Multi-scale emission source inversion method based on three-dimensional UNet structure

By constructing a multi-scale emission source inversion method with a three-dimensional UNet structure, and combining ensemble Kalman filtering and deep learning, the problems of high computational cost and insufficient feature extraction of EnKF are solved, achieving efficient and accurate emission source inversion and improving the accuracy of atmospheric pollutant forecasting.

CN121706620BActive Publication Date: 2026-06-12NANJING UNIV OF INFORMATION SCI & TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
NANJING UNIV OF INFORMATION SCI & TECH
Filing Date
2026-02-13
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

Existing EnKF methods are computationally expensive and difficult to deploy in business applications. Deep learning models do not fully extract features and do not make sufficient use of multi-scale information in emission source inversion, resulting in insufficient accuracy in air pollutant forecasts.

Method used

A multi-scale emission source inversion method based on a three-dimensional UNet structure is adopted. By constructing a three-dimensional spatial multi-scale feature fusion UNet model and combining it with an ensemble Kalman filter assimilation system, emission source inversion is performed quickly and with high accuracy using PM2.5 observation data and concentration forecast background field. A multi-scale feature fusion module is constructed and a multi-scale composite loss function is introduced to optimize the model training process.

Benefits of technology

It achieves emission source inversion with high computational efficiency and excellent inversion accuracy, can capture the multi-scale spatial structure of pollutants, improves the accuracy of pollutant numerical forecasting, reduces computational resource consumption, and is applicable to emission source inversion of various air pollutants.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121706620B_ABST
    Figure CN121706620B_ABST
Patent Text Reader

Abstract

The application discloses a multi-scale emission source inversion method based on a three-dimensional UNet structure and belongs to the technical field of pollutant emission source inversion, and comprises the following steps: optimizing an emission source by using EnKF assimilation observation data to generate sample labels; constructing input samples containing a PM2.5 concentration prediction background field and PM2.5 observation data; constructing a three-dimensional space multi-scale feature fusion UNet model and training the model by using the sample labels and the input samples; the model captures the spatial distribution characteristics of pollutants through a three-dimensional convolution structure, extracts and fuses local to global features in parallel through a multi-scale feature fusion module, and adopts a multi-scale composite loss function to guide the training; and the trained model can be applied to realize fast and high-precision PM2.5 emission field inversion. It can be seen that the application realizes efficient and accurate emission source inversion by using a deep learning method, and provides an effective technical means for improving the accuracy of pollutant numerical prediction.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Method and device for estimating PM2.5 concentration in three-dimensional space based on improved UNet

    CN119418229A

  • Navigation industry carbon emission prediction method based on fusion of multi-scale feature extraction and time sequence dependence analysis

    CN120725212A