A New Application of Random Forest Algorithm to Estimate Coverage of Moss-Dominated Biological Soil Crusts in Semi-Arid Mu Us Sandy Land, China

Xiang Chen,Atsushi Tsunekawa,Kun Feng,Tao Wang,Zichen Guo,Fei Peng,Wenping Kang,Shulin Liu

doi:10.3390/rs11111286

Abstract

Biological soil crusts (BSCs) play an essential role in desert ecosystems. Knowledge of the distribution and disappearance of BSCs is vital for the management of ecosystems and for desertification researches. However, the major remote sensing approaches used to extract BSCs are multispectral indices, which lack accuracy, and hyperspectral indices, which have lower data availability and require a higher computational effort. This study employs random forest (RF) models to optimize the extraction of BSCs using band combinations similar to the two multispectral BSC indices (Crust Index-CI; Biological Soil Crust Index-BSCI), but covering all possible band combinations. Simulated multispectral datasets resampled from in-situ hyperspectral data were used to extract BSC information. Multispectral datasets (Landsat-8 and Sentinel-2 datasets) were then used to detect BSC coverage in Mu Us Sandy Land, located in northern China, where BSCs dominated by moss are widely distributed. The results show that (i) the spectral curves of moss-dominated BSCs are different from those of other typical land surfaces, (ii) the BSC coverage can be predicted using the simulated multispectral data (mean square error (MSE) < 0.01), (iii) Sentinel-2 satellite datasets with CI-based band combinations provided a reliable RF model for detecting moss-dominated BSCs (10-fold validation, R2 = 0.947; ground validation, R2 = 0.906). In conclusion, application of the RF algorithm to the Sentinel-2 dataset can precisely and effectively map BSCs dominated by moss. This new application can be used as a theoretical basis for detecting BSCs in other arid and semi-arid lands within desert ecosystems.

Highlights

IntroductionBiological soil crusts (BSCs) containing microphytic communities (i.e., cyanobacteria, lichens, liverworts, and mosses), grow within or directly on top of soil [1]
Biological soil crusts (BSCs) containing microphytic communities, grow within or directly on top of soil [1]
The Crust Index (CI) [10] and the Biological Soil Crust Index (BSCI) [11] were employed to identify BSCs using multispectral optical information obtained from Landsat Thematic Mapper (TM) and Landsat Enhanced Thematic Mapper Plus (ETM+) images, respectively

Summary

Introduction

Biological soil crusts (BSCs) containing microphytic communities (i.e., cyanobacteria, lichens, liverworts, and mosses), grow within or directly on top of soil [1]. The differences between spectra relating to BSC, vegetation, and bare soil have been analyzed to enable the effective determination of BSCs [9,10,11,12] and to quantitatively predict their relative cover [5]. Based on these efforts, several BSC indices have been developed using optical reflectivity. Satisfactory results cannot be obtained when applying the CI and BSCI in regions covered by a mixture of photosynthetic and non-photosynthetic vegetation, bare sand, rocks, and BSCs [8,13] because it is difficult to extract the subtle spectral characteristics of BSCs [14]. There are no BSC indices for detecting moss-dominated BSCs

Objectives

Methods

Findings

Discussion

Conclusion