A hybrid machine learning modelling for optimization of flood susceptibility mapping in the eastern Mediterranean DOI
Hazem Ghassan Abdo, Sahar Mohammed Richi, Saeed Alqadhi

et al.

Natural Hazards, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 23, 2024

Language: Английский

Advanced integration of ensemble learning and MT-InSAR for enhanced slow-moving landslide susceptibility zoning DOI
Taorui Zeng, Liyang Wu, Yuichi S. Hayakawa

et al.

Engineering Geology, Journal Year: 2024, Volume and Issue: 331, P. 107436 - 107436

Published: Feb. 9, 2024

Language: Английский

Citations

25
Exploring risk factors and their differences on suicidal ideation and suicide attempts among depressed adolescents based on decision tree model DOI
Yang Wang, J Y Liu, Siyu Chen

et al.

Journal of Affective Disorders, Journal Year: 2024, Volume and Issue: 352, P. 87 - 100

Published: Feb. 13, 2024

Language: Английский

Citations

5
Deformation Mechanisms and Rainfall Lag Effects of Deep-Seated Ancient Landslides in High-Mountain Regions: A Case Study of the Zhongxinrong Landslide, Upper Jinsha River DOI Creative Commons
Xue Li, Changbao Guo, Wenkai Chen

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(4), P. 687 - 687

Published: Feb. 18, 2025

In high-mountain canyon regions, many settlements are located on large, deep-seated ancient landslides. The deformation characteristics, triggering mechanisms, and long-term developmental trends of these landslides significantly impact the safety stability communities. However, mechanism under influence human engineering activities remains unclear. SBAS-InSAR (Small Baseline Subset-Interferometric Synthetic Aperture Radar) technology, UAV LiDAR, field surveys were utilized in this study to identify a large landslide upper Jinsha River Basin: Zhongxinrong landslide. It extends approximately 1220 m length, with vertical displacement around 552 m. average thickness mass ranges from 15.0 35.0 m, total volume is estimated be between 1.48 × 107 m3 3.46 m3. primarily driven by combination natural anthropogenic factors, leading formation two distinct accumulation bodies, each exhibiting unique characteristics. Accumulation Body II-1 predominantly influenced rainfall road operation, resulting significant part contrast, II-2 mainly affected river erosion at front edge, causing creeping tensile toe. Detailed analysis reveals marked acceleration following events when cumulative over 15-day period exceeds 120 mm. lag time peak 2 28 days. Furthermore, high-elevation area consistently exhibits slower response compared lower zones. These findings highlight importance both factors risk assessment provide valuable insights for prevention strategies, particularly regions similar geological socio-environmental conditions.

Language: Английский

Citations

0
Dynamic Landslide Susceptibility Mapping on Time-Series InSAR and Explainable Machine Learning: A Case Study at Wushan in the Three Gorges Reservoir Area, China DOI

NaLin,

Kai Ding,

Libing Tan

et al.

Advances in Space Research, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
Research on Optimized Selection of Insar Interferometric Image Pairs Based on Graph Theory DOI
Wenfei Xi,

Tingting Jin,

Junqi Guo

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Multi-criteria analysis and geospatial applications-based mapping flood vulnerable areas: a case study from the eastern Mediterranean DOI
Hazem Ghassan Abdo, Taorui Zeng,

Mohammed J. Alshayeb

et al.

Natural Hazards, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 10, 2024

Language: Английский

Citations

3
国土地理院の時系列干渉SAR画像に基づく北海道の活動性地すべり地形データマップの作成と精度検証 DOI Open Access

USAMI Seiya

E-journal GEO, Journal Year: 2024, Volume and Issue: 19(1), P. 132 - 144

Published: Jan. 1, 2024

国土地理院が日本全国の時系列干渉SAR画像(TS-InSAR画像)を公開したことにより,活動性地すべり地形(ALs)の所在の把握が期待されている.本稿では,TS-InSAR画像に基づき作成した「北海道の活動性地すべり地形データマップ(HoLsDM v1.2)」の概要とそのALs検出精度について述べる.HoLsDM v1.2により,道内に少なくとも345カ所のALsが存在し,その分布は地域性を持つことが示された.一方,HoLsDM v1.2では面積が2.43 ha未満のALs,地すべりの変動方向とALOS-2の衛星視線方向とのなす角が大きいALs,地すべり地内の変動量の差が11.8 cm以上のALsを検出できていない可能性が示された.しかし,これらの特性を理解して活用すれば,HoLsDM v1.2は地すべり災害リスクの評価や地すべりが発生する地形・地質条件の理解促進に有効だと考えられる.

Citations

1
Enhancing landslide inventory mapping through Multi-SAR image analysis: a comprehensive examination of current landslide zones DOI
Fatih Kadı, Ekrem Saralıoğlu

Acta Geodaetica et Geophysica, Journal Year: 2024, Volume and Issue: 59(4), P. 509 - 528

Published: Aug. 19, 2024

Language: Английский

Citations

0
Spatio-temporal forecasting of landslide hazard in Chongqing National Transmission Protection Regions, China DOI Creative Commons

Bijing Jin,

Shuhao Liu, Taorui Zeng

et al.

International Journal of Digital Earth, Journal Year: 2024, Volume and Issue: 17(1)

Published: Aug. 20, 2024

Previous studies on landslide susceptibility (LS) and hazard (LH) assessments have overlooked a crucial measure for evaluating validation effectiveness, which involves the use of post-temporal inventories instead solely relying historical data. Therefore, this study constructed regional LH prediction framework at different timescales using data from 2002 to 2021. Firstly, based updated conditioning factors, datasets modelling were built various periods. Then, performances traditional ma chine learning, ensemble deep learning models compared. Finally, multi-period rainfall results used in innovative forecasting. Our show that model (random forest) has stronger generalisation ability time periods, with all Area Under Curve (AUC) values exceeding 0.9. The erosion intensity can effectively forecast LH, shortened timescale improve accuracy At very high level, percentage landslides increased 25.23% 42.86%. This comprehensively explores spatio-temporal dynamic changes accurately identifying areas posing threats National Transmission Line Protection Regions (NTLPR).

Language: Английский

Citations

0
An Innovative Ensemble Approach of Deep Learning Models with Soft Computing Techniques for GIS-based drought-zonation mapping in Rarh Region, West Bengal DOI Creative Commons

Gopal Chowdhury,

Sayantan Mandal, Ashis Kumar Saha

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 3, 2024

Abstract Drought is a complex natural disaster impacting ecosystems and communities, making its identification crucial for mitigation efforts. This study aimed to assess drought scenarios in the Rarh Region of West Bengal at 3-, 6-, 12-month intervals. The region an amalgamation plateau Gangetic delta, facing decreasing rainfall trend, particularly Birbhum Purba Bardhhaman districts. Bardhhaman, known good track rice production, now severe drought, which concerning matter. assessed their collinearity by evaluating 27 assessment variables grouped into meteorological, agricultural, hydrological, socio-economic facets. A Multi-Layer Perceptron Neural Network (MLP NN) was applied as benchmark, followed DenseNet neural network. Finally, Hybrid Deep Learning Ensemble model developed compare precision create drought-prone map. Results indicated that, on average, 26.66% highly 3-month interval, 20% 6 months, 25% 12 months. models were validated using ROC-AUC, Standard Error, Asymptotic Significance. showed highest accuracy, achieving 94.2%, 94.3%, 95.3% intervals, respectively. research provides valuable insights policymakers address increasing risks region.

Language: Английский

Citations

0