Prediction of Soil Moisture Content Based on Improved BP Neural Network

He, Shulin; Liu, Yong; Sun, Hong‐Bo; Zheng, Kaiwen; Zhang, Yandi

doi:10.1145/3469213.3470223

Cited by 3 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A BP neural network is a multilayer feed-forward neural network trained using the error back-propagation algorithm. It is one of the most widely used neural network models and can learn the rules governing the relationship between objects through training 22,23,24 . It consists of neurons and contains input, hidden, and output layers, where the hidden layer reflects the mapping relationship between the input layer and the output layer.…”

Section: Bp Neural Network Modelmentioning

confidence: 99%

Displacement prediction of fine-grained tailings ponds based on WOA-BP neural network

Liu,

Wang,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

Tailing reservoir is an important auxiliary facility of mine and a dangerous source of man-made debris flow with high potential energy. China’s tailings ponds are shifting toward fine-grained high dams. Accordingly, displacement is one of the key factors affecting pond stability, and it is important to understand the displacement trend of the tailings pond to ensure its safe operation. Accordingly, this paper adopts the whale algorithm to optimize the back propagation(BP) neural network and establishes the WOA-BP neural network nonlinear prediction model to avoid the error generated by the model experiment due to the scaling effect. The infiltration line and displacement data of a tailings pond in Sichuan Province in the past two years are collected consecutively to form a learning sample, which is then used for training to predict the displacement of the tailings pond through the WOA-BP neural network model. Thereafter, these prediction results are compared with the actual monitoring values as well as the BP neural network model prediction values. The results revealed that the relative error of the WOA-BP neural network model prediction results was approximately 4.5%, and the Pearson correlation coefficients were all above 0.998. Compared with the traditional BP neural network model, the optimization model has a stronger search capability, wider application range, higher prediction accuracy, a more global optimal solution, and better response. The nonlinear fuzzy mapping provides new insights into tailings pond displacement and safety prediction.

show abstract

Section: Bp Neural Network Modelmentioning

confidence: 99%

Displacement prediction of fine-grained tailings ponds based on WOA-BP neural network

Liu,

Wang,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Prediction of cooling effect of constant temperature community bin based on BP neural network

Zhu

et al. 2023

Int J Biometeorol

View full text Add to dashboard Cite

Gap-filling greenhouse gas fluxes for the closed chamber method at paddy fields using machine learning techniques

PHUNGERN,

GOTO,

DING

et al. 2023

J. Agric. Meteorol.

View full text Add to dashboard Cite

Measurements of greenhouse gas (GHG) emissions from paddy fields can often include flux measurement errors due to either instrument errors or unfavorable weather. Therefore, data post-processing, including the gap-filling process, is required to improve data quality and quantify the GHG flux budget. This study applied machine learning (ML) techniques with polynomial and multivariate polynomial regression models for gap-filling methane (CH 4 ) and carbon dioxide (CO 2 ) fluxes from closed chamber (CC) method measurements and compared results with mean diurnal variation (MDV) and look-up table (LUT) techniques. The most influential factors affecting methane emissions in the paddy field were used for input variables in the models: air temperature, soil temperature, soil redox potential, soil water content, solar radiation, and days after transplanting. The models' performances were compared using mean absolute error (MAE) and root mean square error (RMSE). The results showed that MAE and RMSE for gap-filling CH 4 fluxes were 1.299-2.984 and 2.499-4.981 mg CH 4 m -2 h -1 , respectively. Also, the multivariate polynomial regression models performed better for gap-filling CH 4 fluxes (RMSE = 2.499 mg CH 4 m -2 h -1 ) than the polynomial regression models, MDV (RMSE = 3.210 mg CH 4 m -2 h -1 ), and LUT (RMSE = 3.339 mg CH 4 m -2 h -1 ) techniques. The MAE and RMSE for gap-filling CO 2 fluxes were 0.282-0.949 and 0.435-1.078 g CO 2 m -2 h -1 , respectively. The ML techniques with polynomial regression using solar radiation (RMSE = 0.435 g CO 2 m -2 h -1 ) and multivariate models (RMSE = 0.445 g CO 2 m -2 h -1 ) perform better on gap-filling CO 2 fluxes than MDV (RMSE = 0.544 g CO 2 m -2 h -1 ), and LUT (RMSE = 0.553 g CO 2 m-2 h -1 ) techniques. The gap-filling using the multivariate polynomial regression models used in this study improved the reliability of the diurnal variation in GHG fluxes. Therefore, ML techniques could be a proper alternative for gap-filling GHG fluxes.

show abstract

Prediction of Soil Moisture Content Based on Improved BP Neural Network

Cited by 3 publications

References 1 publication

Displacement prediction of fine-grained tailings ponds based on WOA-BP neural network

Displacement prediction of fine-grained tailings ponds based on WOA-BP neural network

Prediction of cooling effect of constant temperature community bin based on BP neural network

Gap-filling greenhouse gas fluxes for the closed chamber method at paddy fields using machine learning techniques

Contact Info

Product

Resources

About