TY - JOUR

T1 - The Brazilian Soil Spectral Service (BraSpecS)

T2 - A User‐Friendly System for Global Soil Spectra Communication

AU - Demattê, José A.M.

AU - Paiva, Ariane Francine da Silveira

AU - Poppiel, Raul Roberto

AU - Rosin, Nícolas Augusto

AU - Ruiz, Luis Fernando Chimelo

AU - Mello, Fellipe Alcantara de Oliveira

AU - Minasny, Budiman

AU - Grunwald, Sabine

AU - Ge, Yufeng

AU - Dor, Eyal Ben

AU - Gholizadeh, Asa

AU - Gomez, Cecile

AU - Chabrillat, Sabine

AU - Francos, Nicolas

AU - Ayoubi, Shamsollah

AU - Fiantis, Dian

AU - Biney, James Kobina Mensah

AU - Wang, Changkun

AU - Belal, Abdelaziz

AU - Naimi, Salman

AU - Hafshejani, Najmeh Asgari

AU - Bellinaso, Henrique

AU - Moura‐bueno, Jean Michel

AU - Silvero, Nélida E.Q.

N1 - Funding Information: Funding: This research was funded by São Paulo Research Foundation (FAPESP) (grant numbers 2014/22262‐0, 2016/26176‐6, and 2020/04306‐0). Funding Information: Acknowledgments: We are grateful to the Geotechnologies in Soil Science Group (GeoCiS/ESALQ‐ USP; http://esalqgeocis.wixsite.com/english accessed on 2 February 2022) for team support. We are grateful to Sérgio Ricardo Scagnolato, Luciano Brandine de Negreiros and Fábio Chaddad for the site technical support. We specially knowledge all participants that delivered spectra and dataset to make this work possible, in special the ones that can be found in the Brazilian Soil Spectral Library (https://bibliotecaespectral.wixsite.com/english/lista‐de‐cedentes accessed on 2 February 2022; [16]) and the overseas ones whose countries are indicated in the tables and in the site (https://gossats.wixsite.com/home accessed on 2 February 2022). This work was supported by the São Paulo Research Foundation (FAPESP) (grant numbers 2014/22262‐0 2016/26176‐6, and 2020/04306‐0). Funding Information: This research was funded by S?o Paulo Research Foundation (FAPESP) (grant numbers 2014/22262?0, 2016/26176?6, and 2020/04306?0).

PY - 2022/2/5

Y1 - 2022/2/5

N2 - Although many Soil Spectral Libraries (SSLs) have been created globally, these libraries still have not been operationalized for end‐users. To address this limitation, this study created an online Brazilian Soil Spectral Service (BraSpecS). The system was based on the Brazilian Soil Spectral Library (BSSL) with samples collected in the Visible–Near–Short‐wave infrared (vis–NIR–SWIR) and Mid‐infrared (MIR) ranges. The interactive platform allows users to find spectra, act as custo-dians of the data, and estimate several soil properties and classification. The system was tested by 500 Brazilian and 65 international users. Users accessed the platform (besbbr.com.br), uploaded their spectra, and received soil organic carbon (SOC) and clay content prediction results via email. The BraSpecS prediction provided good results for Brazilian data, but performed variably for other countries. Prediction for countries outside of Brazil using local spectra (External Country Soil Spectral Libraries, ExCSSL) mostly showed greater performance than BraSpecS. Clay R 2 ranged from 0.5 (BraSpecS) to 0.8 (ExCSSL) in vis–NIR–SWIR, but BraSpecS MIR models were more accurate in most situations. The development of external models based on the fusion of local samples with BSSL formed the Global Soil Spectral Library (GSSL). The GSSL models improved soil properties prediction for different countries. Nevertheless, the proposed system needs to be continually updated with new spectra so they can be applied broadly. Accordingly, the online system is dynamic, users can contribute their data and the models will adapt to local information. Our community‐driven web platform allows users to predict soil attributes without learning soil spectral modeling, which will invite end‐users to utilize this powerful technique.

AB - Although many Soil Spectral Libraries (SSLs) have been created globally, these libraries still have not been operationalized for end‐users. To address this limitation, this study created an online Brazilian Soil Spectral Service (BraSpecS). The system was based on the Brazilian Soil Spectral Library (BSSL) with samples collected in the Visible–Near–Short‐wave infrared (vis–NIR–SWIR) and Mid‐infrared (MIR) ranges. The interactive platform allows users to find spectra, act as custo-dians of the data, and estimate several soil properties and classification. The system was tested by 500 Brazilian and 65 international users. Users accessed the platform (besbbr.com.br), uploaded their spectra, and received soil organic carbon (SOC) and clay content prediction results via email. The BraSpecS prediction provided good results for Brazilian data, but performed variably for other countries. Prediction for countries outside of Brazil using local spectra (External Country Soil Spectral Libraries, ExCSSL) mostly showed greater performance than BraSpecS. Clay R 2 ranged from 0.5 (BraSpecS) to 0.8 (ExCSSL) in vis–NIR–SWIR, but BraSpecS MIR models were more accurate in most situations. The development of external models based on the fusion of local samples with BSSL formed the Global Soil Spectral Library (GSSL). The GSSL models improved soil properties prediction for different countries. Nevertheless, the proposed system needs to be continually updated with new spectra so they can be applied broadly. Accordingly, the online system is dynamic, users can contribute their data and the models will adapt to local information. Our community‐driven web platform allows users to predict soil attributes without learning soil spectral modeling, which will invite end‐users to utilize this powerful technique.

KW - Community practice

KW - Precision agriculture

KW - Proximal soil sensing

KW - Soil analysis

KW - Soil health monitoring

KW - Soil quality

KW - Soil spectral library

KW - Spectroscopy

UR - http://www.scopus.com/inward/record.url?scp=85124190083&partnerID=8YFLogxK

U2 - 10.3390/rs14030740

DO - 10.3390/rs14030740

M3 - Article

AN - SCOPUS:85124190083

VL - 14

JO - Remote sensing

JF - Remote sensing

SN - 2072-4292

IS - 3

M1 - 740

ER -