Predictive Soil Spectroscopy
Welcome!
Welcome to our training on Predictive Soil Spectroscopy! This material was prepared for an in-person event held in St Louis, MO, at the ACS international meeting 2023, but now it has been online so that anyone can reuse it.
Soil spectroscopy, specifically Diffuse Reflectance Infrared (DRIFT) spectroscopy, is rapidly becoming a routine tool for soil scientists in academia and in industry.
One of the most popular uses of soil spectroscopy is for the rapid and low-cost estimation of a number of key soil properties.
This workshop touch on the basics of soil spectroscopy including project design, considerations for building a spectral library, working with large public spectral libraries and model building, prediction, and interpretability.
Most of the learning will focus on using the freely available R programming language.
This material was prepared with R version 4.3.0 and it is recommended to use RStudio as the graphical user interface.
Prerequisites
This training is mostly focused on the use of tidy programming principles with pipe operators, leveraging the R packages from the tidyverse like dplyr, tidyr, and ggplot2.
For the machine learning framework, we decided to use the MLR3 ecosystem.
Alternatively, we have included a chemometrics chapter where the common tools and algorithms for working with spectral data are introduced. This was possible with the amazing package mdatools.
We do, however, recommend that you keep an eye on this online training material as it keeps evolving in time and new methods may be incorporated.
If you are interested in getting started in R using tidy packages and principles, we strongly recommend vising the R 4 Data Science book page:
- For installing R and RStudio, it is recommended to check the Prerequisites page.
- Learning how to set a basic project on RStudio is neatly described in Workflow: projects.
- We are going to have several demonstrations of data import and wrangling by piped operations, and plot visualizations with ggplot.
Other spectral operations, like importing raw files, preprocessing, compression, and modeling will be done with dedicated libraries, e.g., asdreader, opusreader2, prospectr, resemble, mlr3, and others.
Recommended literature
The fundamentals of infrared spectroscopy are well presented in Johnston & Aochi (2018) and Stenberg & Viscarra-Rossel (2018), while Wadoux et al. (2021) provides a great walk-through of soil spectral inference in R.
Johnston, C. T., & Aochi, Y. O. (2018). Fourier Transform Infrared and Raman Spectroscopy (pp. 269–321). https://doi.org/10.2136/sssabookser5.3.c10
Stenberg, B., Viscarra-Rossel, R. (2010). Diffuse Reflectance Spectroscopy for High-Resolution Soil Sensing. In: Viscarra Rossel, R., McBratney, A., Minasny, B. (eds) Proximal Soil Sensing. Progress in Soil Science. Springer, Dordrecht. https://doi.org/10.1007/978-90-481-8859-8_3
Margenot A.J., Calderón F.J., Goyne K.W., Mukome F.N.D and Parikh S.J. (2017) IR Spectroscopy, Soil Analysis Applications. In: Lindon, J.C., Tranter, G.E., and Koppenaal, D.W. (eds.) The Encyclopedia of Spectroscopy and Spectrometry, 3rd edition vol. 2, pp. 448-454. Oxford: Academic Press. http://dx.doi.org/10.1016/B978-0-12-409547-2.12170-5
Wadoux, A. M. J.-C., Malone, B., Minasny, B., Fajardo, M., & McBratney, A. B. (2021). Soil Spectral Inference with R. In Progress in Soil Science. Springer International Publishing. https://doi.org/10.1007/978-3-030-64896-1
Ng, W., Minasny, B., Jeon, S. H., & McBratney, A. (2022). Mid-infrared spectroscopy for accurate measurement of an extensive set of soil properties for assessing soil functions. Soil Security, 6, 100043. https://doi.org/10.1016/j.soisec.2022.100043
Shepherd, K. D., Ferguson, R., Hoover, D., van Egmond, F., Sanderman, J., & Ge, Y. (2022). A global soil spectral calibration library and estimation service. Soil Security, 7, 100061. https://doi.org/10.1016/j.soisec.2022.100061
Soil Spectroscopy for Global Good. Open Soil Spectral Library. https://soilspectroscopy.github.io/ossl-manual/
Disclaimer
Woodwell Climate Research Center, University of Florida, OpenGeoHub foundation and its suppliers and licensors hereby disclaim all warranties of any kind, express or implied, including, without limitation, the warranties of merchantability, fitness for a particular purpose and non-infringement. Neither Woodwell Climate Research Center, University of Florida, OpenGeoHub foundation nor its suppliers and licensors, makes any warranty that the Website will be error free or that access thereto will be continuous or uninterrupted. You understand that you download from, or otherwise obtain content or services through, the Website at your own discretion and risk.
If you notice an error or outdated information, please submit a correction/pull request or open an issue.
License
This website/book and attached software is free to use, and is licensed under the MIT License. The OSSL training data and models, if not otherwise indicated, are available either under the Creative Commons Attribution 4.0 International CC-BY and/or CC-BY-SA license / Open Data Commons Open Database License (ODbL) v1.0.
Acknowledgments
Soil Spectroscopy for Global Good is organized by Woodwell Climate Research Center, University of Florida, and OpenGeoHub foundation. This project has been funded by the USDA National Institute of Food and Agriculture award #2020-67021-32467.
Citing
José Lucas Safanelli, Robert Minarik, Jonathan Sanderman, Tomislav Hengl. Predictive Soil Spectroscopy. 2023. Available on: https://soilspectroscopy.github.io/soilspec-workshop/.
