PMID- 30641879
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20190128
LR  - 20200225
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 19
IP  - 2
DP  - 2019 Jan 11
TI  - Evaluation of Machine Learning Approaches to Predict Soil Organic Matter and pH 
      Using vis-NIR Spectra.
LID - 10.3390/s19020263 [doi]
LID - 263
AB  - Soil organic matter (SOM) and pH are essential soil fertility indictors of paddy 
      soil in the middle-lower Yangtze Plain. Rapid, non-destructive and accurate 
      determination of SOM and pH is vital to preventing soil degradation caused by 
      inappropriate land management practices. Visible-near infrared (vis-NIR) 
      spectroscopy with multivariate calibration can be used to effectively estimate 
      soil properties. In this study, 523 soil samples were collected from paddy fields 
      in the Yangtze Plain, China. Four machine learning approaches-partial least 
      squares regression (PLSR), least squares-support vector machines (LS-SVM), 
      extreme learning machines (ELM) and the Cubist regression model (Cubist)-were 
      used to compare the prediction accuracy based on vis-NIR full bands and bands 
      reduced using the genetic algorithm (GA). The coefficient of determination (R(2)), 
      root mean square error (RMSE), and ratio of performance to inter-quartile 
      distance (RPIQ) were used to assess the prediction accuracy. The ELM with GA 
      reduced bands was the best model for SOM (SOM: R(2) = 0.81, RMSE = 5.17, RPIQ = 
      2.87) and pH (R(2) = 0.76, RMSE = 0.43, RPIQ = 2.15). The performance of the LS-SVM 
      for pH prediction did not differ significantly between the model with GA (R(2) = 
      0.75, RMSE = 0.44, RPIQ = 2.08) and without GA (R(2) = 0.74, RMSE = 0.45, RPIQ = 
      2.07). Although a slight increase was observed when ELM were used for prediction 
      of SOM and pH using reduced bands (SOM: R(2) = 0.81, RMSE = 5.17, RPIQ = 2.87; pH: 
      R(2) = 0.76, RMSE = 0.43, RPIQ = 2.15) compared with full bands (R(2) = 0.81, RMSE = 
      5.18, RPIQ = 2.83; pH: R(2) = 0.76, RMSE = 0.45, RPIQ = 2.07), the number of 
      wavelengths was greatly reduced (SOM: 201 to 44; pH: 201 to 32). Thus, the ELM 
      coupled with reduced bands by GA is recommended for prediction of properties of 
      paddy soil (SOM and pH) in the middle-lower Yangtze Plain.
FAU - Yang, Meihua
AU  - Yang M
AD  - Institute of Agricultural Remote Sensing and Information Technology Application, 
      College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 
      310058, China. 0015862@zju.edu.cn.
AD  - Department of Environmental Engineering, Yuzhang Normal University, Nanchang 
      330103, China. 0015862@zju.edu.cn.
FAU - Xu, Dongyun
AU  - Xu D
AD  - Institute of Agricultural Remote Sensing and Information Technology Application, 
      College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 
      310058, China. xudongyun@zju.edu.cn.
FAU - Chen, Songchao
AU  - Chen S
AD  - The Institute National de la Recherche Agronomique (INRA), Unite InfoSol, 45075 
      Orleans, France. songchao.chen@inra.fr.
FAU - Li, Hongyi
AU  - Li H
AD  - Department of Land Resource Management, Jiangxi University of Finance and 
      Economics, Nanchang 330013, China. lihongyi1981@zju.edu.cn.
FAU - Shi, Zhou
AU  - Shi Z
AUID- ORCID: 0000-0003-3914-5402
AD  - Institute of Agricultural Remote Sensing and Information Technology Application, 
      College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 
      310058, China. shizhou@zju.edu.cn.
AD  - Key Laboratory of Spectroscopy Sensing, Ministry of Agriculture, Hangzhou 310058, 
      China. shizhou@zju.edu.cn.
LA  - eng
PT  - Journal Article
DEP - 20190111
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
PMC - PMC6359233
OTO - NOTNLM
OT  - machine learning approaches
OT  - pH
OT  - paddy soil
OT  - soil organic matter
OT  - vis-NIR spectra
COIS- The authors declare no conflict of interest.
EDAT- 2019/01/16 06:00
MHDA- 2019/01/16 06:01
PMCR- 2019/01/01
CRDT- 2019/01/16 06:00
PHST- 2018/10/08 00:00 [received]
PHST- 2018/12/24 00:00 [revised]
PHST- 2019/01/07 00:00 [accepted]
PHST- 2019/01/16 06:00 [entrez]
PHST- 2019/01/16 06:00 [pubmed]
PHST- 2019/01/16 06:01 [medline]
PHST- 2019/01/01 00:00 [pmc-release]
AID - s19020263 [pii]
AID - sensors-19-00263 [pii]
AID - 10.3390/s19020263 [doi]
PST - epublish
SO  - Sensors (Basel). 2019 Jan 11;19(2):263. doi: 10.3390/s19020263.