Correction: Nguyen, K.A.; Chen, W. DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning. ISPRS Int. J. Geo-Inf. 2021, 10, 452

The authors of the published paper [1] would like to make the following corrections:

• (1). The last four numbers in the second column (No. of Factors) of Table 3 should read 15, 15, 16, and 16 (instead of 16, 16, 19, and 19)

Original:

Table 3

Performance comparison of machine learning models using threefold cross-validation.

Model and Factors	No. of Factors	Average RMSE (mm/yr)		Average NSE
		Training	Test	Training	Test
RF (all)	36	0.96	2.01	0.83	0.25
GBM (all)	36	0.88	1.84	0.84	0.39
RF (confirmed)	16	1.08	1.91	0.79	0.31
GBM (confirmed)	16	0.79	1.50	0.88	0.59
RF (nonrejected)	19	1.09	1.96	0.79	0.27
GBM (nonrejected)	19	0.82	1.52	0.87	0.57

Corrected:

Table 3

Performance comparison of machine learning models using threefold cross-validation.

Model and Factors	No. of Factors	Average RMSE (mm/yr)		Average NSE
		Training	Test	Training	Test
RF (all)	36	0.96	2.01	0.83	0.25
GBM (all)	36	0.88	1.84	0.84	0.39
RF (confirmed)	15	1.08	1.91	0.79	0.31
GBM (confirmed)	15	0.79	1.50	0.88	0.59
RF (nonrejected)	16	1.09	1.96	0.79	0.27
GBM (nonrejected)	16	0.82	1.52	0.87	0.57

• (2). The last parentheses on page 13 (4.3 Model Prediction) should contain the numbers 15 and 16 (instead of 16 and 19)

Original:

They both have a similar appearance because they used a similar number of variables (16 and 19).

Corrected:

They both have a similar appearance because they used a similar number of variables (15 and 16).

The authors apologize for any inconvenience caused and state that the scientific conclusions are unaffected. The original article has been updated.

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Reference

1. Nguyen, K.A.; Chen, W. DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning. ISPRS Int. J. Geo-Inf.; 2021; 10, 452. [DOI: https://dx.doi.org/10.3390/ijgi10070452]