Soil Moisture Retrieval Using Microwave Remote Sensing Data and a Deep Belief Network in the Naqu Region of the Tibetan Plateau

Soil moisture plays an important role in the land surface model. In this paper, a method of using VV polarization Sentinel-1 SAR and Landsat optical data to retrieve soil moisture data was proposed by combining the water cloud model (WCM) and the deep belief network (DBN). Since the simple combinati...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhihui Yang, Jun Zhao, Jialiang Liu, Yuanyuan Wen, Yanqiang Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep belief network water cloud model soil moisture Sentinel-1 Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/bf9d0c331ef5403db51de6dedb27aa71
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bf9d0c331ef5403db51de6dedb27aa71
record_format	dspace
spelling	oai:doaj.org-article:bf9d0c331ef5403db51de6dedb27aa712021-11-25T19:02:50ZSoil Moisture Retrieval Using Microwave Remote Sensing Data and a Deep Belief Network in the Naqu Region of the Tibetan Plateau10.3390/su1322126352071-1050https://doaj.org/article/bf9d0c331ef5403db51de6dedb27aa712021-11-01T00:00:00Zhttps://www.mdpi.com/2071-1050/13/22/12635https://doaj.org/toc/2071-1050Soil moisture plays an important role in the land surface model. In this paper, a method of using VV polarization Sentinel-1 SAR and Landsat optical data to retrieve soil moisture data was proposed by combining the water cloud model (WCM) and the deep belief network (DBN). Since the simple combination of training data in the neural network cannot effectively improve the accuracy of the soil moisture inversion results, a WCM physical model was used to eliminate the effect of vegetation cover on the ground backscatter, in order to obtain the bare soil backscatter coefficient. This improved the correlation of ground soil backscatter characteristics with soil moisture. A DBN soil moisture inversion model based on the bare soil backscatter coefficients as the foundation training data combined with radar incidence angle and terrain factors obtained good inversion results. Studies in the Naqu area of the Tibetan Plateau showed that vegetation cover had a significant effect on the soil moisture, and the goodness of fit (R<sup>2</sup>) between the backscatter coefficient and soil moisture before and after the elimination of vegetation cover was 0.38 and 0.50, respectively. The correlation between the backscatter coefficient and the soil moisture was improved after eliminating the vegetation cover. The inversion results of the DBN soil moisture model were further improved through iterative parameters. The model prediction reached its highest level of accuracy when the restricted Boltzmann machine (RBM) was set to seven layers, the bias and R were 0.007 and 0.88, respectively. Ten-fold cross-validation showed that the DBN soil moisture model performed stably with different data. The prediction was further improved when the bare soil backscatter coefficient was used as the training data. The mean values of the root mean square error (RMSE), the inequality coefficient (TIC), and the mean absolute percent error (MAPE) were 0.023, 0.09, and 11.13, respectively.Zhihui YangJun ZhaoJialiang LiuYuanyuan WenYanqiang WangMDPI AGarticledeep belief networkwater cloud modelsoil moistureSentinel-1Environmental effects of industries and plantsTD194-195Renewable energy sourcesTJ807-830Environmental sciencesGE1-350ENSustainability, Vol 13, Iss 12635, p 12635 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep belief network water cloud model soil moisture Sentinel-1 Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
spellingShingle	deep belief network water cloud model soil moisture Sentinel-1 Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350 Zhihui Yang Jun Zhao Jialiang Liu Yuanyuan Wen Yanqiang Wang Soil Moisture Retrieval Using Microwave Remote Sensing Data and a Deep Belief Network in the Naqu Region of the Tibetan Plateau
description	Soil moisture plays an important role in the land surface model. In this paper, a method of using VV polarization Sentinel-1 SAR and Landsat optical data to retrieve soil moisture data was proposed by combining the water cloud model (WCM) and the deep belief network (DBN). Since the simple combination of training data in the neural network cannot effectively improve the accuracy of the soil moisture inversion results, a WCM physical model was used to eliminate the effect of vegetation cover on the ground backscatter, in order to obtain the bare soil backscatter coefficient. This improved the correlation of ground soil backscatter characteristics with soil moisture. A DBN soil moisture inversion model based on the bare soil backscatter coefficients as the foundation training data combined with radar incidence angle and terrain factors obtained good inversion results. Studies in the Naqu area of the Tibetan Plateau showed that vegetation cover had a significant effect on the soil moisture, and the goodness of fit (R<sup>2</sup>) between the backscatter coefficient and soil moisture before and after the elimination of vegetation cover was 0.38 and 0.50, respectively. The correlation between the backscatter coefficient and the soil moisture was improved after eliminating the vegetation cover. The inversion results of the DBN soil moisture model were further improved through iterative parameters. The model prediction reached its highest level of accuracy when the restricted Boltzmann machine (RBM) was set to seven layers, the bias and R were 0.007 and 0.88, respectively. Ten-fold cross-validation showed that the DBN soil moisture model performed stably with different data. The prediction was further improved when the bare soil backscatter coefficient was used as the training data. The mean values of the root mean square error (RMSE), the inequality coefficient (TIC), and the mean absolute percent error (MAPE) were 0.023, 0.09, and 11.13, respectively.
format	article
author	Zhihui Yang Jun Zhao Jialiang Liu Yuanyuan Wen Yanqiang Wang
author_facet	Zhihui Yang Jun Zhao Jialiang Liu Yuanyuan Wen Yanqiang Wang
author_sort	Zhihui Yang
title	Soil Moisture Retrieval Using Microwave Remote Sensing Data and a Deep Belief Network in the Naqu Region of the Tibetan Plateau
title_short	Soil Moisture Retrieval Using Microwave Remote Sensing Data and a Deep Belief Network in the Naqu Region of the Tibetan Plateau
title_full	Soil Moisture Retrieval Using Microwave Remote Sensing Data and a Deep Belief Network in the Naqu Region of the Tibetan Plateau
title_fullStr	Soil Moisture Retrieval Using Microwave Remote Sensing Data and a Deep Belief Network in the Naqu Region of the Tibetan Plateau
title_full_unstemmed	Soil Moisture Retrieval Using Microwave Remote Sensing Data and a Deep Belief Network in the Naqu Region of the Tibetan Plateau
title_sort	soil moisture retrieval using microwave remote sensing data and a deep belief network in the naqu region of the tibetan plateau
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/bf9d0c331ef5403db51de6dedb27aa71
work_keys_str_mv	AT zhihuiyang soilmoistureretrievalusingmicrowaveremotesensingdataandadeepbeliefnetworkinthenaquregionofthetibetanplateau AT junzhao soilmoistureretrievalusingmicrowaveremotesensingdataandadeepbeliefnetworkinthenaquregionofthetibetanplateau AT jialiangliu soilmoistureretrievalusingmicrowaveremotesensingdataandadeepbeliefnetworkinthenaquregionofthetibetanplateau AT yuanyuanwen soilmoistureretrievalusingmicrowaveremotesensingdataandadeepbeliefnetworkinthenaquregionofthetibetanplateau AT yanqiangwang soilmoistureretrievalusingmicrowaveremotesensingdataandadeepbeliefnetworkinthenaquregionofthetibetanplateau
_version_	1718410361921601536

Soil Moisture Retrieval Using Microwave Remote Sensing Data and a Deep Belief Network in the Naqu Region of the Tibetan Plateau

Ejemplares similares