☆ 4.7 Article

Mapping landslides through a temporal lens: an insight toward multi-temporal landslide mapping using the u-net deep learning model

GISCIENCE & REMOTE SENSING (2023)

Related references

Note: Only part of the references are listed.

Article Geosciences, Multidisciplinary

Transfer learning improves landslide susceptibility assessment

Haojie Wang et al.

Summary: This study proposes a transfer learning-based approach for landslide susceptibility assessment, which improves prediction accuracy in data-limited regions by training models in data-rich regions and transferring knowledge through model transfer and fine-tuning.

GONDWANA RESEARCH (2023)

Add to Collection

Article Engineering, Geological

Landslide detection in the Himalayas using machine learning algorithms and U-Net

Sansar Raj Meena et al.

Summary: Event-based landslide inventories are crucial for understanding the causal relationship between triggering events and landslides, and for subsequent risk studies. This study explores the potential of U-Net and machine learning approaches for automated landslide detection in the Himalayas. The results suggest that the U-Net model performs slightly better than other methods in landslide detection.

LANDSLIDES (2022)

Add to Collection

Article Environmental Sciences

Rapid Mapping of Landslides on SAR Data by Attention U-Net

Lorenzo Nava et al.

Summary: Multiple landslide events are common worldwide and can cause significant damage. This study explores the potential of SAR data combined with other data sources to map landslides, even under cloud cover. The findings demonstrate that the combination of SAR data and DL algorithms can help quickly map landslides, even during storms and under deep cloud cover.

REMOTE SENSING (2022)

Add to Collection

Article Environmental Sciences

Automatic Detection of Coseismic Landslides Using a New Transformer Method

Xiaochuan Tang et al.

Summary: This article introduces the research on landslide detection using Transformer. By building a new dataset and using the Transformer-based semantic segmentation model SegFormer, the experiments prove that Transformer outperforms CNN in landslide detection.

REMOTE SENSING (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Rapidly Evolving Controls of Landslides After a Strong Earthquake and Implications for Hazard Assessments

Xuanmei Fan et al.

Summary: Strong earthquakes on mountain slopes can produce a large number of unconsolidated deposits that are prone to remobilization by aftershocks and rainstorms. This study reveals that seismic-related variables decrease in prediction capability with time, while hydro-topographic parameters become more important and predominant within a decade, highlighting the need for updated hazard assessment models in postearthquake landscapes.

GEOPHYSICAL RESEARCH LETTERS (2021)

Add to Collection

Article Geosciences, Multidisciplinary

Landslide Geometry Reveals its Trigger

Kamal Rana et al.

Summary: This study proposes a method to classify the triggering mechanisms of landslides in existing inventories, enabling their use in landslide hazard modeling by utilizing machine-learning classifier random forest with geometric characteristics as feature space. Application of the method to six landslide inventories showed high accuracy, and it was demonstrated that landslides with identical trigger mechanisms exhibit similar geometric properties.

GEOPHYSICAL RESEARCH LETTERS (2021)

Add to Collection

Article Engineering, Geological

Rapid mapping of landslides in the Western Ghats (India) triggered by 2018 extreme monsoon rainfall using a deep learning approach

Sansar Raj Meena et al.

Summary: This study utilized deep learning convolution neural networks with topographical data to map rainfall-induced landslides in the Kodagu district of India. By combining spectral information with slope data, the model achieved higher overall accuracy and reduced false positives, aiding in accurately identifying landslide areas. The methodology can be applied to other landslide-prone regions for hazard mitigation support.

LANDSLIDES (2021)

Add to Collection

Article Geochemistry & Geophysics

GAN-Based Siamese Framework for Landslide Inventory Mapping Using Bi-Temporal Optical Remote Sensing Images

Bo Fang et al.

Summary: This letter proposes a new framework for landslide inventory mapping, using a combination of generative adversarial network and Siamese neural network, with two cascaded modules for domain adaptation and landslide detection. The method is proven to efficiently and accurately produce landslide inventory maps from bi-temporal remote sensing images.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2021)

Add to Collection

Article Environmental Sciences

Semi-Supervised Multi-Temporal Deep Representation Fusion Network for Landslide Mapping from Aerial Orthophotos

Xiaokang Zhang et al.

