Spatial assessment of landslide susceptibility mapping generated by fuzzy-AHP and decision tree approaches

Saygın, Fikret; Şişman, Yasemin; Dengi̇z, Orhan; Sisman, Aziz

doi:10.1016/j.asr.2023.01.057

Cited by 13 publications

(7 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note: ‘①’ indicates cultivated terraces; ‘②’ indicates grassy terraces. If the AUC value is greater than 0.50 and the closer it is to 1, the more accurate the terrace simulation rules are (Saygin et al, 2023). [Colour figure can be viewed at wileyonlinelibrary.com]…”

Section: Resultsmentioning

confidence: 99%

“…Additionally, we divided the sample points into two parts: 70% were utilized to train the rules, while the remaining 30% were utilized to assess their accuracy. The performance of classification models is generally evaluated using receiver operating characteristic (ROC) curves and area under the curve (AUC) values (Saygin et al, 2023). In this study, we validated the classification efficacy of the DTM through ROC curves.…”

Section: Methodology and Methodsmentioning

confidence: 99%

“…As a classical DTM, the CHAID (Chi-Square Automatic Interaction Detection) algorithm was utilized in this study, which involves partitioning a subset of a domain into two or more consecutive child nodes from a dataset (Saygin et al, 2023). To simulate the basic terraced areas, the terrace simulation rules were established in DTM by training the data layer generated in Section 2.3.1.…”

Section: Establishment Of Terrace Simulation Rules Using the Decision...mentioning

confidence: 99%

See 2 more Smart Citations

Mapping long‐term terrace change in the Chinese Loess Plateau: A new approach by decision tree model with digital elevation model (DEM) and land use

Shi,

Wei

2024

Earth Surf Processes Landf

View full text Add to dashboard Cite

Human‐created terraces are distributed extensively in the Chinese Loess Plateau, which play key roles in soil conservation, agricultural production and sustainable development. However, large‐scale and long‐term terrace mapping remains a big challenge due to the complexity of topography, land cover and the deficiency of high‐quality historical spatial data. Facing this task, our study aims to develop a new approach for capturing 30 years (from 1990 to 2020) of terrace patterns at macroscales (the whole Loess Plateau, with an area of 6.4 × 105 km2). The decision tree model (DTM) was integrated with digital elevation model (DEM) and land use data to detect terrace change, and terraced samples were extracted from existing findings for spatial validation. Our study confirmed that this new approach can work successfully on identifying cultivated and grassy terraces, as evidenced by receiver operating characteristic (ROC) curves and area under curve (AUC) values. More notably, a decreasing trend was detected in cultivated terraces with continued uneven distribution from 1990 to 2020, while the areas of grassy terraces increased markedly with more‐concentrated larger patches. This finding indicated that huge areas of terrace abandonment may have already occurred in this region. More attention thus should be paid to the rising risks of cropland utilization and food security. Since it is the first time to get long‐term reliable terrace maps on the Loess Plateau, our efforts can help to better take stock of terrace resources for wiser land use managements and agricultural policy adjustments, finally benefiting socio‐ecological sustainability.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodology and Methodsmentioning

confidence: 99%

Section: Establishment Of Terrace Simulation Rules Using the Decision...mentioning

confidence: 99%

See 1 more Smart Citation

Mapping long‐term terrace change in the Chinese Loess Plateau: A new approach by decision tree model with digital elevation model (DEM) and land use

Shi,

Wei

2024

Earth Surf Processes Landf

View full text Add to dashboard Cite

show abstract

“…In this study, the CHAID (Chi-Square Automatic Interaction Detection) algorithm was employed, which is a classic DT constructed by dividing a subset of a domain into two or more consecutive child nodes starting from a dataset (Saygin et al, 2023). Here, four terrain factors were used as feature elements to identify cultivated and grassy terraces, and discriminant rules were formed based on the DT model conducted by SPSS software.…”

Section: Estimation Of Terraces Identification Rules Using Decision T...mentioning

confidence: 99%

“…Specifically, we divided the sample points into two parts, where 70% of the sample points were used to train the rule and the remaining 30% to test its accuracy. The ROC (Receiver Operating Characteristics) curve and AUC (Area Under the Curve) values are mostly used to analyze the performance of classification models (Saygin et al, 2023), so we applied them to test the identification rules of cultivated terraces and grassy terraces calculated by the DT model.…”

Section: Estimation Of Terraces Identification Rules Using Decision T...mentioning

confidence: 99%

Identifying large-scale terrace landscape pattern in the Loess Plateau of China: A new approach based on DEM and land use data

Shi

Wei

2023

Preprint

View full text Add to dashboard Cite

The historic significance and development value of terracing is extremely important, which is an unavoidable requirement to ensure national agricultural production and to restore the soil environment. Effective capture of spatial information from large-scale terrace areas can provide data reference and support for macro-planning, timely management and decision making in terrace construction. Overcoming the limitation that remote sensing cannot effectively expand temporal and spatial scales, in this study, we present a novel method for rapidly identifying large-scale spatial patterns of terraces over multiple time periods. Based on the decision tree (DT) model algorithm, this paper took the existing research results as the sampling data of terraces, combined digital elevation model and land use data, and excavated the rules of terrace identification. The spatial distribution of terraces in the Loess Plateau from 1990 to 2020 was then analyzed visually, based on the terrace recognition rules, and its accuracy was checked against the existing literature. Overall, the results show that terrace recognition rules based on the DT model can effectively identify cultivated and grassy terraces with AUC values greater than 0.7. Furthermore, the kappa coefficients for the cultivated and grass terraces, which were 0.92 and 0.86, were in agreement with the sampling data. Between 1990 and 2020, cultivated terrace area decreased and patch distribution remained patchy, as the area of the grassy terraces increased and the plots continued to aggregate. Once verified, the overall effect of the terrace identification results is substantial, and there is no significant departure from the relevant literature. The aim of this study is to explore an efficient identification method to capture information on the spatial distribution of terraces at a macro scale, providing a new approach to quantitative terrace research from a large-scale perspective.

show abstract

GIS-based landslide susceptibility zoning using a coupled model: a case study in Badong County, China

Wang,

Deng,

Liu

2023

Environ Sci Pollut Res

View full text Add to dashboard Cite

Spatial assessment of landslide susceptibility mapping generated by fuzzy-AHP and decision tree approaches

Cited by 13 publications

References 71 publications

Mapping long‐term terrace change in the Chinese Loess Plateau: A new approach by decision tree model with digital elevation model (DEM) and land use

Mapping long‐term terrace change in the Chinese Loess Plateau: A new approach by decision tree model with digital elevation model (DEM) and land use

Identifying large-scale terrace landscape pattern in the Loess Plateau of China: A new approach based on DEM and land use data

GIS-based landslide susceptibility zoning using a coupled model: a case study in Badong County, China

Contact Info

Product

Resources

About