View in EDS HTML Full Text PDF Full Text

Using deep neural networks for evaluation of soil quality based on VIS–NIR spectroscopy.

Saved in:
Bibliographic Details
Title: Using deep neural networks for evaluation of soil quality based on VIS–NIR spectroscopy.
Authors: Safaie, Mehdi1 (AUTHOR), Hosseinpour-Zarnaq, Mohammad1 (AUTHOR) hosseinpour.moh1@gmail.com, Omid, Mahmoud1 (AUTHOR) omid@ut.ac.ir, Sarmadian, Fereydoon1 (AUTHOR), Ghasemi-Mobtaker, Hassan1 (AUTHOR)
Source: Earth Science Informatics. Feb2024, Vol. 17 Issue 1, p271-281. 11p.
Subject Terms: *Artificial neural networks, *Convolutional neural networks, *Partial least squares regression, *Soil quality, *Soil texture, *Structural optimization
Abstract: This study is focused on evaluating the potential of deep neural networks for assessing soil properties based on VIS–NIR spectroscopy with spectral wavelength ranges of 350–2500 nm and 10 nm resolution on a global scale. The dataset was provided by the ICRAF-ISRIC soil spectral library and consists of 4438 samples from 58 countries. In This research we used the powerful one-dimensional (1D) convolutional neural network (CNN) models to predict soil organic carbon (OC), pH, calcium carbonate (CaCO3), cation exchange capacity (CEC), effective CEC (ECEC), sum of cations (SC), base saturation (BS), exchangeable acidity (ACe), exchangeable cations (aluminum (Al), calcium (Ca), magnesium (Mg), sodium (Na) and‌ potassium (K)), silt, sand and clay content. Also, traditional regression approaches of spectral data including partial least squares regression (PLSR), multilayer perceptron (MLP) and random forest (RF) with optimum preprocessing of spectral data were also tested and the models' performances were evaluated and compared. The optimum structure of models was determined by testing different components for PLSR, selecting the best number of neurons in the hidden layer, activation functions, and solvers for MLP, and finding the proper number of trees and maximum depth in RF. The CNN-based model estimated the OC, pH, CaCO3, CEC, ECEC, SC, BS, ACe, Al, Ca, Mg, Na, K, silt, sand and clay content with the ratio of percent deviation (RPD) of 2.98, 1.9, 2.48, 2.01, 2.05, 2.39, 1.97, 1.01, 1.59, 2.06, 1.72, 1.69, 1.29, 1.38, 1.8 and 1.97, respectively. We evaluated the performance of CNN-based methods with an effective architecture for soil spectral data analysis. The CNN model outperforms other regression algorithms in terms of accuracy and low predicting errors using non-preprocessed data. However, the use of diverse soil properties for modeling spectral data can provide sufficient information on the advantages and disadvantages of VIS–NIR data in predictions. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 175021553
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Using deep neural networks for evaluation of soil quality based on VIS–NIR spectroscopy.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Safaie%2C+Mehdi%22">Safaie, Mehdi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hosseinpour-Zarnaq%2C+Mohammad%22">Hosseinpour-Zarnaq, Mohammad</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> hosseinpour.moh1@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Omid%2C+Mahmoud%22">Omid, Mahmoud</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> omid@ut.ac.ir</i><br /><searchLink fieldCode="AR" term="%22Sarmadian%2C+Fereydoon%22">Sarmadian, Fereydoon</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ghasemi-Mobtaker%2C+Hassan%22">Ghasemi-Mobtaker, Hassan</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Earth+Science+Informatics%22">Earth Science Informatics</searchLink>. Feb2024, Vol. 17 Issue 1, p271-281. 11p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Partial+least+squares+regression%22">Partial least squares regression</searchLink><br />*<searchLink fieldCode="DE" term="%22Soil+quality%22">Soil quality</searchLink><br />*<searchLink fieldCode="DE" term="%22Soil+texture%22">Soil texture</searchLink><br />*<searchLink fieldCode="DE" term="%22Structural+optimization%22">Structural optimization</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This study is focused on evaluating the potential of deep neural networks for assessing soil properties based on VIS–NIR spectroscopy with spectral wavelength ranges of 350–2500 nm and 10 nm resolution on a global scale. The dataset was provided by the ICRAF-ISRIC soil spectral library and consists of 4438 samples from 58 countries. In This research we used the powerful one-dimensional (1D) convolutional neural network (CNN) models to predict soil organic carbon (OC), pH, calcium carbonate (CaCO3), cation exchange capacity (CEC), effective CEC (ECEC), sum of cations (SC), base saturation (BS), exchangeable acidity (ACe), exchangeable cations (aluminum (Al), calcium (Ca), magnesium (Mg), sodium (Na) and‌ potassium (K)), silt, sand and clay content. Also, traditional regression approaches of spectral data including partial least squares regression (PLSR), multilayer perceptron (MLP) and random forest (RF) with optimum preprocessing of spectral data were also tested and the models' performances were evaluated and compared. The optimum structure of models was determined by testing different components for PLSR, selecting the best number of neurons in the hidden layer, activation functions, and solvers for MLP, and finding the proper number of trees and maximum depth in RF. The CNN-based model estimated the OC, pH, CaCO3, CEC, ECEC, SC, BS, ACe, Al, Ca, Mg, Na, K, silt, sand and clay content with the ratio of percent deviation (RPD) of 2.98, 1.9, 2.48, 2.01, 2.05, 2.39, 1.97, 1.01, 1.59, 2.06, 1.72, 1.69, 1.29, 1.38, 1.8 and 1.97, respectively. We evaluated the performance of CNN-based methods with an effective architecture for soil spectral data analysis. The CNN model outperforms other regression algorithms in terms of accuracy and low predicting errors using non-preprocessed data. However, the use of diverse soil properties for modeling spectral data can provide sufficient information on the advantages and disadvantages of VIS–NIR data in predictions. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=175021553
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s12145-023-01168-4
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 271
    Subjects:
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Partial least squares regression
        Type: general
      – SubjectFull: Soil quality
        Type: general
      – SubjectFull: Soil texture
        Type: general
      – SubjectFull: Structural optimization
        Type: general
    Titles:
      – TitleFull: Using deep neural networks for evaluation of soil quality based on VIS–NIR spectroscopy.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Safaie, Mehdi
      – PersonEntity:
          Name:
            NameFull: Hosseinpour-Zarnaq, Mohammad
      – PersonEntity:
          Name:
            NameFull: Omid, Mahmoud
      – PersonEntity:
          Name:
            NameFull: Sarmadian, Fereydoon
      – PersonEntity:
          Name:
            NameFull: Ghasemi-Mobtaker, Hassan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: Feb2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 18650473
          Numbering:
            – Type: volume
              Value: 17
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Earth Science Informatics
              Type: main
ResultId 1