Sustainable climatic metrics determination with ensemble predictive analytics

Ashis Pattanaik, Vandana Sharma, Kanhaiya Kunj, Sushruta Mishra, Celestine Iwendi, Jude Osamor

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Downloads (Pure)


Sustainable features are dependent on vital climatic elements that has a prominent impact on the retention of sustainability provided its metrics are in desired domain. Regression analysis and ensemble learning models are some of the predictive analytics methods which were used to detect the association of every feature on sustainable criteria. Weather samples from Delhi during 1970-2020 is used in the research which considers features like humidity, pollutant level, temperature etc which are gathered from several authenticated sites like pollution management unit of India. After analyzing several elements affecting weather endurability, it is noticed that pollutant level and temperature exhibit the highest significance recording 30% and 44% respectively. Also the R-square metric of 86% and 82% was observed with implementation of analytics models. The major conclusion recorded that random forest outperformed regression model and it established the importance of predictive analytics in predicting sustainability results. The research validated the relevance of climatic tracking for regulating sustainability.

Original languageEnglish
Title of host publication2023 4th International Conference on Computation, Automation and Knowledge Management (ICCAKM)
Number of pages8
ISBN (Electronic)9798350393248
ISBN (Print)9798350393255
Publication statusPublished - 5 Mar 2024


  • climate change
  • linear regression
  • machine learning
  • random forest
  • sustainability

ASJC Scopus subject areas

  • Information Systems and Management
  • Artificial Intelligence
  • Control and Optimization
  • Safety, Risk, Reliability and Quality
  • Computer Networks and Communications
  • Computer Science Applications


Dive into the research topics of 'Sustainable climatic metrics determination with ensemble predictive analytics'. Together they form a unique fingerprint.

Cite this