English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

. Enhancing the spatial resolution of pedological information is a greatchallenge in the field of digital soil mapping (DSM). Several techniqueshave emerged to disaggregate conventional soil maps initially and are available at acoarser spatial resolution than required for solving environmental andagricultural issues. At the regional level, polygon maps represent soilcover as a tessellation of polygons defining soil map units (SMUs), whereeach SMU can include one or several soil type units (STUs) with givenproportions derived from expert knowledge. Such polygon maps can bedisaggregated at a finer spatial resolution by machine-learning algorithms,using the Disaggregation and Harmonisation of Soil Map Units ThroughResampled Classification Trees (DSMART) algorithm. This study aimed tocompare three approaches of the spatial disaggregation of legacy soil maps basedon DSMART decision trees to test the hypothesis that the disaggregation ofsoil landscape distribution rules may improve the accuracy of the resultingsoil maps. Overall, two modified DSMART algorithms (DSMART with extra soilprofiles; DSMART with soil landscape relationships) and the original DSMARTalgorithm were tested. The quality of disaggregated soil maps at a 50 mresolution was assessed over a large study area (6775 km 2 )using an external validation based on 135 independent soil profiles selectedby probability sampling, 755 legacy soil profiles and existing detailed 1:25 000 soil maps. Pairwise comparisons were also performed, using the Shannonentropy measure, to spatially locate the differences between disaggregated maps.The main results show that adding soil landscape relationships to thedisaggregation process enhances the performance of the prediction of soil type distribution. Considering the three most probable STUs and using 135 independent soil profiles, the overall accuracy measures (the percentage ofsoil profiles where predictions meet observations) are 19.8 % for DSMARTwith expert rules against 18.1 % for the original DSMART and 16.9 %for DSMART with extra soil profiles. These measures were almost 2 timeshigher when validated using 3×3 windows. They achieved 28.5 % for DSMARTwith soil landscape relationships and 25.3 % and 21 % for original DSMARTand DSMART with extra soil observations, respectively. In general, addingsoil landscape relationships and extra soil observations constraints allowthe model to predict a specific STU that can occur in specific environmentalconditions. Thus, including global soil landscape expert rules in the DSMARTalgorithm is crucial for obtaining consistent soil maps with a clear internaldisaggregation of SMUs across the landscape.

soil

Comparing three approaches of spatial disaggregation of legacy soil maps based on the Disaggregation and Harmonisation of Soil Map Units Through Resampled Classification Trees (DSMART) algorithm