Sediment content in nandong underground river based on levenberg-marquardt algorithm and BP neural network

Penghui Wang, Yanqing Li, Funing Lan, Yi Zhao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Nandong Underground River is a large-scale karst subterranean streamin southwest China. The basin witnessed a high degree of rocky desertification, a wide distribution area and serious soil erosion. The underground river is the carrier of water and soil loss in the area. The sediment concentration of the underground river can directly reflect the soil erosion in the river basin. In this paper, rainfall is taken as a given input variable, and the suspended sediment content is taken as the unknown variable to be predicted. Based on the BP neural network improved by the Levenberg-Marquardt algorithm, the suspended sediment concentration in Nandong underground river basin is modeled and predicted.Through repeatedly adjustment and optimization, three-layer BP neural network structure model with 4 (input layer dimension) -10 (number of hidden layer node) -1 (single output variable) is determined and simulated verification iss conducted. The simulation results show that the model can predict the sediment concentration with high accuracy. By analyzing the sample of error value, it is found that most of them are samples whose rainfall value is zero. It is deduced that the asymmetry of input and output is the reason of system error. The sediment concentration model proposed by this paper is a simple and effective method to quantitatively study the erosion and sediment yield. It can provide data reference for the local rocky desertification control project.

Original languageEnglish
Title of host publicationProceedings of the 5th Academic Conference of Geology Resource Management and Sustainable Development
EditorsHenry Zhang, Chang Bo Cheng
PublisherAussino Academic Publishing House (AAPH)
Pages554-562
Number of pages9
Volume2017-December
ISBN (Electronic)9781921712647
Publication statusPublished - Jan 1 2017
Externally publishedYes
Event5th Academic Conference of Geology Resource Management and Sustainable Development - Beijing City, China
Duration: Dec 17 2017Dec 18 2017

Other

Other5th Academic Conference of Geology Resource Management and Sustainable Development
CountryChina
CityBeijing City
Period12/17/1712/18/17

Fingerprint

Sediments
Rivers
Neural networks
suspended sediment
soil erosion
Erosion
river basin
Suspended sediments
river
sediment
rainfall
Soils
Catchments
Rain
desertification
sediment yield
karst
asymmetry
erosion
Model structures

Keywords

  • Levenberg-Marquardt algorithm
  • Neural network
  • Prediction
  • Rainfall
  • Rocky desertification
  • Suspended sediment content
  • Underground River

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology
  • Geology

Cite this

Wang, P., Li, Y., Lan, F., & Zhao, Y. (2017). Sediment content in nandong underground river based on levenberg-marquardt algorithm and BP neural network. In H. Zhang, & C. B. Cheng (Eds.), Proceedings of the 5th Academic Conference of Geology Resource Management and Sustainable Development (Vol. 2017-December, pp. 554-562). Aussino Academic Publishing House (AAPH).

Sediment content in nandong underground river based on levenberg-marquardt algorithm and BP neural network. / Wang, Penghui; Li, Yanqing; Lan, Funing; Zhao, Yi.

