A dynamic correction method and system based on carbon emission prediction and a storage medium

CN122288093APending Publication Date: 2026-06-26ENERGY RES INST OF JIANGXI ACAD OF SCI +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-20
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing carbon emission prediction models suffer from declining accuracy over time due to fixed parameters that cannot adapt to the time-varying characteristics of data. Furthermore, they lack real-time dynamic correction capabilities and cannot support high-frequency carbon management and trading decisions.

Method used

A dynamic bias threshold is used to trigger the model correction process. By constructing an incremental training dataset, lightweight adaptive feature updates and incremental fine-tuning of model parameters are performed. Features are selected by combining SHAP value and Pearson correlation coefficient to achieve online adaptive correction of the carbon emission prediction model.

Benefits of technology

It achieves real-time accuracy and stability of carbon emission prediction models, quickly adapts to production conditions and weather changes, reduces the lag effect of model corrections, and meets the needs of high-frequency carbon management and trading decisions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122288093A_ABST
    Figure CN122288093A_ABST
Patent Text Reader

Abstract

This invention belongs to the field of carbon emission prediction technology, specifically involving a dynamic correction method, system, and storage medium based on carbon emission prediction. First, a carbon emission prediction model is pre-trained using historical and associated feature data and deployed to online prediction nodes. Then, prediction-measured data pairs are collected, and the real-time prediction relative deviation is calculated by correcting the mean absolute percentage error. A multi-factor dynamic deviation threshold formula with boundary constraints is used to determine whether correction is triggered. After correction is triggered, an incremental training dataset is constructed. Features are jointly filtered using SHAP values ​​and Pearson correlation coefficients to complete lightweight adaptive updates. Then, incremental training with bottom-level freezing and top-level adaptive learning rate fine-tuning yields the corrected model. Finally, the corrected model is generalized and validated. If effective, the online model is updated, and the basic threshold and weight coefficients of the dynamic deviation threshold formula are iterated.
Need to check novelty before this filing date? Find Prior Art