Articles | Volume 6, issue 1
SOIL, 6, 215–229, 2020
https://doi.org/10.5194/soil-6-215-2020
SOIL, 6, 215–229, 2020
https://doi.org/10.5194/soil-6-215-2020
Original research article
03 Jun 2020
Original research article | 03 Jun 2020

Development of pedotransfer functions for water retention in tropical mountain soil landscapes: spotlight on parameter tuning in machine learning

Anika Gebauer et al.

Related authors

Performance of three machine learning algorithms for predicting soil organic carbon in German agricultural soil
Ali Sakhaee, Anika Gebauer, Mareike Ließ, and Axel Don
SOIL Discuss., https://doi.org/10.5194/soil-2021-107,https://doi.org/10.5194/soil-2021-107, 2021
Revised manuscript under review for SOIL
Short summary

Related subject area

Soil and methods
Estimating soil fungal abundance and diversity at a macroecological scale with deep learning spectrotransfer functions
Yuanyuan Yang, Zefang Shen, Andrew Bissett, and Raphael A. Viscarra Rossel
SOIL, 8, 223–235, https://doi.org/10.5194/soil-8-223-2022,https://doi.org/10.5194/soil-8-223-2022, 2022
Short summary
Thermal signature and quantification of charcoal in soil by differential scanning calorimetry and BPCA markers
Brieuc Hardy, Nils Borchard, and Jens Leifeld
SOIL Discuss., https://doi.org/10.5194/soil-2021-146,https://doi.org/10.5194/soil-2021-146, 2022
Revised manuscript accepted for SOIL
Short summary
An underground, wireless, open-source, low-cost system for monitoring oxygen, temperature, and soil moisture
Elad Levintal, Yonatan Ganot, Gail Taylor, Peter Freer-Smith, Kosana Suvocarev, and Helen E. Dahlke
SOIL, 8, 85–97, https://doi.org/10.5194/soil-8-85-2022,https://doi.org/10.5194/soil-8-85-2022, 2022
Short summary
Performance of three machine learning algorithms for predicting soil organic carbon in German agricultural soil
Ali Sakhaee, Anika Gebauer, Mareike Ließ, and Axel Don
SOIL Discuss., https://doi.org/10.5194/soil-2021-107,https://doi.org/10.5194/soil-2021-107, 2021
Revised manuscript under review for SOIL
Short summary
Estimation of soil properties with mid-infrared soil spectroscopy across yam production landscapes in West Africa
Philipp Baumann, Juhwan Lee, Emmanuel Frossard, Laurie Paule Schönholzer, Lucien Diby, Valérie Kouamé Hgaza, Delwende Innocent Kiba, Andrew Sila, Keith Sheperd, and Johan Six
SOIL, 7, 717–731, https://doi.org/10.5194/soil-7-717-2021,https://doi.org/10.5194/soil-7-717-2021, 2021
Short summary

Cited articles

Ardia, D., Mullen, K., Peterson, B., Ulrich, J., and Boudt, K.: R package “DEoptim”: Global Optimization by Differential Evolution, available at: https://cran.r-project.org/package=DEoptim (last access: 5 July 2019), 2016. 
Arlot, S. and Celisse, A.: A survey of cross-validation procedures for model selection, Stat. Surv., 4, 40–79, https://doi.org/10.1214/09-SS054, 2009. 
Babangida, N. M., Ul Mustafa, M. R., Yusuf, K. W., Isa, M. H., and Baig, I.: Evaluation of low degree polynomial kernel support vector machines for modelling Pore-water pressure responses, Matec. Web Conf., 59, 6 pp., https://doi.org/10.1051/matecconf/20165904003, 2016. 
Barros, A. H. C., Lier, Q. de J. van, Maia, A. de H. N., and Scarpare, F. V.: Pedotransfer functions to estimate water retention parameters of soils in northeastern Brazil, Rev. Bras. Ciência do Solo, 37, 379–391, https://doi.org/10.1590/S0100-06832013000200009, 2013. 
Bendix, J., Gämmerler, S., Reudenbach, C., and Bendix, A.: A case study on rainfall dynamics during El Niño/La Niña 1997/99 in Ecuador and surrounding areas as inferred from GOES-8 and TRMM-PR observations, Erdkunde, 57, 81–93, https://doi.org/10.3112/erdkunde.2003.02.01, 2003. 
Download
Short summary
Pedotransfer functions (PTFs) for soil water retention were developed for two tropical soil landscapes using machine learning. The models corresponding to these PTFs had to be adjusted by tuning their parameters. The standard tuning approach was compared to mathematical optimization. The latter resulted in much better model performance. The PTFs derived are of particular importance for soil process and hydrological models.