Proceedings of the 5th Academic Conference of Geology Resource Management and Sustainable Development. ed. / Henry Zhang; Chang Bo Cheng. Vol. 2017-December Aussino Academic Publishing House (AAPH), 2017. p. 554-562.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, P, Li, Y, Lan, F & Zhao, Y 2017, Sediment content in nandong underground river based on levenberg-marquardt algorithm and BP neural network. in H Zhang & CB Cheng (eds), Proceedings of the 5th Academic Conference of Geology Resource Management and Sustainable Development. vol. 2017-December, Aussino Academic Publishing House (AAPH), pp. 554-562, 5th Academic Conference of Geology Resource Management and Sustainable Development, Beijing City, China, 12/17/17.
Wang P, Li Y, Lan F, Zhao Y. Sediment content in nandong underground river based on levenberg-marquardt algorithm and BP neural network. In Zhang H, Cheng CB, editors, Proceedings of the 5th Academic Conference of Geology Resource Management and Sustainable Development. Vol. 2017-December. Aussino Academic Publishing House (AAPH). 2017. p. 554-562
Wang, Penghui ; Li, Yanqing ; Lan, Funing ; Zhao, Yi. / Sediment content in nandong underground river based on levenberg-marquardt algorithm and BP neural network. Proceedings of the 5th Academic Conference of Geology Resource Management and Sustainable Development. editor / Henry Zhang ; Chang Bo Cheng. Vol. 2017-December Aussino Academic Publishing House (AAPH), 2017. pp. 554-562
@inproceedings{cdbe7ecf30c94eceac8efb73c53ac22e,
title = "Sediment content in nandong underground river based on levenberg-marquardt algorithm and BP neural network",
abstract = "Nandong Underground River is a large-scale karst subterranean streamin southwest China. The basin witnessed a high degree of rocky desertification, a wide distribution area and serious soil erosion. The underground river is the carrier of water and soil loss in the area. The sediment concentration of the underground river can directly reflect the soil erosion in the river basin. In this paper, rainfall is taken as a given input variable, and the suspended sediment content is taken as the unknown variable to be predicted. Based on the BP neural network improved by the Levenberg-Marquardt algorithm, the suspended sediment concentration in Nandong underground river basin is modeled and predicted.Through repeatedly adjustment and optimization, three-layer BP neural network structure model with 4 (input layer dimension) -10 (number of hidden layer node) -1 (single output variable) is determined and simulated verification iss conducted. The simulation results show that the model can predict the sediment concentration with high accuracy. By analyzing the sample of error value, it is found that most of them are samples whose rainfall value is zero. It is deduced that the asymmetry of input and output is the reason of system error. The sediment concentration model proposed by this paper is a simple and effective method to quantitatively study the erosion and sediment yield. It can provide data reference for the local rocky desertification control project.",
keywords = "Levenberg-Marquardt algorithm, Neural network, Prediction, Rainfall, Rocky desertification, Suspended sediment content, Underground River",
author = "Penghui Wang and Yanqing Li and Funing Lan and Yi Zhao",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "2017-December",
pages = "554--562",
editor = "Henry Zhang and Cheng, {Chang Bo}",
booktitle = "Proceedings of the 5th Academic Conference of Geology Resource Management and Sustainable Development",
publisher = "Aussino Academic Publishing House (AAPH)",

}

TY - GEN

T1 - Sediment content in nandong underground river based on levenberg-marquardt algorithm and BP neural network

AU - Wang, Penghui

AU - Li, Yanqing

AU - Lan, Funing

AU - Zhao, Yi

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Nandong Underground River is a large-scale karst subterranean streamin southwest China. The basin witnessed a high degree of rocky desertification, a wide distribution area and serious soil erosion. The underground river is the carrier of water and soil loss in the area. The sediment concentration of the underground river can directly reflect the soil erosion in the river basin. In this paper, rainfall is taken as a given input variable, and the suspended sediment content is taken as the unknown variable to be predicted. Based on the BP neural network improved by the Levenberg-Marquardt algorithm, the suspended sediment concentration in Nandong underground river basin is modeled and predicted.Through repeatedly adjustment and optimization, three-layer BP neural network structure model with 4 (input layer dimension) -10 (number of hidden layer node) -1 (single output variable) is determined and simulated verification iss conducted. The simulation results show that the model can predict the sediment concentration with high accuracy. By analyzing the sample of error value, it is found that most of them are samples whose rainfall value is zero. It is deduced that the asymmetry of input and output is the reason of system error. The sediment concentration model proposed by this paper is a simple and effective method to quantitatively study the erosion and sediment yield. It can provide data reference for the local rocky desertification control project.

AB - Nandong Underground River is a large-scale karst subterranean streamin southwest China. The basin witnessed a high degree of rocky desertification, a wide distribution area and serious soil erosion. The underground river is the carrier of water and soil loss in the area. The sediment concentration of the underground river can directly reflect the soil erosion in the river basin. In this paper, rainfall is taken as a given input variable, and the suspended sediment content is taken as the unknown variable to be predicted. Based on the BP neural network improved by the Levenberg-Marquardt algorithm, the suspended sediment concentration in Nandong underground river basin is modeled and predicted.Through repeatedly adjustment and optimization, three-layer BP neural network structure model with 4 (input layer dimension) -10 (number of hidden layer node) -1 (single output variable) is determined and simulated verification iss conducted. The simulation results show that the model can predict the sediment concentration with high accuracy. By analyzing the sample of error value, it is found that most of them are samples whose rainfall value is zero. It is deduced that the asymmetry of input and output is the reason of system error. The sediment concentration model proposed by this paper is a simple and effective method to quantitatively study the erosion and sediment yield. It can provide data reference for the local rocky desertification control project.

KW - Levenberg-Marquardt algorithm

KW - Neural network

KW - Prediction

KW - Rainfall

KW - Rocky desertification

KW - Suspended sediment content

KW - Underground River

UR - http://www.scopus.com/inward/record.url?scp=85051651854&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051651854&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2017-December

SP - 554

EP - 562

BT - Proceedings of the 5th Academic Conference of Geology Resource Management and Sustainable Development

A2 - Zhang, Henry

A2 - Cheng, Chang Bo

PB - Aussino Academic Publishing House (AAPH)

ER -