scholarly journals Remotely sensed estimation of total iron content in soil with harmonic analysis and BP neural network

Plant Methods ◽  
2021 ◽  
Vol 17 (1) ◽  
Author(s):  
Xueqin Jiang ◽  
Shanjun Luo ◽  
Shenghui Fang ◽  
Bowen Cai ◽  
Qiang Xiong ◽  
...  
Keyword(s):  
Neural Network ◽  
Harmonic Analysis ◽  
Bp Neural Network ◽  
Iron Content ◽  
Regional Scale ◽  
Principal Component ◽  
Total Iron ◽  
Estimation Accuracy ◽  
Good Effect ◽  
Total Iron Content

Abstract Background The estimation of total iron content at the regional scale is of much significance as iron deficiency has become a routine problem for many crops. Methods In this study, a novel method for estimating total iron content in soil (TICS) was proposed using harmonic analysis (HA) and back propagation (BP) neural network model. Several data preprocessing methods of first derivative (FD), wavelet packet transform (WPT), and HA were conducted to improve the correlation between the soil spectra and TICS. The principal component analysis (PCA) was exploited to obtained three kinds of characteristic variables (FD, WPT-FD, and WPT-FD-HA) for TICS estimation. Furthermore, the estimated accuracy of three BP models based on these variables was compared. Results The results showed that the BP models of different soil types based on WPT-FD-HA had better estimation accuracy, with the highest R2 value of 0.95, and the RMSE of 0.68 for the loessial soil. It was proved that the characteristic variable obtained by harmonic decomposition improved the validity of the input variables and the estimation accuracy of the TICS models. Meanwhile, it was identified that the WPT-FD-HA-BP model can not only estimate the total iron content of a single soil type with high accuracy but also demonstrate a good effect on the estimation of TICS of mixed soil. Conclusion The HA method and BP neural network combined with WPT and FD have great potential in TICS estimation under the conditions of single soil and mixed soil. This method can be expected to be applied to the prediction of crop biochemical parameters.

scholarly journals Remotely Sensed Estimation of Total Iron Content in Soil With Harmonic Analysis and BP Neural Network

2021 ◽  
Author(s):  
xueqin jiang ◽  
Shanjun Luo ◽  
Shenghui Fang ◽  
Bowen Cai ◽  
Qiang Xiong ◽  
...  
Keyword(s):  
Neural Network ◽  
Harmonic Analysis ◽  
Bp Neural Network ◽  
Iron Content ◽  
Regional Scale ◽  
Principal Component ◽  
Total Iron ◽  
Estimation Accuracy ◽  
Good Effect ◽  
Total Iron Content

Abstract Background: The estimation of total iron content at the regional scale is much of significance as iron deficiency has become a routine problem for many crops. Methods: In this study, a novel method for estimating total iron content in soil (TICS) was proposed using harmonic analysis (HA) and back propagation (BP) neural network model. Several data preprocessing methods of first derivative (FD), wavelet packet transform (WPT), and HA were conducted to improve the correlation between the soil spectra and TICS. The principal component analysis (PCA) was exploited to obtained three kinds of characteristic variables (FD-PCA, WPT-FD-PCA, and WPT-FD-HA-PCA) for TICS estimation. Furthermore, the estimated accuracy of three BP models based on these variables was compared. Results: The results showed that the BP models of different soil types based on WPT-FD-HA-PCA had better estimation accuracy, with the highest R2 value of 0.95, and the RMSE of 0.68 of the loessial soil. It was proved that the characteristic variable obtained by harmonic decomposition improved the validity of the input variables and the estimation accuracy of the TICS models. Meanwhile, it was identified that the WPT-FD-HA-PCA-BP model can not only estimate the total iron content of a single soil type with high accuracy but also demonstrate a good effect on the estimation of TICS of mixed soil.Conclusion: The HA method and BP neural network combined with WPT and FD have great potential in TICS estimation under the conditions of single soil and mixed soil. This method can be expected to be applied to the prediction of crop biochemical parameters.

