skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Upscaling Soil Organic Carbon Measurements at the Continental Scale Using Multivariate Clustering Analysis and Machine Learning

Journal Article · · Journal of Geophysical Research. Biogeosciences
DOI:https://doi.org/10.1029/2023JG007702· OSTI ID:2320276

Abstract Estimates of soil organic carbon (SOC) stocks are essential for many environmental applications. However, significant inconsistencies exist in SOC stock estimates for the U.S. across current SOC maps. We propose a framework that combines unsupervised multivariate geographic clustering (MGC) and supervised Random Forests regression, improving SOC maps by capturing heterogeneous relationships with SOC drivers. We first used MGC to divide the U.S. into 20 SOC regions based on the similarity of covariates (soil biogeochemical, bioclimatic, biological, and physiographic variables). Subsequently, separate Random Forests models were trained for each SOC region, utilizing environmental covariates and SOC observations. Our estimated SOC stocks for the U.S. (52.6 ± 3.2 Pg for 0–30 cm and 108.3 ± 8.2 Pg for 0–100 cm depth) were within the range estimated by existing products like Harmonized World Soil Database, HWSD (46.7 Pg for 0–30 cm and 90.7 Pg for 0–100 cm depth) and SoilGrids 2.0 (45.7 Pg for 0–30 cm and 133.0 Pg for 0–100 cm depth). However, independent validation with soil profile data from the National Ecological Observatory Network showed that our approach ( R 2  = 0.51) outperformed the estimates obtained from Harmonized World Soil Database ( R 2  = 0.23) and SoilGrids 2.0 ( R 2  = 0.39) for the topsoil (0–30 cm). Uncertainty analysis (e.g., low representativeness and high coefficients of variation) identified regions requiring more measurements, such as Alaska and the deserts of the U.S. Southwest. Our approach effectively captures the heterogeneous relationships between widely available predictors and the current SOC baseline across regions, offering reliable SOC estimates at 1 km resolution for benchmarking Earth system models.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE; USDOE Office of Science (SC), Biological and Environmental Research (BER). Earth & Environmental Systems Science (EESS); National Science Foundation (NSF)
Grant/Contract Number:
AC05-00OR22725; DEB-2106137; DEB-2106138
OSTI ID:
2320276
Alternate ID(s):
OSTI ID: 2301629; OSTI ID: 2317677
Journal Information:
Journal of Geophysical Research. Biogeosciences, Journal Name: Journal of Geophysical Research. Biogeosciences Vol. 129 Journal Issue: 2; ISSN 2169-8953
Publisher:
American Geophysical Union (AGU)Copyright Statement
Country of Publication:
United States
Language:
English

References (92)

