Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Jun 19;21(12):4208.
doi: 10.3390/s21124208.

Machine Learning Strategy for Soil Nutrients Prediction Using Spectroscopic Method

Janez Trontelj Ml  1 , Olga Chambers  1
Affiliations

Machine Learning Strategy for Soil Nutrients Prediction Using Spectroscopic Method

Janez Trontelj Ml et al. Sensors (Basel). .

Abstract

The research presented in this paper is based on the hypothesis that the machine learning approach improves the accuracy of soil properties prediction. The correlations obtained in this research are important for understanding the overall strategy for soil properties prediction using optical spectroscopy sensors. Several research results have been stated and investigated. A comparison is made between six commonly used techniques: Random Forest, Decision Tree, Naïve Bayes, Support Vector Machine, Least-Square Support Vector Machine and Artificial Neural Network, showing that the best prediction accuracy cannot always be achieved by the most common and complicated method. The influence of the chosen category for nutrient characterization was investigated, indicating better prediction when a multi-component strategy was used. In contrast, the prediction of single-component soil properties was less accurate. In addition, the influence of category levels was not as significant as expected when choosing between 3-level, 5-level or 13-level nutrient characterization for some nutrients, which can be used for a more precise nutrient characterization strategy. A comparative analysis was performed between soil from a local farm with similar texture and soils collected from different locations in Slovenia, which gave a better prediction for a local farm. Finally, the influence of principal component analysis was validated using 5, 10, 20 and 50 first principal components, indicating the better performance of machine learning when using the 50 principal components.

Keywords: machine learning; nutrients prediction; precision farming; soil analysis; soil category; soil spectra.

PubMed Disclaimer

Conflict of interest statement

The author declares no conflict of interest.

Figures

Figure 1
Figure 1
The experimental set-up for spectroscopic data acquisition.
Figure 2
Figure 2
Flow diagram of the Training set class labelling using single-component (left) and multi-component (right) strategy, corresponding Category II.
Figure 3
Figure 3
Comparison of the results corresponding to different machine learning techniques for the Global soil dataset using Category II system for category labelling.
Figure 4
Figure 4
Comparison of the results corresponding to different machine learning techniques for Local soil dataset using Category II system for category labelling.
Figure 5
Figure 5
The precision corresponding to the Global soil dataset when a different amount of the principal components is used.
Figure 5
Figure 5
The precision corresponding to the Global soil dataset when a different amount of the principal components is used.
See this image and copyright information in PMC

References

    1. Adamchuk V., Lund E., Sethuramasamyraja B., Morgan M., Dobermann A., Marx D. Direct measurement of soil chemical properties on-the-go using ion-selective electrodes. Comput. Electron. Agric. 2005;48:272–294. doi: 10.1016/j.compag.2005.05.001. - DOI
    1. Davenport J., Jabro J. Assessment of hand held ion selective electrode technology for direct measurement of soil chemical properties. Commun. Soil Sci. Plant Anal. 2011;32:3077–3085. doi: 10.1081/CSS-120001108. - DOI
    1. Bogrekci I., Lee S. 2005 ASAE Annual International Meeting. American Society of Agricultural and Biological Engineers; St. Joseph, MI, USA: 2005. Design of a Portable Raman Sensor for Phosphorus Sensing in Soils. - DOI
    1. Villas-Boas P.R., Franco M.A., Martin-Neto L., Gollany H.T., Milori D.M.B.P. Applications of laser-induced breakdown spectroscopy for soil characterization, part II: Review of elemental analysis and soil classification. Eur. J. Soil Sci. 2020;71:805–818. doi: 10.1111/ejss.12889. - DOI
    1. Vohland M., Besold J., Hill J., Fründ H.C. Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy. Geoderma. 2011;166:198–205. doi: 10.1016/j.geoderma.2011.08.001. - DOI