Cargando…

In search of an optimum sampling algorithm for prediction of soil properties from infrared spectra

BACKGROUND: The use of visible-near infrared (vis-NIR) spectroscopy for rapid soil characterisation has gained a lot of interest in recent times. Soil spectra absorbance from the visible-infrared range can be calibrated using regression models to predict a set of soil properties. The accuracy of the...

Descripción completa

Detalles Bibliográficos
Autores principales: Ng, Wartini, Minasny, Budiman, Malone, Brendan, Filippi, Patrick
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6173947/
https://www.ncbi.nlm.nih.gov/pubmed/30310751
http://dx.doi.org/10.7717/peerj.5722
_version_ 1783361219977019392
author Ng, Wartini
Minasny, Budiman
Malone, Brendan
Filippi, Patrick
author_facet Ng, Wartini
Minasny, Budiman
Malone, Brendan
Filippi, Patrick
author_sort Ng, Wartini
collection PubMed
description BACKGROUND: The use of visible-near infrared (vis-NIR) spectroscopy for rapid soil characterisation has gained a lot of interest in recent times. Soil spectra absorbance from the visible-infrared range can be calibrated using regression models to predict a set of soil properties. The accuracy of these regression models relies heavily on the calibration set. The optimum sample size and the overall sample representativeness of the dataset could further improve the model performance. However, there is no guideline on which sampling method should be used under different size of datasets. METHODS: Here, we show different sampling algorithms performed differently under different data size and different regression models (Cubist regression tree and Partial Least Square Regression (PLSR)). We analysed the effect of three sampling algorithms: Kennard-Stone (KS), conditioned Latin Hypercube Sampling (cLHS) and k-means clustering (KM) against random sampling on the prediction of up to five different soil properties (sand, clay, carbon content, cation exchange capacity and pH) on three datasets. These datasets have different coverages: a European continental dataset (LUCAS, n = 5,639), a regional dataset from Australia (Geeves, n = 379), and a local dataset from New South Wales, Australia (Hillston, n = 384). Calibration sample sizes ranging from 50 to 3,000 were derived and tested for the continental dataset; and from 50 to 200 samples for the regional and local datasets. RESULTS: Overall, the PLSR gives a better prediction in comparison to the Cubist model for the prediction of various soil properties. It is also less prone to the choice of sampling algorithm. The KM algorithm is more representative in the larger dataset up to a certain calibration sample size. The KS algorithm appears to be more efficient (as compared to random sampling) in small datasets; however, the prediction performance varied a lot between soil properties. The cLHS sampling algorithm is the most robust sampling method for multiple soil properties regardless of the sample size. DISCUSSION: Our results suggested that the optimum calibration sample size relied on how much generalization the model had to create. The use of the sampling algorithm is beneficial for larger datasets than smaller datasets where only small improvements can be made. KM is suitable for large datasets, KS is efficient in small datasets but results can be variable, while cLHS is less affected by sample size.
format Online
Article
Text
id pubmed-6173947
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-61739472018-10-11 In search of an optimum sampling algorithm for prediction of soil properties from infrared spectra Ng, Wartini Minasny, Budiman Malone, Brendan Filippi, Patrick PeerJ Soil Science BACKGROUND: The use of visible-near infrared (vis-NIR) spectroscopy for rapid soil characterisation has gained a lot of interest in recent times. Soil spectra absorbance from the visible-infrared range can be calibrated using regression models to predict a set of soil properties. The accuracy of these regression models relies heavily on the calibration set. The optimum sample size and the overall sample representativeness of the dataset could further improve the model performance. However, there is no guideline on which sampling method should be used under different size of datasets. METHODS: Here, we show different sampling algorithms performed differently under different data size and different regression models (Cubist regression tree and Partial Least Square Regression (PLSR)). We analysed the effect of three sampling algorithms: Kennard-Stone (KS), conditioned Latin Hypercube Sampling (cLHS) and k-means clustering (KM) against random sampling on the prediction of up to five different soil properties (sand, clay, carbon content, cation exchange capacity and pH) on three datasets. These datasets have different coverages: a European continental dataset (LUCAS, n = 5,639), a regional dataset from Australia (Geeves, n = 379), and a local dataset from New South Wales, Australia (Hillston, n = 384). Calibration sample sizes ranging from 50 to 3,000 were derived and tested for the continental dataset; and from 50 to 200 samples for the regional and local datasets. RESULTS: Overall, the PLSR gives a better prediction in comparison to the Cubist model for the prediction of various soil properties. It is also less prone to the choice of sampling algorithm. The KM algorithm is more representative in the larger dataset up to a certain calibration sample size. The KS algorithm appears to be more efficient (as compared to random sampling) in small datasets; however, the prediction performance varied a lot between soil properties. The cLHS sampling algorithm is the most robust sampling method for multiple soil properties regardless of the sample size. DISCUSSION: Our results suggested that the optimum calibration sample size relied on how much generalization the model had to create. The use of the sampling algorithm is beneficial for larger datasets than smaller datasets where only small improvements can be made. KM is suitable for large datasets, KS is efficient in small datasets but results can be variable, while cLHS is less affected by sample size. PeerJ Inc. 2018-10-03 /pmc/articles/PMC6173947/ /pubmed/30310751 http://dx.doi.org/10.7717/peerj.5722 Text en ©2018 Ng et al. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited.
spellingShingle Soil Science
Ng, Wartini
Minasny, Budiman
Malone, Brendan
Filippi, Patrick
In search of an optimum sampling algorithm for prediction of soil properties from infrared spectra
title In search of an optimum sampling algorithm for prediction of soil properties from infrared spectra
title_full In search of an optimum sampling algorithm for prediction of soil properties from infrared spectra
title_fullStr In search of an optimum sampling algorithm for prediction of soil properties from infrared spectra
title_full_unstemmed In search of an optimum sampling algorithm for prediction of soil properties from infrared spectra
title_short In search of an optimum sampling algorithm for prediction of soil properties from infrared spectra
title_sort in search of an optimum sampling algorithm for prediction of soil properties from infrared spectra
topic Soil Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6173947/
https://www.ncbi.nlm.nih.gov/pubmed/30310751
http://dx.doi.org/10.7717/peerj.5722
work_keys_str_mv AT ngwartini insearchofanoptimumsamplingalgorithmforpredictionofsoilpropertiesfrominfraredspectra
AT minasnybudiman insearchofanoptimumsamplingalgorithmforpredictionofsoilpropertiesfrominfraredspectra
AT malonebrendan insearchofanoptimumsamplingalgorithmforpredictionofsoilpropertiesfrominfraredspectra
AT filippipatrick insearchofanoptimumsamplingalgorithmforpredictionofsoilpropertiesfrominfraredspectra