autoRA: An Algorithm to Automatically Delineate Reference Areas—A Case Study to Map Soil Classes in Bahia, Brazil

The reference area (RA) approach has been frequently used in soil surveying and mapping projects, since it allows for reduced costs. However, a crucial point in using this approach is the choice or delineation of an RA, which can compromise the accuracy of prediction models. In this study, an innova...

Full description

Saved in:
Bibliographic Details
Main Authors: Hugo Rodrigues, Marcos Bacis Ceddia, Gustavo Mattos Vasques, Sabine Grunwald, Ebrahim Babaeian, André Luis Oliveira Villela
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Land
Subjects:
Online Access:https://www.mdpi.com/2073-445X/14/3/604
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850280517712216064
author Hugo Rodrigues
Marcos Bacis Ceddia
Gustavo Mattos Vasques
Sabine Grunwald
Ebrahim Babaeian
André Luis Oliveira Villela
author_facet Hugo Rodrigues
Marcos Bacis Ceddia
Gustavo Mattos Vasques
Sabine Grunwald
Ebrahim Babaeian
André Luis Oliveira Villela
author_sort Hugo Rodrigues
collection DOAJ
description The reference area (RA) approach has been frequently used in soil surveying and mapping projects, since it allows for reduced costs. However, a crucial point in using this approach is the choice or delineation of an RA, which can compromise the accuracy of prediction models. In this study, an innovative algorithm that delineates RA (autoRA—automatic reference areas) is presented, and its efficiency is evaluated in Sátiro Dias, Bahia, Brazil. autoRA integrates multiple environmental covariates (e.g., geomorphology, geology, digital elevation models, temperature, precipitation, etc.) using the Gower’s Dissimilarity Index to capture landscape variability more comprehensively. One hundred and two soil profiles were collected under a specialist’s manual delineation to establish baseline mapping soil taxonomy. We tested autoRA coverages ranging from 10% to 50%, comparing them to RA manual delineation and a conventional “Total Area” (TA) approach. Environmental heterogeneity was insufficiently sampled at lower coverages (autoRA at 10–20%), resulting in poor classification accuracy (0.11–0.14). In contrast, larger coverages significantly improved performance: 30% yielded an accuracy of 0.85, while 40% and 50% reached 0.96. Notably, 40% struck the best balance between high accuracy (kappa = 0.65) and minimal redundancy, outperforming RA manual delineation (accuracy = 0.75) and closely matching the best TA outcomes. These findings underscore the advantage of applying an automated, diversity-driven strategy like autoRA before field campaigns, ensuring the representative sampling of critical environmental gradients to improve DSM workflows.
format Article
id doaj-art-eaf4a86078eb4f2aac147e0faaa292f0
institution OA Journals
issn 2073-445X
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Land
spelling doaj-art-eaf4a86078eb4f2aac147e0faaa292f02025-08-20T01:48:41ZengMDPI AGLand2073-445X2025-03-0114360410.3390/land14030604autoRA: An Algorithm to Automatically Delineate Reference Areas—A Case Study to Map Soil Classes in Bahia, BrazilHugo Rodrigues0Marcos Bacis Ceddia1Gustavo Mattos Vasques2Sabine Grunwald3Ebrahim Babaeian4André Luis Oliveira Villela5Laboratory of Soil and Water in Agroecosystems (LASA), Postgraduation in Soil Science, Agronomy Institute, Federal Rural University of Rio de Janeiro, Seropédica 23890-000, BrazilLaboratory of Soil and Water in Agroecosystems (LASA), Postgraduation in Soil Science, Agronomy Institute, Federal Rural University of Rio de Janeiro, Seropédica 23890-000, BrazilBrazilian Research Brazilian Agricultural Research Corporation—Soils, Rio de Janeiro 22460-000, BrazilPedometrics, Landscape Analysis & GIS Laboratory, Soil, Water, and Ecosystem Sciences Department, University of Florida, Gainesville, FL 