Open Access
Open access
Remote Sensing, volume 15, issue 10, pages 2494

Spatial Prediction of Soil Organic Carbon Stock in the Moroccan High Atlas Using Machine Learning

Modeste Meliho 1
Mohamed Boulmane 2
Abdellatif Khattabi 3
Caleb Efelic Dansou 4
Collins Ashianga Orlando 5
Nadia Mhammdi 6
Koffi Dodji Noumonvi 7
1
 
AgroParisTech—Centre de Nancy, 14 rue Girardet-CS 14216, 54042 Nancy CEDEX, France
2
 
Division d’Aménagement de Territoire et Conservation d’Environnement et de Patrimoine au Conseil Régional, Béni Mellal-Khenifra 25000, Morocco
3
 
Ecole Nationale Forestière d’Ingenieurs (ENFI), Salé 11000, Morocco
5
 
Independent Researcher, Rabat 10000, Morocco
Publication typeJournal Article
Publication date2023-05-09
Journal: Remote Sensing
scimago Q1
SJR1.091
CiteScore8.3
Impact factor4.2
ISSN20724292, 23154632, 23154675
General Earth and Planetary Sciences
Abstract

Soil organic carbon (SOC) is an essential component, which soil quality depends on. Thus, understanding the spatial distribution and controlling factors of SOC is paramount to achieving sustainable soil management. In this study, SOC prediction for the Ourika watershed in Morocco was done using four machine learning (ML) algorithms: Cubist, random forest (RF), support vector machine (SVM), and gradient boosting machine (GBM). A total of 420 soil samples were collected at three different depths (0–10 cm, 10–20 cm, and 20–30 cm) from which SOC concentration and bulk density (BD) were measured, and consequently SOC stock (SOCS) was determined. Modeling data included 88 variables incorporating environmental covariates, including soil properties, climate, topography, and remote sensing variables used as predictors. The results showed that RF (R2 = 0.79, RMSE = 1.2%) and Cubist (R2 = 0.77, RMSE = 1.2%) were the most accurate models for predicting SOC, while none of the models were satisfactory in predicting BD across the watershed. As with SOC, Cubist (R2 = 0.86, RMSE = 11.62 t/ha) and RF (R2 = 0.79, RMSE = 13.26 t/ha) exhibited the highest predictive power for SOCS. Land use/land cover (LU/LC) was the most critical factor in predicting SOC and SOCS, followed by soil properties and bioclimatic variables. Both combinations of bioclimatic–topographic variables and soil properties–remote sensing variables were shown to improve prediction performance. Our findings show that ML algorithms can be a viable tool for spatial modeling of SOC in mountainous Mediterranean regions, such as the study area.

Found 
Found 

Top-30

Journals

1
2
1
2

Publishers

1
2
3
4
1
2
3
4
  • We do not take into account publications without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Share
Cite this
GOST | RIS | BibTex | MLA
Found error?