A machine learning approach to predicting plant available phosphorus that accounts for soil heterogeneity and regional variability
Journal of Soils and Sediments · 2024-01 · 24 (1) · 390-401
DOI: 10.1007/s11368-023-03648-y ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Soils and Sediments, online erschienen am 20.09.2023. Verfasst von Rebecca L. Hall und 8 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Geological Survey of Ireland.
Abstract (Originalsprache)
Purpose
Mehlich-3 extractable P, Al, Ca, and Fe combined with pH can be used to help explain soil chemical processes which regulate P retention, such as the role of Al, Ca, Fe, and pH levels in P fixation and buffering capacity. However, Mehlich-3 is not always the standard test used in agriculture. The objective of this study is to assess the most reliable conversion of Mehlich-3 Al, Ca, Fe, and P and pH into a commonly used soil P test, Morgan’s P, and specifically to predict values into decision support for fertiliser recommendations.
Methods
A geochemical database of 5631 mineral soil samples which covered the northern area of Ireland was used to model soil test P and P indices using Mehlich-3 data.
Results
A random forest machine learning algorithm produced an R 2 of 0.96 and accurately predicted soil P index from external validation in 90% of samples (with an error range of ± 1 mg L −1 ). The model accuracy was reduced when predicted Morgan’s P concentration was outside of the sampled area.
Conclusions
It is recommended that random forest is used to produce Mehlich-3 conversions, especially when data covers large spatial scales with large heterogeneity in soil types and regional variations. To implement conversion models into P testing regimes, it is recommended that representative soil types/geochemical attributes are present in the dataset. Furthermore, completion of a national scale geochemical survey is needed. This will enable accurate predictions of Morgan’s P concentration for a wider range of soils and geographical scale.
Förderung
- Geological Survey of Ireland
Zitieren
APA
Hall, R. L., Santana, F. B. D., Grunsky, E. C., Browne, M. A., Lowe, V., Fitzsimons, M., Higgins, S., Gallagher, V., & Daly, K. (2024). A machine learning approach to predicting plant available phosphorus that accounts for soil heterogeneity and regional variability. Journal of Soils and Sediments, 24(1), 390-401. https://doi.org/10.1007/s11368-023-03648-y
Vancouver
Hall RL, Santana FBD, Grunsky EC, Browne MA, Lowe V, Fitzsimons M, et al. A machine learning approach to predicting plant available phosphorus that accounts for soil heterogeneity and regional variability. Journal of Soils and Sediments. 2024;24(1):390-401. doi:10.1007/s11368-023-03648-y
BibTeX
@article{Hall2024,
author = {Hall, Rebecca L. and Santana, Felipe Bachion de and Grunsky, Eric C. and Browne, Margaret A. and Lowe, Victoria and Fitzsimons, Mairéad and Higgins, Suzanne and Gallagher, Vincent and Daly, Karen},
title = {A machine learning approach to predicting plant available phosphorus that accounts for soil heterogeneity and regional variability},
journal = {Journal of Soils and Sediments},
year = {2024},
volume = {24},
number = {1},
pages = {390--401},
doi = {10.1007/s11368-023-03648-y}
}
EUVIMED