32611, USAEnvironmental Soil Physics Lab, Soil, Water, and Ecosystem Sciences Department, University of Florida, Gainesville, FL 32611, USATechnical College of the Federal Rural University of Rio de Janeiro, Rio de Janeiro 23897-000, BrazilThe reference area (RA) approach has been frequently used in soil surveying and mapping projects, since it allows for reduced costs. However, a crucial point in using this approach is the choice or delineation of an RA, which can compromise the accuracy of prediction models. In this study, an innovative algorithm that delineates RA (autoRA—automatic reference areas) is presented, and its efficiency is evaluated in Sátiro Dias, Bahia, Brazil. autoRA integrates multiple environmental covariates (e.g., geomorphology, geology, digital elevation models, temperature, precipitation, etc.) using the Gower’s Dissimilarity Index to capture landscape variability more comprehensively. One hundred and two soil profiles were collected under a specialist’s manual delineation to establish baseline mapping soil taxonomy. We tested autoRA coverages ranging from 10% to 50%, comparing them to RA manual delineation and a conventional “Total Area” (TA) approach. Environmental heterogeneity was insufficiently sampled at lower coverages (autoRA at 10–20%), resulting in poor classification accuracy (0.11–0.14). In contrast, larger coverages significantly improved performance: 30% yielded an accuracy of 0.85, while 40% and 50% reached 0.96. Notably, 40% struck the best balance between high accuracy (kappa = 0.65) and minimal redundancy, outperforming RA manual delineation (accuracy = 0.75) and closely matching the best TA outcomes. These findings underscore the advantage of applying an automated, diversity-driven strategy like autoRA before field campaigns, ensuring the representative sampling of critical environmental gradients to improve DSM workflows.https://www.mdpi.com/2073-445X/14/3/604soil class mappingdigital soil mappingpreviously mapped areas
spellingShingle Hugo Rodrigues
Marcos Bacis Ceddia
Gustavo Mattos Vasques
Sabine Grunwald
Ebrahim Babaeian
André Luis Oliveira Villela
autoRA: An Algorithm to Automatically Delineate Reference Areas—A Case Study to Map Soil Classes in Bahia, Brazil
Land
soil class mapping
digital soil mapping
previously mapped areas
title autoRA: An Algorithm to Automatically Delineate Reference Areas—A Case Study to Map Soil Classes in Bahia, Brazil
title_full autoRA: An Algorithm to Automatically Delineate Reference Areas—A Case Study to Map Soil Classes in Bahia, Brazil
title_fullStr autoRA: An Algorithm to Automatically Delineate Reference Areas—A Case Study to Map Soil Classes in Bahia, Brazil
title_full_unstemmed autoRA: An Algorithm to Automatically Delineate Reference Areas—A Case Study to Map Soil Classes in Bahia, Brazil
title_short autoRA: An Algorithm to Automatically Delineate Reference Areas—A Case Study to Map Soil Classes in Bahia, Brazil
title_sort autora an algorithm to automatically delineate reference areas a case study to map soil classes in bahia brazil
topic soil class mapping
digital soil mapping
previously mapped areas
url https://www.mdpi.com/2073-445X/14/3/604
work_keys_str_mv AT hugorodrigues autoraanalgorithmtoautomaticallydelineatereferenceareasacasestudytomapsoilclassesinbahiabrazil
AT marcosbacisceddia autoraanalgorithmtoautomaticallydelineatereferenceareasacasestudytomapsoilclassesinbahiabrazil
AT gustavomattosvasques autoraanalgorithmtoautomaticallydelineatereferenceareasacasestudytomapsoilclassesinbahiabrazil
AT sabinegrunwald autoraanalgorithmtoautomaticallydelineatereferenceareasacasestudytomapsoilclassesinbahiabrazil
AT ebrahimbabaeian autoraanalgorithmtoautomaticallydelineatereferenceareasacasestudytomapsoilclassesinbahiabrazil
AT andreluisoliveiravillela autoraanalgorithmtoautomaticallydelineatereferenceareasacasestudytomapsoilclassesinbahiabrazil