Abstract
It is of fundamental importance to model the relationship between geo-environmental factors and piping erosion because of the environmental degradation attributed to soil loss. Methods that identify areas prone to piping erosion at the regional scale are limited. The main objective of this research is to develop a novel modeling approach by using three machine learning algorithms—mixture discriminant analysis (MDA), flexible discriminant analysis (FDA), and support vector machine (SVM) in addition to an unmanned aerial vehicle (UAV) images to map susceptibility to piping erosion in the loess-covered hilly region of Golestan Province, Northeast Iran. In this research, we have used 22 geo-environmental indices/factors and 345 identified pipes as predictors and dependent variables. The piping susceptibility maps were assessed by the area under the ROC curve (AUC). Validation of the results showed that the AUC for the three mentioned algorithms varied from 90.32% to 92.45%. We concluded that the proposed approach could efficiently produce a piping susceptibility map.
| Original language | English |
|---|---|
| Pages (from-to) | 1554-1566 |
| Journal | Science of the Total Environment |
| Volume | 646 |
| DOIs | |
| Publication status | Published - 1 Jan 2019 |
Fingerprint
Keywords
- Loess plateau
- Machine learning algorithms
- Piping collapse
- Susceptibility map
- Unmanned aerial vehicle (UAV)
Cite this
}
How can statistical and artificial intelligence approaches predict piping erosion susceptibility? / Hosseinalizadeh, Mohsen; Kariminejad, Narges; Rahmati, Omid; Keesstra, Saskia; Alinejad, Mohammad; Mohammadian Behbahani, Ali.
In: Science of the Total Environment, Vol. 646, 01.01.2019, p. 1554-1566.Research output: Contribution to journal › Article › Academic › peer-review
TY - JOUR
T1 - How can statistical and artificial intelligence approaches predict piping erosion susceptibility?
AU - Hosseinalizadeh, Mohsen
AU - Kariminejad, Narges
AU - Rahmati, Omid
AU - Keesstra, Saskia
AU - Alinejad, Mohammad
AU - Mohammadian Behbahani, Ali
PY - 2019/1/1
Y1 - 2019/1/1
N2 - It is of fundamental importance to model the relationship between geo-environmental factors and piping erosion because of the environmental degradation attributed to soil loss. Methods that identify areas prone to piping erosion at the regional scale are limited. The main objective of this research is to develop a novel modeling approach by using three machine learning algorithms—mixture discriminant analysis (MDA), flexible discriminant analysis (FDA), and support vector machine (SVM) in addition to an unmanned aerial vehicle (UAV) images to map susceptibility to piping erosion in the loess-covered hilly region of Golestan Province, Northeast Iran. In this research, we have used 22 geo-environmental indices/factors and 345 identified pipes as predictors and dependent variables. The piping susceptibility maps were assessed by the area under the ROC curve (AUC). Validation of the results showed that the AUC for the three mentioned algorithms varied from 90.32% to 92.45%. We concluded that the proposed approach could efficiently produce a piping susceptibility map.
AB - It is of fundamental importance to model the relationship between geo-environmental factors and piping erosion because of the environmental degradation attributed to soil loss. Methods that identify areas prone to piping erosion at the regional scale are limited. The main objective of this research is to develop a novel modeling approach by using three machine learning algorithms—mixture discriminant analysis (MDA), flexible discriminant analysis (FDA), and support vector machine (SVM) in addition to an unmanned aerial vehicle (UAV) images to map susceptibility to piping erosion in the loess-covered hilly region of Golestan Province, Northeast Iran. In this research, we have used 22 geo-environmental indices/factors and 345 identified pipes as predictors and dependent variables. The piping susceptibility maps were assessed by the area under the ROC curve (AUC). Validation of the results showed that the AUC for the three mentioned algorithms varied from 90.32% to 92.45%. We concluded that the proposed approach could efficiently produce a piping susceptibility map.
KW - Loess plateau
KW - Machine learning algorithms
KW - Piping collapse
KW - Susceptibility map
KW - Unmanned aerial vehicle (UAV)
U2 - 10.1016/j.scitotenv.2018.07.396
DO - 10.1016/j.scitotenv.2018.07.396
M3 - Article
VL - 646
SP - 1554
EP - 1566
JO - Science of the Total Environment
JF - Science of the Total Environment
SN - 0048-9697
ER -