive models by iteratively minimizing error, thereby improving the accuracy and reliability of climate forecasts and anomaly detection.Through case studies and experimental results, we demonstrate how ML models optimized via Gradient Descent can effectively identify climate change indicators and support early warning systems. The paper also discusses the challenges of applying machine learning to climate science, including data quality, model interpretability, and computational constraints. Overall, this research highlights the transformative potential of machine learning in advancing climate change detection and enhancing environmental decision-making.
Climate change detection is critical for understanding the evolving patterns of environmental transformations and their impacts on ecosystems, economies, and human health. This paper presents a comprehensive climate change detection system that leverages advanced data analytics, machine learning algorithms, and environmental datasets to identify and monitorclimate-related changes effectively. The system integrates data from diverse sources, including satellite imagery, weather stations, ocean buoys, and historical climate models, to enhance the accuracy of trend analysis. The model’s performance is evaluated through statistical metrics like score and mean squared error to ensure reliability.
Keywords: Machine Learning, linear regression, exponential regression, polynomial regression
