rs-local data-mines information from spectral libraries to improve local calibrations

Article


Lobsey, C. R., Viscarra Rossel, R. A., Roudier, P. and Hedley, C. B.. 2017. "rs-local data-mines information from spectral libraries to improve local calibrations." European Journal of Soil Science. 68 (6), pp. 840-852. https://doi.org/10.1111/ejss.12490
Article Title

rs-local data-mines information from spectral libraries to improve local calibrations

ERA Journal ID41617
Article CategoryArticle
AuthorsLobsey, C. R. (Author), Viscarra Rossel, R. A. (Author), Roudier, P. (Author) and Hedley, C. B. (Author)
Journal TitleEuropean Journal of Soil Science
Journal Citation68 (6), pp. 840-852
Number of Pages13
Year2017
Place of PublicationUnited Kingdom
ISSN1351-0754
1365-2389
Digital Object Identifier (DOI)https://doi.org/10.1111/ejss.12490
Web Address (URL)http://onlinelibrary.wiley.com/doi/10.1111/ejss.12490/epdf
Abstract

Diffuse reflectance spectroscopy in the visible–near infrared (vis–NIR) and mid infrared (mid-IR) can be used to estimate soil properties, such as organic carbon (C) content. Compared with conventional laboratory methods, it enables practical and inexpensive measurements at finer spatial and temporal resolutions, which are needed to improve the assessment and management of soil and the environment. Measurements of soil properties with spectra require empirical calibration and soil spectral libraries (SSL) have been developed for this purpose at the regional, continental and global scales. Calibrations derived with these SSLs, however, are often shown to predict poorly at local sites. Here we present a new method, rs-local, that uses a small representative set of site-specific (or ‘local’) data and re-sampling techniques to select a subset of data from a large vis-NIR SSL to improve calibrations at the site. We demonstrate the implementation of rs-local by estimating soil organic C in two fields with different soil types, one in Australia and one in New Zealand. We found that with as few as 12 to 20 site-specific samples and the SSL, training datasets derived with rs-local could accurately predict soil organic C concentrations. Predictions with the rs-local data were comparable to, or better than those made with site-specific calibrations with up to 300 samples. Our method outperformed other published ‘local’ spectroscopic techniques that we tested. Thus, rs-local can effectively improve both the accuracy and financial viability of soil spectroscopy.

Keywordsaccuracy assessment; algorithm; assessment method; calibration; data mining; laboratory method; organic carbon; soil carbon; soil property; spatial resolution; spectral analysis; spectroscopy
ANZSRC Field of Research 2020469999. Other information and computing sciences not elsewhere classified
410699. Soil sciences not elsewhere classified
Public Notes

File reproduced in accordance with the copyright policy of the publisher/author.

Byline AffiliationsNational Centre for Engineering in Agriculture
Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia
Manaaki Whenua – Landcare Research, New Zealand
Institution of OriginUniversity of Southern Queensland
Permalink -

https://research.usq.edu.au/item/q479z/rs-local-data-mines-information-from-spectral-libraries-to-improve-local-calibrations

  • 724
    total views
  • 9
    total downloads
  • 3
    views this month
  • 0
    downloads this month

