Rank of prediction models fitted with the Open Soil Spectral Library (OSSL).

Rank of prediction models fitted with the Open Soil Spectral Library (OSSL).

<p>Lin’s concordance correlation coefficient (CCC) from 10-fold cross-validation with refitting. Striped bars represent models with a ratio of performance to the interquartile range (RPIQ) < 2.</p>

Saved in:

Bibliographic Details
Main Author:	José L. Safanelli (20552654) (author)
Other Authors:	Tomislav Hengl (623477) (author), Leandro L. Parente (20552657) (author), Robert Minarik (20552660) (author), Dellena E. Bloom (9227405) (author), Katherine Todd-Brown (20552663) (author), Asa Gholizadeh (693351) (author), Wanderson de Sousa Mendes (20552666) (author), Jonathan Sanderman (784692) (author)
Published:	2025
Subjects:	Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Chemical Sciences not elsewhere classified widely used method training machine learning independent model evaluation global good initiative estimating soil properties study also presents centralized open resource representation flag ). soil spectroscopy community affordable soil data performing ml algorithm two spectral regions harmonizing several ssls soil spectroscopy spectral regions soil types opening data discusses several also subject spectral variations open resources open development ssls ). widespread adoption well predicted total sulfur scientific discovery reliable outputs refitting show predictive modeling prediction uncertainty prediction capacity new samples help bridge future development fold cross extractable sodium extractable nutrients exploratory analysis enable hundreds cubist comes conditions represented agricultural monitoring
Tags:	Add Tag No Tags, Be the first to tag this record!

Cannot write session to /tmp/vufind_sessions/sess_jjchcv14vdapnm7g24e5ibg3sp