Numerical simulation method for atmospheric pollutant diffusion based on deep learning
An air pollutant, numerical simulation technology, applied in CAD numerical modeling, data processing applications, climate sustainability, etc., can solve the problem of spatial grid interpolation data smoothness and fitting degree improvement, difficult air pollutant attributes similar Sex and other issues, to achieve the effect of strong generalization
Pending Publication Date: 2022-06-07
太原则成信息技术有限公司
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the current spatial grid interpolation can only consider the spatial autocorrelation factors, and it is difficult to finely consider the similarity of the attributes of atmospheric pollutants that continuously change in time and space. It is limited by various conditions, and the smoothness and fitting of the spatial grid interpolation data degree needs to be further improved
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0018] Example: as figure 1 As shown in the figure, a deep learning-based numerical simulation method for the diffusion of atmospheric pollutants includes: performing data cleaning, selecting N sets of data sets from the monitoring data of all spatial points collected multiple times in a specific area, where N is an integer, and N≥ 10; Randomly assign N sets of data sets into a set of training sets and a set of validation sets; construct a deep neural network; train a deep neural network with cross-validation of the training set and the validation set; use the trained deep neural network to predict all The concentration value of the unknown space point is inserted into the predicted concentration value of all unknown space points in the spatial grid of a specific area to construct a refined and smooth concentration field.
[0019] like figure 2 As shown, for the diffusion concentration point with positional continuity in the concentration diffusion field, the specific method...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a numerical simulation method for atmospheric pollutant diffusion based on deep learning, which comprises the following steps: data cleaning is carried out, and N sets of data sets are selected from monitoring data of all spatial points collected for multiple times in a specific area, N is an integer, and N is greater than or equal to 10; randomly distributing the N sets of data sets into a group of training sets and a group of verification sets; constructing a deep neural network; performing cross validation training on the deep neural network by using the training set and the validation set; and predicting the concentration values of all unknown space points in a specific area by using the trained deep neural network, inserting the predicted concentration values of all unknown space points in the space grid of the specific area, and constructing a refined smooth concentration field. According to the atmospheric pollutant diffusion numerical simulation method based on deep learning, the smoothness and the fitting degree of spatial interpolation data are improved.
Description
technical field [0001] The invention relates to the technical field of atmospheric environment, in particular to a spatial interpolation method constructed based on a deep neural network for numerical simulation of pollutant diffusion in the atmospheric environment. Background technique [0002] Atmospheric pollution is a complex phenomenon. The concentration of air pollutants at different times and places is affected by many factors. The concentrations of air pollutants are different, and the air quality varies greatly. At present, environmental quality monitoring stations monitor atmospheric environmental conditions by monitoring limited discrete spatial point data and processing these monitoring data. The processed results often cannot evaluate the air quality of the monitoring area. Therefore, numerical simulation methods are used to establish spatial grids. , add simulated space points, perform spatial grid interpolation, and perform spatial distribution of air pollutio...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06Q10/04G06Q50/26G06F111/10
CPCG06F30/27G06Q10/04G06Q50/26G06F2111/10Y02A90/10
Inventor 李鸣野张耀华李小明张畦霖
Owner 太原则成信息技术有限公司