Effects of spatial data resolution on the modelling and mapping of soil organic carbon content in hill country grassland landscapes
dc.citation.issue | 1 | |
dc.citation.volume | 40 | |
dc.contributor.author | Tran DX | |
dc.contributor.author | Dominati E | |
dc.contributor.author | Lowry J | |
dc.contributor.author | Mackay A | |
dc.contributor.author | Vibart R | |
dc.contributor.author | Pearson D | |
dc.contributor.author | Devantier B | |
dc.contributor.author | Noakes E | |
dc.date.accessioned | 2024-10-08T19:53:01Z | |
dc.date.available | 2024-10-08T19:53:01Z | |
dc.date.issued | 2024-01-19 | |
dc.description.abstract | Limited use has been made of spatially explicit modelling of soil organic carbon (SOC) in highly complex farmed landscapes to advance current mapping efforts. This study aimed to address this gap in knowledge by evaluating the spatial prediction of SOC content in the 0–75 mm soil depth in hill country landscapes in New Zealand (NZ) using point-based training data, along with topographic covariates and Sentinel 2 spectral band ratios using an automated set of machine learning (AutoML) tools in ArcGIS. Subsequently, it also focused on quantifying the effects of spatial data resolution (i.e., 1, 8, 15, and 25 m) in terms of predicted map accuracy. Farmlets with contrasting phosphorus fertilizer and sheep grazing histories located at the Ballantrae Hill Country Research Station, NZ were selected to conduct the research. Six candidate algorithms incorporated in the AutoML tools (i.e., XGBoost, LightGBM, linear regression, decision trees, extra trees, random forest) and ensemble model were utilized to model the spatial pattern of SOC content. The results show that the ensemble model that combine predictions of various algorithms applied for 1 m data resolution enables the highest performance and accuracy (i.e., R2 =.76, RMSE = 0.66%). Among the predictive variables used in the model, slope, wetness, and topographic position indices were found to be the most important topographical features that explain SOC patterns in the study area. Inclusion of spectral indices derived from remote sensing, including surface soil moisture and clay minerals ratio, made further improvement to the SOC content prediction. The study reveals that a decrease in the resolution of the geospatial data does not substantively affect the mean SOC content estimation of a farm-scale modelling. However, using coarser resolution data reduces the ability of the model to predict changes in the spatial pattern of SOC content across a hill country grassland landscape. | |
dc.description.confidential | false | |
dc.edition.edition | January 2024 | |
dc.identifier.citation | Tran DX, Dominati E, Lowry J, Mackay A, Vibart R, Pearson D, Devantier B, Noakes E. (2024). Effects of spatial data resolution on the modelling and mapping of soil organic carbon content in hill country grassland landscapes. Soil Use and Management. 40. 1. | |
dc.identifier.doi | 10.1111/sum.12966 | |
dc.identifier.eissn | 1475-2743 | |
dc.identifier.elements-type | journal-article | |
dc.identifier.issn | 0266-0032 | |
dc.identifier.number | e12966 | |
dc.identifier.uri | https://mro.massey.ac.nz/handle/10179/71626 | |
dc.language | English | |
dc.publisher | John Wiley and Sons Ltd on behalf of British Society of Soil Science | |
dc.publisher.uri | https://bsssjournals.onlinelibrary.wiley.com/doi/10.1111/sum.12966 | |
dc.relation.isPartOf | Soil Use and Management | |
dc.rights | (c) The author/s | en |
dc.rights.license | CC BY-NC-ND 4.0 | en |
dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/4.0/ | en |
dc.subject | automated machine learning | |
dc.subject | grassland | |
dc.subject | hill country | |
dc.subject | soil organic carbon | |
dc.subject | spatial data resolution | |
dc.title | Effects of spatial data resolution on the modelling and mapping of soil organic carbon content in hill country grassland landscapes | |
dc.type | Journal article | |
pubs.elements-id | 480564 | |
pubs.organisational-group | Other |