|LAMICHHANE, SUSHIL - University Of New England|
|KUMAR, LALIT - Eastcoast Geospatial Consultants|
Submitted to: Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 11/19/2021
Publication Date: N/A
Interpretive Summary: Remote sensing and topographic data are widely used to predict and map the spatial distribution of soil organic carbon (SOC). This study applied nine different combinations of topographic and multi-season remotely sensed data and mapped SOC in the cultivated lands of a middle mountain catchment of Nepal using a machine learning technique. Prediction of SOC contents was improved when remote sensing data of multiple seasons were used together with the terrain variables.
Technical Abstract: Although algorithms are well developed to predict soil organic carbon (SOC), selecting appropriate covariates to improve the accuracy of prediction is an ongoing challenge. Terrain attributes and remote sensing data are the most common covariates for SOC prediction. This study tested the predictive performance of nine different combinations of topographic variables and multi-season remotely sensed data to improve the prediction of SOC in the cultivated lands of a middle mountain catchment of Nepal. The random forest method was used to predict SOC contents and the quantile regression forest for quantifying the prediction uncertainty. Prediction of SOC contents was improved when remote sensing data of multiple seasons were used together with the terrain variables. Remote sensing data of multiple seasons capture the dynamic conditions of surface soils more effectively than using an image of a single season. It is concluded that the use of remote sensing images of multiple seasons instead of a snapshot of a single period may be more effective for improving the prediction of SOC in a digital soil mapping framework. However, an image with the right timing of cropping season can provide comparable results if a parsimonious model is preferred.