Global soil carbon: understanding and managing the largest terrestrial carbon pool journal February 2014
High sensitivity of peat decomposition to climate change through water-table feedback journal October 2008
Potential of Multivariate Quantitative Methods for Delineation and Visualization of Ecoregions journal April 2004
Networking our science to characterize the state, vulnerabilities, and management opportunities of soil organic matter journal September 2017
Variability of the Cecil Map Unit in Appomattox County, Virginia journal September 1989
Total carbon and nitrogen in the soils of the world journal June 1996
Towards a global-scale soil climate mitigation strategy journal October 2020
Soil Organic Carbon Across Mexico and the Conterminous United States (1991–2010) journal February 2020
Principal component analysis: Principal component analysis journal June 2010
MODIS/Terra Vegetation Indices 16-Day L3 Global 1km SIN Grid V061 dataset January 2021
Variability within a soil mapping unit mapped at the soil type level in the Wanganui district journal November 1976
Similar importance of edaphic and climatic factors for controlling soil organic carbon stocks of the world journal March 2021
Game theory interpretation of digital soil mapping convolutional neural networks journal August 2020
Forest soil carbon inventories and dynamics along an elevation gradient in the southern Appalachian Mountains journal May 1999
Building and testing conceptual and empirical models for predicting soil bulk density journal December 2007
Carbon unlocked from soils journal September 2005
Importance and strength of environmental controllers of soil organic carbon changes with scale journal October 2020
Application of Machine Learning Methods for Estimation Soil Bulk Density conference February 2022
Spatial heterogeneity and environmental predictors of permafrost region soil organic carbon stocks journal February 2021
Improvements of the MODIS terrestrial gross and net primary production global data set journal March 2005
WorldClim 2: new 1-km spatial resolution climate surfaces for global land areas: NEW CLIMATE SURFACES FOR GLOBAL LAND AREAS journal May 2017
Digital soil mapping: A brief history and some lessons journal February 2016
Altitudinal gradients of soil and vegetation carbon and nitrogen in a high altitude nature reserve of Karakoram ranges journal March 2016
The landscape of soil carbon data: Emerging questions, synergies and databases journal May 2019
Continental-scale controls on soil organic carbon across sub-Saharan Africa journal January 2021
Beyond clay: towards an improved set of variables for predicting soil organic matter content journal February 2018
Welcome to the Tidyverse journal November 2019
Improving model parsimony and accuracy by modified greedy feature selection in digital soil mapping journal April 2023
Carbon Sequestration in Dryland Ecosystems journal December 2003
Global Carbon Budget 2022 journal November 2022
Soil mapping, classification, and pedologic modeling: History and future directions journal February 2016
Causes of variation in soil carbon simulations from CMIP5 Earth system models and comparison with observations journal January 2013
Current status, uncertainty and future needs in soil organic carbon monitoring journal January 2014
Ecohydrology of dry regions of the United States: precipitation pulses and intraseasonal drought journal June 2009
Reviews and syntheses: The promise of big diverse soil data, moving current practices towards future potential journal July 2022
geemap: A Python package for interactive mapping with Google Earth Engine journal July 2020
National estimation of soil organic carbon storage potential for arable soils: A data-driven approach coupled with carbon-landscape zones journal May 2019
The Unified North American Soil Map and its implication on the soil organic carbon stock in North America journal January 2013
How accurately can soil organic carbon stocks and stock changes be quantified by soil inventories? journal January 2011
Google Earth Engine: Planetary-scale geospatial analysis for everyone journal December 2017
Mississippi river sediment diversions and coastal wetland sustainability: Synthesis of responses to freshwater, sediment, and nutrient inputs journal May 2019
Soil organic carbon pools in the northern circumpolar permafrost region: SOIL ORGANIC CARBON POOLS journal June 2009
Status and trends in Arctic vegetation: Evidence from experimental warming and long-term monitoring journal March 2019
The 4p1000 initiative: Opportunities, limitations and challenges for implementing soil organic carbon sequestration as a sustainable development strategy journal March 2019
Altitudinal variation in soil organic carbon stock in coniferous subtropical and broadleaf temperate forests in Garhwal Himalaya journal August 2009
Vulnerability of Permafrost Carbon to Climate Change: Implications for the Global Carbon Cycle journal September 2008
Representativeness-based sampling network design for the State of Alaska journal June 2013
The Carbon Budget in Soils journal May 2001
Empirical relationships between environmental factors and soil organic carbon produce comparable prediction accuracy to machine learning journal September 2022
