Performance of logistic regression and support vector machine conjunction with the GIS and RS in the landslide susceptibility assessment: Case study in Nakhon Si Thammarat, southern Thailand

Journal of King Saud University - Science, Journal Year: 2024, Volume and Issue: 36(8), P. 103306 - 103306

Published: June 17, 2024

The occurrence of landslides has risen in the past few decades, particularly mountainous regions worldwide, including Nakhon Si Thammarat, southern Thailand. Despite various methods being employed for initial management landslide disasters, none have proven universally effective. goal this research is to create and assess susceptibility maps (LSMs) within area by employing support vector machine (SVM) logistic regression, together with Geographic Information System (GIS) Remote Sensing (RS) techniques. Eleven factors contributing were identified as topographic, environmental, geological influences. 365 aimlessly selected into training (70%) testing (30%) datasets. four LSMs indicated that approximately 13%–20% study exhibit a high corresponding elevation relatively steep slope angles. To evaluate compare LSM models, AUC value dataset 0.977, 0.975, 0.958, 0.967 0.973, 0.969, 0.956, 0.964 SVM radial basis function (rbf) kernel, polynomial deg 2, linear kernel regression respectively. Among these SVMs rbf demonstrated highest prediction rate. However, it requires significant amount time choose best parameters achieving accuracy prediction. In summary, are applicable at regional level enhance hazards.

Language: Английский

---

Enhanced U-Net++ for Improved Semantic Segmentation in Landslide Detection

Sensors, Journal Year: 2025, Volume and Issue: 25(9), P. 2670 - 2670

Published: April 23, 2025

Landslide detection and segmentation are critical for disaster risk assessment management. However, achieving accurate remains challenging due to the complex nature of landslide terrains limited availability high-quality labeled datasets. This paper proposes an enhanced U-Net++ model semantic landslides in Wenchuan region using CAS Dataset. The proposed integrates multi-scale feature extraction attention mechanisms enhance accuracy robustness. experimental results demonstrate that ASK-UNet++ outperforms traditional methods, a mean intersection over union (mIoU) 97.53%, Dice coefficient 98.27%, overall 96.04%. These findings highlight potential approach improving monitoring response strategies.

Language: Английский

---

Public Administration in an Age of Polycrises: Multi-nodal Governance Approaches in Some South East Asian Countries

Published: Jan. 1, 2025

Language: Английский

---

Surface–subsurface characterization via interfaced geophysical–geotechnical and optimized regression modeling

Modeling Earth Systems and Environment, Journal Year: 2024, Volume and Issue: 10(4), P. 5121 - 5143

Published: June 13, 2024

Language: Английский

---