Regional ensemble modeling reduces uncertainty for digital soil mapping

Authors: BRUNGARD, COLBY - New Mexico State University; NAUMAN, TRAVIS - Us Geological Survey (USGS); DUNIWAY, MIKE - Us Geological Survey (USGS); VEBLEN, KARI - Us Geological Survey (USGS); NEHRING, KYLE - Natural Resources Conservation Service (NRCS, USDA); Salley, Shawn; ANCHANG, JULIUS - New Mexico State University

Submitted to: Geoderma
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 2/3/2021
Publication Date: 9/1/2021
Citation: Brungard, C., Nauman, T., Duniway, M., Veblen, K., Nehring, K., Salley, S.W., Anchang, J. 2021. Regional ensemble modeling reduces uncertainty for digital soil mapping. Geoderma. 396. https://doi.org/10.1016/j.geoderma.2021.114998.
DOI: https://doi.org/10.1016/j.geoderma.2021.114998

Interpretive Summary: Recent country and continental-scale digital soil mapping efforts have used a single model to predict soil properties across large regions. However, different eco-physiographic regions within large-extent areas are likely to have different soil-landscape relationships so models built specifically for these regions may more accurately capture these relationships relative to a ‘global’ model. We ask the question: Is a single ‘global’ model sufficient or are regionally-specific models needed for accurate digital soil mapping? We found: 1) useful inter-regional differences in global model accuracy were revealed when the global model was validated by region. 2) No consistent relationship between training observation density and accuracy/uncertainty metrics. 3) No meaningful differences in accuracy and uncertainty metrics between physiographic and geographic regions. 4) Ensembles of regionally-specific models were approximately as accurate as global models. 5) Both region-specific models and ensembles of regional models were less uncertain than the global model. Overall, we recommend the use of soil depth class predictions made from MLRA regional ensemble models because this prediction had higher accuracy than the ecoregion ensemble model prediction, but lower uncertainty than both the global model and the landform ensemble model predictions. We answer our question: Ensembles of regionally-specific models are approximately as accurate as global models, but result in less uncertainty.

Technical Abstract: Recent country and continental-scale digital soil mapping efforts have used a single model to predict soil properties across large regions. However, different eco-physiographic regions within large-extent areas are likely to have different soil-landscape relationships so models built specifically for these regions may more accurately capture these relationships relative to a ‘global’ model. We ask the question: Is a single ‘global’ model sufficient or are regionally-specific models needed for accurate digital soil mapping? We test this question by modeling soil depth classes across the 432,000 km2 upper Colorado River Basin in the Western USA using a single global model, multiple regional models applied to different eco-physiographic areas within the study area, and ensembles of the regional models. Accuracy for the global model using the validation set was 62.8%. Regional model accuracies ranged between 56.1% and 75.0%. We found: 1) useful inter-regional differences in global model accuracy were revealed when the global model was validated by region. 2) No consistent relationship between training observation density and accuracy/uncertainty metrics. 3) No meaningful differences in accuracy and uncertainty metrics between physiographic and geographic regions. 4) Ensembles of regionally-specific models were approximately as accurate as global models. 5) Both region-specific models and ensembles of regional models were less uncertain than the global model. Overall, we recommend the use of soil depth class predictions made from MLRA regional ensemble models because this prediction had higher accuracy than the ecoregion ensemble model prediction, but lower uncertainty than both the global model and the landform ensemble model predictions. We answer our question: Ensembles of regionally-specific models are approximately as accurate as global models, but result in less uncertainty.