Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Explainable ensemble learning framework for predicting industrial and energy sector GHG emissions.

Mantena Sireesha1, Ashutosh Pandey2, Abdul Gaffar Sheik3

  • 1Center for Geospatial and Saline Studies, Sasi Institute of Technology & Engineering, Tadepalligudem, Andhra Pradesh, 534101, India.

Scientific Reports
|June 25, 2026
PubMed
Summary

Related Concept Videos

Global Climate Change01:50

Global Climate Change

Throughout its ~4.5 billion year history, the Earth has experienced periods of warming and cooling. However, the current drastic increase in global temperatures is well outside of the Earth’s cyclic norms, and evidence for human-caused global climate change is compelling. Paleoclimatology, the study of ancient climate conditions, provides ample evidence for human-caused global climate change by comparing recent conditions with those in the past.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Towards decoupling frontend enhancement and backend recognition in monaural robust ASR.

Computer speech & language·2026
Same author

Polyphenols-rich Indian barberry berries extract alleviates inorganic arsenic exposure-induced cognitive impairments and associated gut microflora alterations.

Food research international (Ottawa, Ont.)·2026
Same author

Granitic intrusions enhance strain localization and rapid mantle exhumation along an oceanic detachment fault.

Science advances·2026
Same author

Advances in transfer learning for smart wastewater treatment plants: Learning frameworks and emerging pathways.

Journal of environmental management·2026
Same author

Bridging Text and Speech for Emotion Understanding: An Explainable Multimodal Transformer Fusion Framework with Unified Audio-Text Attribution.

Journal of Intelligence·2025
Same author

Association of Fordyce's Granules with hyperlipidemia: A clinical indicator of lipid profile alterations.

Bioinformation·2025

Advanced ensemble models accurately predict greenhouse gas (GHG) emissions, outperforming traditional methods. Gradient Boosting and XGBoost show superior performance, identifying CO₂ as a major contributor for effective emission control strategies.

Area of Science:

  • Environmental Science
  • Data Science
  • Climate Science

Background:

  • Greenhouse gas (GHG) emission prediction is complex due to nonlinearities and data variability.
  • Traditional models struggle with diverse emission patterns across energy and industrial sectors.

Purpose of the Study:

  • To apply and compare advanced ensemble models for global multi-gas (CO₂, CH₄, N₂O, F-gases) prediction.
  • To forecast future GHG emissions and identify key contributing variables using explainable AI.

Main Methods:

  • Ensemble models: Gradient Boosting (GB), Random Forest (RF), XGBoost, CatBoost, AdaBoost.
  • Explainable AI (XAI) techniques: SHAP, LIME, ICEs, PDPs for transparent prediction.
  • 172-year historical data analysis for industrial and energy sectors.
Keywords:
Explainable artificial intelligenceGlobal scenarioGreenhouse gasMachine learningPrediction

Related Experiment Videos

Main Results:

  • GB and XGBoost models demonstrated superior accuracy (R² ≈ 0.9997) in industrial sectors.
  • Gradient Boosting achieved maximum accuracy (R² = 0.9997) in the energy sector.
  • XAI quantified CO₂'s significant contribution (68.4% energy, 64.2% industrial).

Conclusions:

  • Advanced ensemble models provide accurate GHG emission predictions.
  • XAI techniques effectively reveal key emission drivers like CO₂, CH₄, and F-gases.
  • Findings support data-driven emission control and sustainable management policies.