Export as

Related outputs

Australian rapid-response airborne observation of the Hayabusa2 reentry
Zander, Fabian, Buttsworth, David R., Birch, Byrenn, Noller, Lachlan, Wright, Duncan, James, Christopher M., Thompson, Matthew, Apirana, Steven, Leis, John, Lobsey, Craig and Payne, Allan. 2021. "Australian rapid-response airborne observation of the Hayabusa2 reentry." Journal of Spacecraft and Rockets. 58 (6), pp. 1915-1919. https://doi.org/10.2514/1.A35062
A Bayesian approach toward the use of qualitative information to inform on-farm decision making: The example of soil compaction
Roberton S.D., Lobsey, C.R. and Bennett, J.McL.. 2021. "A Bayesian approach toward the use of qualitative information to inform on-farm decision making: The example of soil compaction ." Geoderma. 382. https://doi.org/10.1016/j.geoderma.2020.114705
Site-specific irrigation using automated control and machine vision for horticulture crops in Queensland and New Zealand
McCarthy, Alison, El-Naggar, Ahmed, Roudier, Pierre and Hedley, Carolyn. 2017. "Site-specific irrigation using automated control and machine vision for horticulture crops in Queensland and New Zealand." 18th Australian Agronomy Conference 2017. Ballarat, Victoria 24 - 28 Sep 2017 Australia.
Assessing the Sensitivity of Site-Specific Lime and Gypsum Recommendations to Soil Sampling Techniques and Spatial Density of Data Collection in Australian Agriculture: A Pedometric Approach
Roberton, Stirling, Bennett, John McL., Lobsey, Craig R. and Bishop, Thomas F. A.. 2020. "Assessing the Sensitivity of Site-Specific Lime and Gypsum Recommendations to Soil Sampling Techniques and Spatial Density of Data Collection in Australian Agriculture: A Pedometric Approach ." Agronomy. 10 (11), pp. 1-18. https://doi.org/10.3390/agronomy10111676
Machine vision for camera-based horticulture crop growth monitoring
McCarthy, Alison, Hedley, Carolyn and El-Naggar, Ahmed. 2017. "Machine vision for camera-based horticulture crop growth monitoring." International Tri-Conference for Precision Agriculture in 2017 (PA17)/7th Asian-Australasian Conference on Precision Agriculture. Hamilton, New Zealand 16 - 18 Oct 2017 New Zealand. https://doi.org/10.5281/zenodo.893702
Scoping review of proximal soil sensors for grain growing
Viscarra Rossel, Raphael A. and Lobsey, Craig. 2016. Scoping review of proximal soil sensors for grain growing. Canberra, Australia. CSIRO Publishing. https://doi.org/10.4225/08/5953fcda5ab78
Novel soil profile sensing to monitor organic C stocks and condition
Viscarra Rossel, Raphael A., Lobsey, Craig R., Sharman, Chris, Flick, Paul and McLachlan, Gordon. 2017. "Novel soil profile sensing to monitor organic C stocks and condition." Environmental Science and Technology. 51 (10), pp. 5630-5641. https://doi.org/10.1021/acs.est.7b00889
Evaluation of two methods to eliminate the effect of water from soil vis–NIR spectra for predictions of organic carbon
Roudier, P., Hedley, C.B., Lobsey, C .R., Viscarra Rossel, R. A. and Leroux, C.. 2017. "Evaluation of two methods to eliminate the effect of water from soil vis–NIR spectra for predictions of organic carbon." Geoderma. 296, pp. 98-107. https://doi.org/10.1016/j.geoderma.2017.02.014
Water: advanced irrigation technologies
Hedley, C. B., Knox, J. W., Raine, S. R. and Smith, R.. 2014. "Water: advanced irrigation technologies." van Alfen, Neal K. (ed.) Encyclopedia of agriculture and food systems. United States. Elsevier. pp. 378-406
Proximal soil sensing. An effective approach for soil measurements in space and time
Viscarra Rossel, R. A., McKenzie, N. J., Adamchuk, V. I., Sudduth, K. A. and Lobsey, C.. 2011. "Proximal soil sensing. An effective approach for soil measurements in space and time." Advances in Agronomy. 113, pp. 237-282. https://doi.org/10.1016/B978-0-12-386473-4.00010-5
Baseline estimates of soil organic carbon by proximal sensing: comparing design-based, model-assisted and model-based inference
Viscarra Rossel, R. A., Brus, D. J., Lobsey, C., Shi, Z. and McLachlan, G.. 2016. "Baseline estimates of soil organic carbon by proximal sensing: comparing design-based, model-assisted and model-based inference." Geoderma. 265, pp. 152-163. https://doi.org/10.1016/j.geoderma.2015.11.016
Sensing of soil bulk density for more accurate carbon accounting
Lobsey, C. R. and Viscarra Rossel, R. A.. 2016. "Sensing of soil bulk density for more accurate carbon accounting." European Journal of Soil Science. 67 (4), pp. 504-513. https://doi.org/10.1111/ejss.12355
Soil organic carbon dust emission: an omitted global source of atmospheric CO2
Chappell, Adrian, Webb, Nicholas P., Butler, Harry J., Strong, Craig L., McTainsh, Grant H., Leys, John F. and Viscarra Rossel, Raphael A.. 2013. "Soil organic carbon dust emission: an omitted global source of atmospheric CO2." Global Change Biology. 19 (10), pp. 3238-3244. https://doi.org/10.1111/gcb.12305