Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Feb 4;11(1):3147.
doi: 10.1038/s41598-021-82527-3.

Credal decision tree based novel ensemble models for spatial assessment of gully erosion and sustainable management

Alireza Arabameri  1 , Nitheshnirmal Sadhasivam  2   3 , Hamza Turabieh  4 , Majdi Mafarja  5 , Fatemeh Rezaie  6   7 , Subodh Chandra Pal  8 , M Santosh  9   10
Affiliations

Credal decision tree based novel ensemble models for spatial assessment of gully erosion and sustainable management

Alireza Arabameri et al. Sci Rep. .

Abstract

We introduce novel hybrid ensemble models in gully erosion susceptibility mapping (GESM) through a case study in the Bastam sedimentary plain of Northern Iran. Four new ensemble models including credal decision tree-bagging (CDT-BA), credal decision tree-dagging (CDT-DA), credal decision tree-rotation forest (CDT-RF), and credal decision tree-alternative decision tree (CDT-ADTree) are employed for mapping the gully erosion susceptibility (GES) with the help of 14 predictor factors and 293 gully locations. The relative significance of GECFs in modelling GES is assessed by random forest algorithm. Two cut-off-independent (area under success rate curve and area under predictor rate curve) and six cut-off-dependent metrics (accuracy, sensitivity, specificity, F-score, odd ratio and Cohen Kappa) were utilized based on both calibration as well as testing dataset. Drainage density, distance to road, rainfall and NDVI were found to be the most influencing predictor variables for GESM. The CDT-RF (AUSRC = 0.942, AUPRC = 0.945, accuracy = 0.869, specificity = 0.875, sensitivity = 0.864, RMSE = 0.488, F-score = 0.869 and Cohen's Kappa = 0.305) was found to be the most robust model which showcased outstanding predictive accuracy in mapping GES. Our study shows that the GESM can be utilized for conserving soil resources and for controlling future gully erosion.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Gully erosion susceptibility mapping using (a) credal decision tree (CDT), (b) CDT-Dagging, (c) CDT-ADTree, (d) CDT-Bagging, (e) CDT-rotational forest (RF). ArcGIS 10.5 software was used for preparing this map (https://desktop.arcgis.com/en/).
Figure 2
Figure 2
Training performance of the models.
Figure 3
Figure 3
Validation performance of the models.
Figure 4
Figure 4
Area under the curve of the models in the training and validation data.
Figure 5
Figure 5
Odd ratio values of the models in the training and validation phases.
Figure 6
Figure 6
Values of seed cell area index (SCAI) in the susceptibility classes.
Figure 7
Figure 7
Location of study area in Iran. The map was generated using ArcGIS 10.5 software (https://desktop.arcgis.com/en/).
Figure 8
Figure 8
Flowchart of the methodology adopted in the current study.
Figure 9
Figure 9
Representative field photographs of the mapped gullies in the study area. (a) Lat: 4072920.7; Long 869988.1 (b) Lat: 4045271.7; Long 846437.7.
Figure 10
Figure 10
Gully erosion conditioning factors. (a) Elevation, (b) slope, (c) topography wetness index, (d) terrain rugged index (TRI), (e) distance to stream, (f) drainage density, (g) distance to road, (h) content of clay, (i) content of silt, (j) bulk density, (k) normalized difference vegetation index (NDVI), (l) rainfall, (m) lithology, (n) land use/land cover (LU/LC). The map was generated using ArcGIS 10.5 software (https://desktop.arcgis.com/en/).
See this image and copyright information in PMC

References

    1. Sartori M, et al. A linkage between the biophysical and the economic: Assessing the global market impacts of soil erosion. Land Use Policy. 2019;86:299–312. doi: 10.1016/j.landusepol.2019.05.014. - DOI
    1. Poesen J. Soil erosion in the Anthropocene: Research needs. Earth Surf. Process. Landforms. 2018;43:64–84. doi: 10.1002/esp.4250. - DOI
    1. Arabameri A, et al. A methodological comparison of head-cut based gully erosion susceptibility models: Combined use of statistical and artificial intelligence. Geomorphology. 2020;359:107136. doi: 10.1016/j.geomorph.2020.107136. - DOI
    1. Douglas-Mankin KR, et al. A comprehensive review of ephemeral gully erosion models. CATENA. 2020;195:104901. doi: 10.1016/j.catena.2020.104901. - DOI
    1. Muhs DR. The geochemistry of loess: Asian and North American deposits compared. J. Asian Earth Sci. 2018;155:81–115. doi: 10.1016/j.jseaes.2017.10.032. - DOI

Publication types

LinkOut - more resources