International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 06 | Jun 2025
p-ISSN: 2395-0072
www.irjet.net
Climate Change Impact Prediction Using District Level Data. Er. Ananda Sarjerao Mane Er. Harshvardhan Jitendra Mohite, Er. Ayush Ankush Jadhav Er. Girish Prakash Mohole Guide: Prof. S.R. Kadam H.O.D: Prof. A. N. Patil JAYWANT COLLEGE OF ENGINEERING & POLYTECHNIC, KILLE MACHINDRA GAD, SANGLI. AFFILIATED TO DR. BABASAHEB AMBEDKAR TECHNOLOGICAL UNIVERSITY, LONERE 2024 – 2025 Maharashtra, India ---------------------------------------------------------------------***--------------------------------------------------------------------environmental indicators differ at the district level is critical Abstract - This research addresses the growing concern of
for developing effective and region-specific climate mitigation and adaptation strategies.
climate variability by analyzing environmental data from various districts within Maharashtra, India. It centers on understanding how key environmental indicators—such as atmospheric temperature, carbon dioxide (CO₂) emissions, annual rainfall, forest depletion, rapid urban expansion, and a synthesized Climate Impact Index—vary regionally. The primary goal is to identify whether these indicators demonstrate statistically significant disparities among districts, which is achieved through the application of one-way Analysis of Variance (ANOVA).
This project focuses on analyzing district-wise variations in essential environmental parameters such as temperature, CO₂ emissions, precipitation, deforestation, and urbanization. To uncover statistically significant differences across regions, the study applies one-way ANOVA, a robust statistical technique for comparing means across multiple groups. However, statistical analysis alone does not provide predictive insights.
To move beyond statistical insight and toward proactive planning, the study also incorporates a predictive machine learning framework. A regression-based model is implemented using Python, leveraging powerful data science libraries including Pandas for data manipulation, NumPy for numerical computations, and Joblib for model serialization and deployment. The project uses MongoDB, a NoSQL database, to efficiently store and manage vast environmental datasets, enabling quick access and scalability.
To address this, the project integrates machine learning through a regression-based model developed in Python. By using libraries like Pandas, NumPy, and Joblib, the system learns from historical environmental data and forecasts potential future trends. The data is managed using MongoDB, allowing efficient storage and retrieval of large datasets for seamless processing. The aim is to build a comprehensive, scalable, and insightful platform that supports district-level climate intelligence, ultimately helping authorities, researchers, and policymakers make informed, data-driven decisions to combat climate change locally.
The developed system not only identifies climate trends but also forecasts future changes at the district level. This predictive capacity offers actionable intelligence for regional planners and policymakers to tailor environmental strategies specific to local conditions. By integrating statistical evaluation with machine learning, this project supports datadriven, evidence-based decision-making in environmental governance and climate resilience planning Key Words: : one way ANOVA, Deforestation, Regression Model, CO₂ Emission, Urbanization
Irjet Template sample paragraph .Define abbreviations and acronyms the first time they are used in the text, even after they have been defined in the abstract. Abbreviations such as IEEE, SI, MKS, CGS, sc, dc, and rms do not have to be defined. Do not use abbreviations in the title or heads unless they are unavoidable.
1.INTRODUCTION
1.1 Significance of District-Level Climate Analysis
Climate change has emerged as one of the most pressing global challenges, with its effects varying significantly across different geographical regions. Maharashtra, a diverse and densely populated state in.
Climate conditions do not affect all regions equally; their impacts are shaped by local geography, urbanization, vegetation cover, and human activity. Maharashtra's districts exhibit diverse environmental profiles, making it essential to analyze climate data at a granular level. By focusing on district-wise patterns, this study helps identify high-risk zones, detect anomalies in environmental behavior, and formulate localized climate action plans.
India, experiences wide-ranging environmental conditions across its districts—making it an ideal subject for localized climate impact assessment. Understanding how
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 814