A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Hybrid-optimized logistic regression model of landslide susceptibility along mountain highway
https://orcid.org/0000-0002-2045-729X
Abstract This study aims to explore the influence of the training sample selection method and the presence and absence sample ratio on the study of landslide susceptibility by the logistic stepwise regression (LSR) model. Eight-kilometer range of the main road in Wenchuan County is taken as the research area, and the neighboring Mao County is considered to test the robustness of LSR models. The performance of the models obtained by randomly selecting (RS) 70% of the data as the training sample from the sample set and selecting the data as the training sample by tenfold cross-validation (CV) is compared. At the same time, the difference in model performance when the number of absence samples in the training samples is 1, 5, 7, and 10 times that of the presence samples is also studied. The results show that (1) the CV-LSR model is not only better than the RS-LSR model in terms of model prediction accuracy, but is also more stable and effective in factor selection; (2) when the number of absence samples in the training sample is too large, the model will underestimate the landslide susceptibility, and when the number of presence and absence samples is the same, the prediction effect of the model is the best.
Hybrid-optimized logistic regression model of landslide susceptibility along mountain highway
https://orcid.org/0000-0002-2045-729X
Abstract This study aims to explore the influence of the training sample selection method and the presence and absence sample ratio on the study of landslide susceptibility by the logistic stepwise regression (LSR) model. Eight-kilometer range of the main road in Wenchuan County is taken as the research area, and the neighboring Mao County is considered to test the robustness of LSR models. The performance of the models obtained by randomly selecting (RS) 70% of the data as the training sample from the sample set and selecting the data as the training sample by tenfold cross-validation (CV) is compared. At the same time, the difference in model performance when the number of absence samples in the training samples is 1, 5, 7, and 10 times that of the presence samples is also studied. The results show that (1) the CV-LSR model is not only better than the RS-LSR model in terms of model prediction accuracy, but is also more stable and effective in factor selection; (2) when the number of absence samples in the training sample is too large, the model will underestimate the landslide susceptibility, and when the number of presence and absence samples is the same, the prediction effect of the model is the best.
Hybrid-optimized logistic regression model of landslide susceptibility along mountain highway
https://orcid.org/0000-0002-2045-729X
Abstract This study aims to explore the influence of the training sample selection method and the presence and absence sample ratio on the study of landslide susceptibility by the logistic stepwise regression (LSR) model. Eight-kilometer range of the main road in Wenchuan County is taken as the research area, and the neighboring Mao County is considered to test the robustness of LSR models. The performance of the models obtained by randomly selecting (RS) 70% of the data as the training sample from the sample set and selecting the data as the training sample by tenfold cross-validation (CV) is compared. At the same time, the difference in model performance when the number of absence samples in the training samples is 1, 5, 7, and 10 times that of the presence samples is also studied. The results show that (1) the CV-LSR model is not only better than the RS-LSR model in terms of model prediction accuracy, but is also more stable and effective in factor selection; (2) when the number of absence samples in the training sample is too large, the model will underestimate the landslide susceptibility, and when the number of presence and absence samples is the same, the prediction effect of the model is the best.
Hybrid-optimized logistic regression model of landslide susceptibility along mountain highway
Zhang, Yalan (author) / Wen, Haijia (author) / Xie, Peng (author) / Hu, Dongping (author) / Zhang, Jialan (author) / Zhang, Wengang (author)
2021
Article (Journal)
Electronic Resource
English
BKL:
56.00$jBauwesen: Allgemeines
/
38.58
Geomechanik
/
38.58$jGeomechanik
/
56.20
Ingenieurgeologie, Bodenmechanik
/
56.00
Bauwesen: Allgemeines
/
56.20$jIngenieurgeologie$jBodenmechanik
RVK:
ELIB18
Multi-scale landslide susceptibility analysis along a mountain highway in Central Taiwan
| Online Contents | 2016
Multi-scale landslide susceptibility analysis along a mountain highway in Central Taiwan
| British Library Online Contents | 2016
Presenting logistic regression-based landslide susceptibility results
| British Library Online Contents | 2018
Multi-scale landslide susceptibility analysis along a mountain highway in Central Taiwan
| British Library Online Contents | 2016