SoilGrids 2.0: producing soil information for the globe with quantified spatial uncertainty journal January 2021
Controls over carbon storage and turnover in high-latitude soils journal December 2000
Mapping of soil organic carbon stocks for spatially explicit assessments of climate change mitigation potential journal February 2013
Effects of mapped variation in soil conditions on estimates of soil carbon and nitrogen stocks for South America journal August 2000
Using multivariate clustering to characterize ecoregion borders journal January 1999
Soil Property and Class Maps of the Conterminous United States at 100‐Meter Spatial Resolution journal January 2018
Soil Organic Carbon Stocks in Alaska Estimated with Spatial and Pedon Data journal January 2010
Soil Carbon Sequestration Impacts on Global Climate Change and Food Security journal June 2004
How to measure, report and verify soil carbon change to realize the potential of soil carbon sequestration for atmospheric greenhouse gas removal journal October 2019
Distribution of Soil Organic Carbon in the Conterminous United States book January 2014
Acceleration of global warming due to carbon-cycle feedbacks in a coupled climate model journal November 2000
Soils of Mountainous Landscapes other February 2016
Soil organic carbon is not just for soil scientists: measurement recommendations for diverse practitioners journal February 2021
Principal component analysis: a review and recent developments
  • Jolliffe, Ian T.; Cadima, Jorge
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 374, Issue 2065 https://doi.org/10.1098/rsta.2015.0202
journal April 2016
Regional environmental controllers influence continental scale soil carbon stocks and future carbon dynamics journal March 2021
SoilGrids250m: Global gridded soil information based on machine learning journal February 2017
Decipher soil organic carbon dynamics and driving forces across China using machine learning journal March 2022
Soil carbon storage controlled by interactions between geochemistry and climate journal August 2015
The Northern Circumpolar Soil Carbon Database: spatially distributed datasets of soil coverage and soil carbon storage in the northern permafrost regions journal January 2013
Multivariate Quantitative Representativeness and Constituency Analysis of Ecological Observation Networks software June 2023
Predictive soil mapping: a review journal June 2003
Global soil organic carbon assessment journal October 2015
Global distribution of soil organic carbon – Part 1: Masses and frequency distributions of SOC stocks for the tropics, permafrost regions, wetlands, and the world journal January 2015
Building Predictive Models in R Using the caret Package journal January 2008
Paludification in black spruce (Picea mariana) forests of eastern Canada: Potential factors and management implications journal July 2005
Upper Mississippi River: seasonal and floodplain forest influences on organic matter transport journal April 1989
No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America journal January 2018
Predicting the Spatial Variation of the Soil Organic Carbon Pool at a Regional Scale journal January 2010
Threshold effects of flood duration on the vegetation and soils of the Upper Mississippi River floodplain, USA journal April 2012
Alaskan soil carbon stocks: spatial variability and dependence on environmental factors journal January 2012
High stocks of soil organic carbon in the North American Arctic region journal August 2008
Estimating forest soil bulk density using boosted regression modelling: Estimating forest soil bulk density using boosted regression modelling journal November 2010
Estimating heterotrophic respiration at large scales: challenges, approaches, and next steps journal June 2016
Digital mapping of GlobalSoilMap soil properties at a broad scale: A review journal March 2022
Soil Pedon Carbon and Nitrogen Data for Alaska: An Analysis and Update journal January 2013
National soil organic carbon estimates can improve global estimates journal March 2019
SoilGrids1km — Global Soil Information Based on Automated Mapping journal August 2014
Evaluation of pedotransfer functions for predicting soil bulk density for U.S. soils journal December 2018
Pedoclimatic zone-based three-dimensional soil organic carbon mapping in China journal April 2020
Random Forests journal January 2001
Soil organic and inorganic carbon contents of landscape units in Belgium derived using data from 1950 to 1970 journal March 2004
Divergent controls of soil organic carbon between observations and process-based models journal July 2021
Soil carbon distribution in Alaska in relation to soil-forming factors journal November 2011

Similar Records

Spatial distribution of soil carbon stocks in a semi-arid region of India
Journal Article · Thu Oct 18 00:00:00 EDT 2018 · Geoderma Regional · OSTI ID:2320276

The Unified North American Soil Map and Its Implication on the Soil Organic Carbon Stock in North America
Journal Article · Tue Jan 01 00:00:00 EST 2013 · Biogeosciences · OSTI ID:2320276

National soil organic carbon estimates can improve global estimates
Journal Article · Tue Sep 11 00:00:00 EDT 2018 · Geoderma · OSTI ID:2320276

Related Subjects