InSAR-YOLOv8 for wide-area landslide detection in InSAR measurements

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 10, 2025

InSAR monitoring technology is widely used in investigating landslide hazards. Leveraging object detection algorithms to quickly extract information from Wide-Area measurements of great significance. Our InSAR-YOLOv8, an algorithm that automatically detects landslides measurements, addresses the low accuracy and suboptimal performance existing network models. In this method, we first design add a head specifically targeting small-scale objects. This improvement enhances model's ability features across different scales strengthens its capability detect varying sizes. We also replace original C2f module with lighter C2f_Faster process more efficiently, making model efficient. Finally, SIoU loss function replaces CIoU improve bounding box regression enhance accuracy. results show proposed achieves 97.41% mAP50, 66.47% mAP50:95, 92.06% F1 score on dataset, while reducing number parameters by 25%. Compared YOLOv8 other advanced models (YOLOvX, Faster R-CNN, etc.), our exhibits distinct advantages possesses wider range potential applications measurement for detection.

Language: Английский

---

Early Identification of Geological Hazards Along the Power Transmission Line in Weinan Based on SBAS-InSAR

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(2), P. 920 - 920

Published: Jan. 18, 2025

Landslides and ground subsidence pose significant threats to the successful construction operation of transmission line projects in Loess Plateau region. This study aims explore an accurate early identification method for geological hazards, providing support smooth project along route from Baishui County, Weinan City, Shaanxi Province Lantian Xi’an Province. Small baseline subset interferometric synthetic aperture radar (SBAS-InSAR) technology was used acquire surface deformation data area 4 February 2018 21 May 2023. The were spatially analyzed through kernel density analysis, which quickly intuitively identified 52 potential hazard points region, including eight landslides 44 subsidence. Detailed field investigations hazards confirmed accuracy results. A thorough analysis typical such as landslide No. 9 29, revealed severe deformation, posing a threat proposed project. indicates that combining InSAR, can accurately identify around lines, site selection implementation projects.

Language: Английский

---

Dynamic response and damage evolution characteristics of uniform rocky slopes with unstable rock masses based on shaking table tests

Frontiers in Earth Science, Journal Year: 2025, Volume and Issue: 13

Published: March 12, 2025

Seismic activities often trigger catastrophic events including collapses and rockfalls on rocky slopes. This research endeavors to understand the dynamic behavior damage modes in uniform slopes with unstable rock masses. To achieve this objective, paper constructs a physical model of slope mass performs triaxial loading shaking table tests. Subsequently, seismo-dynamic responses associated are scrutinized, initiation deformation mechanisms hazardous revealed. Further, we obtained marginal spectral energy evolution characteristics measurement points both bedrock. deciphers weak structural plane. The results indicate that there distinct elevation surface amplification effects within slopes, which systematically lessened increasing seismic intensity. vertical is more sensitive high seismic-induced process masses split into three stages: trailing edge tension cracking, sliding planes, complete failure plane shear capacity. It also established Hilbert spectra effectively identified containing planes.

Language: Английский

---

InSAR-based monitoring and analysis of settlement in high-filled road embankment and slope in loess region

Frontiers in Earth Science, Journal Year: 2025, Volume and Issue: 13

Published: April 28, 2025

The settlement behavior of high-filled road embankments and slopes in loess regions poses significant challenges to the safety stability engineering. Interferometric Synthetic Aperture Radar (InSAR) technique was used process Sentinel-1A satellite data from 8 April 2021, 9 May 2022. spatiotemporal distribution characteristics surface were analyzed. accuracy reliability InSAR technology results validated through comparison with actual measurement data, after completion pavement further investigated. Results indicate that most severe occurred during early post-construction phase, maximum rates reaching 32 mm/year cumulative peaking at 57 mm. These critical zones located intersection embankment slope south side slope. Following pavement, stabilized within 3 mm, indicating structural road. finite element numerical simulation showed factor 1.39, satisfying limit requirements for slopes. study demonstrated can provide an effective technical means identification engineering hazard risks regions, offering a basis monitoring, warning, scientific prevention.

Language: Английский

---