Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement.

Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, a bottleneck to its more widespread adoption is the need for establishing large reference datasets for training machine learning (ML) models, which are c...

Full description

Saved in:
Bibliographic Details
Main Authors: José L Safanelli, Tomislav Hengl, Leandro L Parente, Robert Minarik, Dellena E Bloom, Katherine Todd-Brown, Asa Gholizadeh, Wanderson de Sousa Mendes, Jonathan Sanderman
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0296545
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832540225741520896
author José L Safanelli
Tomislav Hengl
Leandro L Parente
Robert Minarik
Dellena E Bloom
Katherine Todd-Brown
Asa Gholizadeh
Wanderson de Sousa Mendes
Jonathan Sanderman
author_facet José L Safanelli
Tomislav Hengl
Leandro L Parente
Robert Minarik
Dellena E Bloom
Katherine Todd-Brown
Asa Gholizadeh
Wanderson de Sousa Mendes
Jonathan Sanderman
author_sort José L Safanelli
collection DOAJ
description Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, a bottleneck to its more widespread adoption is the need for establishing large reference datasets for training machine learning (ML) models, which are called soil spectral libraries (SSLs). Similarly, the prediction capacity of new samples is also subject to the number and diversity of soil types and conditions represented in the SSLs. To help bridge this gap and enable hundreds of stakeholders to collect more affordable soil data by leveraging a centralized open resource, the Soil Spectroscopy for Global Good initiative has created the Open Soil Spectral Library (OSSL). In this paper, we describe the procedures for collecting and harmonizing several SSLs that are incorporated into the OSSL, followed by exploratory analysis and predictive modeling. The results of 10-fold cross-validation with refitting show that, in general, mid-infrared (MIR)-based models are significantly more accurate than visible and near-infrared (VisNIR) or near-infrared (NIR) models. From independent model evaluation, we found that Cubist comes out as the best-performing ML algorithm for the calibration and delivery of reliable outputs (prediction uncertainty and representation flag). Although many soil properties are well predicted, total sulfur, extractable sodium, and electrical conductivity performed poorly in all spectral regions, with some other extractable nutrients and physical soil properties also performing poorly in one or two spectral regions (VisNIR or NIR). Hence, the use of predictive models based solely on spectral variations has limitations. This study also presents and discusses several other open resources that were developed from the OSSL, aspects of opening data, current limitations, and future development. With this genuinely open science project, we hope that OSSL becomes a driver of the soil spectroscopy community to accelerate the pace of scientific discovery and innovation.
format Article
id doaj-art-03ef60f587fb431491ba70c80c27eaff
institution Kabale University
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-03ef60f587fb431491ba70c80c27eaff2025-02-05T05:31:32ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e029654510.1371/journal.pone.0296545Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement.José L SafanelliTomislav HenglLeandro L ParenteRobert MinarikDellena E BloomKatherine Todd-BrownAsa GholizadehWanderson de Sousa MendesJonathan SandermanSoil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, a bottleneck to its more widespread adoption is the need for establishing large reference datasets for training machine learning (ML) models, which are called soil spectral libraries (SSLs). Similarly, the prediction capacity of new samples is also subject to the number and diversity of soil types and conditions represented in the SSLs. To help bridge this gap and enable hundreds of stakeholders to collect more affordable soil data by leveraging a centralized open resource, the Soil Spectroscopy for Global Good initiative has created the Open Soil Spectral Library (OSSL). In this paper, we describe the procedures for collecting and harmonizing several SSLs that are incorporated into the OSSL, followed by exploratory analysis and predictive modeling. The results of 10-fold cross-validation with refitting show that, in general, mid-infrared (MIR)-based models are significantly more accurate than visible and near-infrared (VisNIR) or near-infrared (NIR) models. From independent model evaluation, we found that Cubist comes out as the best-performing ML algorithm for the calibration and delivery of reliable outputs (prediction uncertainty and representation flag). Although many soil properties are well predicted, total sulfur, extractable sodium, and electrical conductivity performed poorly in all spectral regions, with some other extractable nutrients and physical soil properties also performing poorly in one or two spectral regions (VisNIR or NIR). Hence, the use of predictive models based solely on spectral variations has limitations. This study also presents and discusses several other open resources that were developed from the OSSL, aspects of opening data, current limitations, and future development. With this genuinely open science project, we hope that OSSL becomes a driver of the soil spectroscopy community to accelerate the pace of scientific discovery and innovation.https://doi.org/10.1371/journal.pone.0296545
spellingShingle José L Safanelli
Tomislav Hengl
Leandro L Parente
Robert Minarik
Dellena E Bloom
Katherine Todd-Brown
Asa Gholizadeh
Wanderson de Sousa Mendes
Jonathan Sanderman
Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement.
PLoS ONE
title Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement.
title_full Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement.
title_fullStr Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement.
title_full_unstemmed Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement.
title_short Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement.
title_sort open soil spectral library ossl building reproducible soil calibration models through open development and community engagement
url https://doi.org/10.1371/journal.pone.0296545
work_keys_str_mv AT joselsafanelli opensoilspectrallibraryosslbuildingreproduciblesoilcalibrationmodelsthroughopendevelopmentandcommunityengagement
AT tomislavhengl opensoilspectrallibraryosslbuildingreproduciblesoilcalibrationmodelsthroughopendevelopmentandcommunityengagement
AT leandrolparente opensoilspectrallibraryosslbuildingreproduciblesoilcalibrationmodelsthroughopendevelopmentandcommunityengagement
AT robertminarik opensoilspectrallibraryosslbuildingreproduciblesoilcalibrationmodelsthroughopendevelopmentandcommunityengagement
AT dellenaebloom opensoilspectrallibraryosslbuildingreproduciblesoilcalibrationmodelsthroughopendevelopmentandcommunityengagement
AT katherinetoddbrown opensoilspectrallibraryosslbuildingreproduciblesoilcalibrationmodelsthroughopendevelopmentandcommunityengagement
AT asagholizadeh opensoilspectrallibraryosslbuildingreproduciblesoilcalibrationmodelsthroughopendevelopmentandcommunityengagement
AT wandersondesousamendes opensoilspectrallibraryosslbuildingreproduciblesoilcalibrationmodelsthroughopendevelopmentandcommunityengagement
AT jonathansanderman opensoilspectrallibraryosslbuildingreproduciblesoilcalibrationmodelsthroughopendevelopmentandcommunityengagement