The atmospheric model of neural networks based on the improved Levenberg-Marquardt algorithm
Traditional atmospheric models are based on the analysis and fitting of various factors influencing the space atmosphere density. Neural network models do not specifically analyze the polynomials of each influencing factor in the atmospheric model, but use large data sets for network construction. T...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2021-08-01
|
| Series: | Open Astronomy |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/astro-2021-0003 |
| _version_ | 1829102236681109504 |
|---|---|
| author | Cui Wenhui Qu Wei Jiang Min Yao Gang |
| author_facet | Cui Wenhui Qu Wei Jiang Min Yao Gang |
| author_sort | Cui Wenhui |
| collection | DOAJ |
| description | Traditional atmospheric models are based on the analysis and fitting of various factors influencing the space atmosphere density. Neural network models do not specifically analyze the polynomials of each influencing factor in the atmospheric model, but use large data sets for network construction. Two traditional atmospheric model algorithms are analyzed, the main factors affecting the atmospheric model are identified, and an atmospheric model based on neural networks containing various influencing factors is proposed. According to the simulation error, the Levenberg-Marquardt algorithm is used to iteratively realize the rapid network weight correction, and the optimal neural network atmospheric model is obtained. The space atmosphere is simulated and calculated with an atmospheric model based on neural networks, and its average error rate is lower than that of traditional atmospheric models such as the DTM2013 model and the MSIS00 model. At the same time, the calculation complexity of the atmospheric model based on the neural networks is significantly simplified than that of the traditional atmospheric model. |
| first_indexed | 2024-12-10T22:56:39Z |
| format | Article |
| id | doaj.art-73725b7e13e84cff8a06a8201f0566ca |
| institution | Directory Open Access Journal |
| issn | 2543-6376 |
| language | English |
| last_indexed | 2024-12-10T22:56:39Z |
| publishDate | 2021-08-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Open Astronomy |
| spelling | doaj.art-73725b7e13e84cff8a06a8201f0566ca2022-12-22T01:30:16ZengDe GruyterOpen Astronomy2543-63762021-08-01301243510.1515/astro-2021-0003The atmospheric model of neural networks based on the improved Levenberg-Marquardt algorithmCui Wenhui0Qu Wei1Jiang Min2Yao Gang3State Key Laboratory of Astronautic Dynamics, Xi’an 710043, China, Tel: +86-18092308590Aerospace Engineering University, Beijing101416, ChinaState Key Laboratory of Astronautic Dynamics, Xi’an710043, ChinaBeijing Institute of Tracking and Telecommunications Technology, Beijing100094, ChinaTraditional atmospheric models are based on the analysis and fitting of various factors influencing the space atmosphere density. Neural network models do not specifically analyze the polynomials of each influencing factor in the atmospheric model, but use large data sets for network construction. Two traditional atmospheric model algorithms are analyzed, the main factors affecting the atmospheric model are identified, and an atmospheric model based on neural networks containing various influencing factors is proposed. According to the simulation error, the Levenberg-Marquardt algorithm is used to iteratively realize the rapid network weight correction, and the optimal neural network atmospheric model is obtained. The space atmosphere is simulated and calculated with an atmospheric model based on neural networks, and its average error rate is lower than that of traditional atmospheric models such as the DTM2013 model and the MSIS00 model. At the same time, the calculation complexity of the atmospheric model based on the neural networks is significantly simplified than that of the traditional atmospheric model.https://doi.org/10.1515/astro-2021-0003improved levenberg-marquardt algorithmneural networksatmospheric model |
| spellingShingle | Cui Wenhui Qu Wei Jiang Min Yao Gang The atmospheric model of neural networks based on the improved Levenberg-Marquardt algorithm Open Astronomy improved levenberg-marquardt algorithm neural networks atmospheric model |
| title | The atmospheric model of neural networks based on the improved Levenberg-Marquardt algorithm |
| title_full | The atmospheric model of neural networks based on the improved Levenberg-Marquardt algorithm |
| title_fullStr | The atmospheric model of neural networks based on the improved Levenberg-Marquardt algorithm |
| title_full_unstemmed | The atmospheric model of neural networks based on the improved Levenberg-Marquardt algorithm |
| title_short | The atmospheric model of neural networks based on the improved Levenberg-Marquardt algorithm |
| title_sort | atmospheric model of neural networks based on the improved levenberg marquardt algorithm |
| topic | improved levenberg-marquardt algorithm neural networks atmospheric model |
| url | https://doi.org/10.1515/astro-2021-0003 |
| work_keys_str_mv | AT cuiwenhui theatmosphericmodelofneuralnetworksbasedontheimprovedlevenbergmarquardtalgorithm AT quwei theatmosphericmodelofneuralnetworksbasedontheimprovedlevenbergmarquardtalgorithm AT jiangmin theatmosphericmodelofneuralnetworksbasedontheimprovedlevenbergmarquardtalgorithm AT yaogang theatmosphericmodelofneuralnetworksbasedontheimprovedlevenbergmarquardtalgorithm AT cuiwenhui atmosphericmodelofneuralnetworksbasedontheimprovedlevenbergmarquardtalgorithm AT quwei atmosphericmodelofneuralnetworksbasedontheimprovedlevenbergmarquardtalgorithm AT jiangmin atmosphericmodelofneuralnetworksbasedontheimprovedlevenbergmarquardtalgorithm AT yaogang atmosphericmodelofneuralnetworksbasedontheimprovedlevenbergmarquardtalgorithm |