Pixel Based Landslide Identification Using Landsat 8 and GEE

Singh, Prachi; Maurya, Vipin Kumar; Dwivedi, Ramji

doi:10.1109/igarss47720.2021.9553358

Cited by 10 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, all these aspects were carefully investigated and addressed to achieve the best possible landslide detection accuracy in GEE while using ready-made datasets in GEE. Comparisons with existing approaches [19,29,[31][32][33][34][38][39][40][41][42][44][45][46][47][48] demonstrated superior performance of ML-LaDeCORsat of at least 10% higher detection accuracy.…”

Section: Discussionmentioning

confidence: 92%

“…A rise in published journal articles related to GEE over the last three years highlights the increased popularity of GEE, with L8 and S2 being the most widely used earth observation satellite sensors, and articles based on Random Forest and water resources most often reported [54]. Several existing landslide detection methods have been implemented in GEE [19,29,39,[42][43][44][45][46]55]. However, only Handwerger et al [19] provide a shared GEE script that allows replication and potential adjustment of the script to other landslide events.…”

Section: Cloud-based Processing Google Earth Engine and Machine Learningmentioning

confidence: 99%

“…In each case, ML-LaDeCORsat outperformed all existing methods. The work of [44] utilizing a supervised classification applied to four conditioning factors (NDWIpost, NDVIpost, DEM, and slope) was identified as the best-performing existing method, but it achieved, taking the JPN case study as an example, 5% lower BA and 10% lower Kappa than ML-LaDeCORsat. Detailed accuracy assessment can be found in Supplementary Table S3 until Table S6.…”

Section: Landslide Detection Accuraciesmentioning

confidence: 99%

See 2 more Smart Citations

Detecting Coseismic Landslides in GEE Using Machine Learning Algorithms on Combined Optical and Radar Imagery

Peters,

Liu,

Keppel

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Landslides, resulting from disturbances in slope equilibrium, pose a significant threat to landscapes, infrastructure, and human life. Triggered by factors such as intense precipitation, seismic activities, or volcanic eruptions, these events can cause extensive damage and endanger nearby communities. A comprehensive understanding of landslide characteristics, including spatio-temporal patterns, dimensions, and morphology, is vital for effective landslide disaster management. Existing remote sensing approaches mostly use either optical or synthetic aperture radar sensors. Integrating information from both these types of sensors promises greater accuracy for identifying and locating landslides. This study proposes a novel approach, the ML-LaDeCORsat (Machine Learning-based coseismic Landslide Detection using Combined Optical and Radar Satellite Imagery), that integrates freely available Sentinel-1, Palsar-2, and Sentinel-2 imagery data in Google Earth Engine (GEE). The approach also integrates relevant spectral indices and suitable bands used in a machine learning-based classification of coseismic landslides. The approach includes a robust and reproducible training and validation strategy and allows one to choose between five classifiers (CART, Random Forest, GTB, SVM, and Naive Bayes). Using landslides from four different earthquake case studies, we demonstrate the superiority of our approach over existing solutions in coseismic landslide identification and localization, providing a GTB-based detection accuracy of 87–92%. ML-LaDeCORsat can be adapted to other landslide events (GEE script is provided). Transfer learning experiments proved that our model can be applied to other coseismic landslide events without the need for additional training data. Our novel approach therefore facilitates quick and reliable identification of coseismic landslides, highlighting its potential to contribute towards more effective disaster management.

show abstract

Section: Discussionmentioning

confidence: 92%

Section: Cloud-based Processing Google Earth Engine and Machine Learningmentioning

confidence: 99%

Section: Landslide Detection Accuraciesmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Coseismic Landslides in GEE Using Machine Learning Algorithms on Combined Optical and Radar Imagery

Peters,

Liu,

Keppel

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…It requires experts to comprehensively utilize image features such as object shape, texture, and spectrum, and then combine some non-remote sensing data for analysis and reasoning. This method consumes a lot of time and energy, and has limitations such as large errors and low efficiency (Hölbling et al, 2014;Moosavi et al, 2014;Wang et al, 2017;Zhao et al, 2017;Singh et al, 2021). Pixel-based methods usually uses binarization algorithm to determine whether a pixel of the image belong to the landslide (Li et al, 2014;Han et al, 2019).…”

Section: Open Access Edited Bymentioning

confidence: 99%

A novel Dynahead-Yolo neural network for the detection of landslides with variable proportions using remote sensing images

Han

FANG²,

Li³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Efficient and automatic landslide detection solutions are beneficial for regional hazard mitigation. At present, scholars have carried out landslide detection based on deep learning. However, continuous improvement regarding the accuracy of landslide detection with better feature extraction of landslides remain an essential issue, especially small-proportion landslides in the remote sensing images are difficult to identify up to date. To address this issue, we propose a detection model, the so-called Dynahead-Yolo which is designed by combining unifying scale-aware, space-aware, and task-aware attention mechanisms into the YOLOv3 framework. The proposed method focuses on the detailed features of landslide images with variable proportions, improving the ability to decode landslides in complex background environments. We determine the most efficient cascade order of the three modules and compare previous detection networks based on randomly generated prediction sets from the three study areas. Compared with the traditional YOLOv3, the detection rate of Dynahead-Yolo in small-proportion landslides and complex background landslides is increased by 13.67% and 14.12%, respectively.

show abstract

“…Landslide identification has always been an important direction in geological hazard research [1]. With the rapid development of remote sensing technology, the interpretation of landslides has gradually shifted from field census and visual interpretation to humancomputer interactive interpretation [2]. Remote sensing technology has the advantages of short time consumption, labor saving, large area and all-round observation of landslides in landslide hazard identification.…”

Section: Introductionmentioning

confidence: 99%

Indicative Effect of Excess Topography on Potential Risk Location of Giant Ancient Landslides—A Case Study in Lengqu River Section

Wang

Bai

2023

Applied Sciences

View full text Add to dashboard Cite

In order to identify giant ancient landslides more effectively and to quantify the risk of giant ancient landslides, this study takes a Lengqu River section located on the Qinghai–Tibet Plateau as an example and then uses the red relief image map (RRIM) method to enhance the digital elevation model (DEM) for topographic 2D visualization to identify giant ancient landslides. Then, the relationships between giant ancient landslides (GALs), resurgent GALs, the deposition of inactive GALs and the excess topography of hillslopes under 30° threshold are analyzed separately. A total of 54 GALs are identified at last by using the RRIM method; 77.75% of GALs are still located on excess topography, 68.38% of resurgent GALs occurred on excess topography, and 62.21% of the deposition of inactive GALs are on non-excess topography. The RRIM method provides a new way to identify giant ancient landslides. The excess topography provides an indication of the risk of new landslides through the destructive effect of GALs on the threshold hillslope, and the preliminary investigation of the quantitative relationship between the resurrection of GALs and excess topography also shows that there is a certain pattern between the resurrection of GALs and the excess topography under the natural state, so the excess topography has a certain indication of the generation of new landslides and secondary resurrection at the original GAL positions.

show abstract

Pixel Based Landslide Identification Using Landsat 8 and GEE

Cited by 10 publications

References 8 publications

Detecting Coseismic Landslides in GEE Using Machine Learning Algorithms on Combined Optical and Radar Imagery

Detecting Coseismic Landslides in GEE Using Machine Learning Algorithms on Combined Optical and Radar Imagery

A novel Dynahead-Yolo neural network for the detection of landslides with variable proportions using remote sensing images

Indicative Effect of Excess Topography on Potential Risk Location of Giant Ancient Landslides—A Case Study in Lengqu River Section

Contact Info

Product

Resources

About