Precision Power System Harmonic Analysis Algorithm Based on ABC-BPNN

2013 ◽  
Vol 483 ◽  
pp. 630-634
Author(s):  
Shu Chuan Gan ◽  
Ling Tang ◽  
Li Cao ◽  
Ying Gao Yue
Keyword(s):  
Neural Network ◽  
Power System ◽  
Harmonic Analysis ◽  
Bp Neural Network ◽  
Artificial Bee Colony Algorithm ◽  
Artificial Bee Colony ◽  
Optimal Solution ◽  
Bee Colony ◽  
Network Algorithm ◽  
Neural Network Algorithm

An algorithm of artificial colony algorithm to optimize the BP neural network algorithm was presented and used to analyze the harmonics of power system. The artificial bee colony algorithm global searching ability, convergence speed for the BP neural network algorithm for harmonic analysis is easy to fall into local optimal solution of the disadvantages, and the initial weights of the artificial bee colony algorithm also greatly enhance whole algorithm model generalization capability. This algorithm using MATLAB for Artificial bee colony algorithm and BP neural network algorithm simulation training toolbox found using artificial bee colony algorithm to optimize BP neural network algorithm converges faster results with greater accuracy, with better harmonic analysis results.

Clay mineralogy of parent materials derived from uppermost Cretaceous and Tertiary sedimentary rocks in southern Saskatchewan

1993 ◽  
Vol 73 (4) ◽  
pp. 447-457 ◽  
Author(s):  
W. E. Dubbin ◽  
A. R. Mermut ◽  
H. P. W. Rostad
Keyword(s):  
Organic Carbon ◽  
Iron Content ◽  
Sedimentary Rocks ◽  
Clay Mineralogy ◽  
Total Iron ◽  
Total Iron Content ◽  
Parent Materials ◽  
Surface Areas ◽  
General Chemical ◽  
Detailed Chemical

Soils developed from parent materials derived from uppermost Cretaceous and Tertiary sedimentary rocks have been delineated from those which do not contain any of these younger sediments. The present study was initiated to determine the validity of this delineation. Parent materials from six locations in southwestern Saskatchewan were collected to determine their general chemical and physical properties. Clay fractions from each of these six parent materials were then subjected to detailed chemical and mineralogical analyses. The two parent materials containing the greatest amount of post-Bearpaw bedrock sediments (Jones Creek, Scotsguard) were characterized by substantially more organic carbon and less CaCO3. The presence of coal and the absence of carbonates in local bedrocks were considered to be the source of these deviations. In general, fine clays were comprised of 64–69% smectite, 14–21% illite and 10–13% kaolinite and coarse clay contained 32–39% smectite, 25–34% illite and 11–14% kaolinite. An exception was found in two fine clays which had less smectite but 3–6% vermiculite. Total iron content of the fine clays ranged from 7.16 to 8.11% expressed as Fe2O3. However, only a small fraction of this iron was extractable using the CDB technique. There were no substantial differences in surface areas or CECs of the clay fractions. Despite minor differences in the chemistry and mineralogy of these six parent materials, a separation of the soil associations does not appear to be warranted. Key words: Parent materials, uppermost Cretaceous, Tertiary, bedrock, clay mineralogy

The Research of Railway Passenger Flow Prediction Model Based on BP Neural Network

2012 ◽  
Vol 605-607 ◽  
pp. 2366-2369 ◽  
Author(s):  
Yao Wang ◽  
Dan Zheng ◽  
Shi Min Luo ◽  
Dong Ming Zhan ◽  
Peng Nie
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Forecast Model ◽  
Good Effect ◽  
Passenger Flow ◽  
Model Based ◽  
Flow Prediction ◽  
Transport Organization ◽  
Railway Passenger ◽  
Short Time

Based on analyzing the principle of BP neural network and time sequence characteristics of railway passenger flow, the forecast model of railway short-term passenger flow based on BP neural network was established. This paper mainly researches on fluctuation characteristics and short-time forecast of holiday passenger flow. Through analysis of passenger flow and then be used in passenger flow forecasting in order to guide the transport organization program especially the train plan of extra passenger train. And the result shows the forecast model based on BP neural network has a good effect on railway passenger flow prediction.

Sign in / Sign up

Export Citation Format

Share Document