Summary: By utilizing the deep learning model SMDRF-Net, which combines unsupervised learning and attention mechanisms, the reliable and efficient identification of landslides in multi-temporal remote sensing images has been achieved, thus enhancing the feature representation capability of the network.

REMOTE SENSING (2021)

Add to Collection

Article Multidisciplinary Sciences

30-year record of Himalaya mass-wasting reveals landscape perturbations by extreme events

Joshua N. Jones et al.

Summary: This study quantifies the magnitudes of mass-wasting caused by the Asia Summer Monsoon, extreme rainfall, and earthquakes in the Nepal Himalaya, finding that rainfall events and earthquakes may perturb mass-wasting to a much greater extent than expected from monsoon alone.

NATURE COMMUNICATIONS (2021)

Add to Collection

Review Oncology

Transfer Learning in Breast Cancer Diagnoses via Ultrasound Imaging

Gelan Ayana et al.

Summary: Transfer learning is crucial in medical image analyses, but obtaining sufficient training datasets can be challenging. This review focuses on the application of transfer learning in ultrasound breast imaging for breast cancer detection, providing insights into existing methods and potential areas for improvement through further research. Transfer learning approaches, pre-processing, pre-training models, and CNN models are discussed, with comparisons of different works and discussions on challenges and future prospects.

CANCERS (2021)

Add to Collection

Article Multidisciplinary Sciences

Assessment of earthquake-induced landslide inventories and susceptibility maps using slope unit-based logistic regression and geospatial statistics

Badal Pokharel et al.

Summary: This study assessed five landslide inventories prepared by different authors after the 2015 Gorkha earthquake, revealing substantial discrepancies among the mapped landslides and notable differences in spatial patterns of landslide-prone areas in susceptibility maps.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Multidisciplinary Sciences

Deep learning-based landslide susceptibility mapping

Mohammad Azarafza et al.

Summary: The study developed a CNN-DNN model for landslide susceptibility mapping in Isfahan province, demonstrating high prediction accuracy compared to benchmark machine learning techniques. The model revealed high-susceptibility areas in the west and southwest of Isfahan province, proving useful for landslide risk management and land use planning.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Multidisciplinary Sciences

A new strategy to map landslides with a generalized convolutional neural network

Nikhil Prakash et al.

Summary: This research proposes a novel strategy for training convolutional neural networks (CNN) by combining inventories from different regions to build a generalized model that can be directly applied to new, unexplored areas. The study demonstrates that CNNs trained on combined inventories have better generalization performance when mapping landslides in new unseen regions.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Multidisciplinary Sciences

A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)

Omid Ghorbanzadeh et al.

Summary: Earthquakes and heavy rainfalls are leading causes of landslides globally, and deep learning approaches like U-Net and ResU-Net have shown promising results in automatic landslide detection using high-resolution satellite imagery. This study successfully applied these algorithms to freely available data and achieved high detection performance in three case study areas.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Geosciences, Multidisciplinary

New Insight into Post-seismic Landslide Evolution Processes in the Tropics

Hakan Tanyas et al.

Summary: Earthquakes not only increase landslide susceptibility during the post-seismic phase, but also have limited observations regarding these processes under tropical conditions. The study shows that landslide susceptibility returns to pre-seismic levels in less than a year in the study areas considered.

FRONTIERS IN EARTH SCIENCE (2021)

Add to Collection

Article Environmental Sciences

Changing significance of landslide Hazard and risk after the 2015 Mw 7.8 Gorkha, Nepal Earthquake

Nick Rosser et al.

Summary: The 2015 Gorkha earthquake in Nepal triggered over 20,000 landslides, with ongoing geological changes leading to even more landslides and significant impact on the local residents. Through detailed monitoring and modeling, it was found that landslide hazard was higher in November 2019 compared to immediately after the earthquake, highlighting the need for continued attention and risk management in the region.

PROGRESS IN DISASTER SCIENCE (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Landslide Mapping Using Two Main Deep-Learning Convolution Neural Network Streams Combined by the Dempster-Shafer Model

Omid Ghorbanzadeh et al.

Summary: This study investigated the use of deep learning CNN technology combined with optical data and topographic factors for earthquake-induced landslide mapping. By training CNN streams with different datasets and combining the results, as well as comparing the mapping results through mean intersection-over-union, it was found that using spectral information and slope topographic factors can improve the mapping accuracy. The improvement of the mean intersection-over-union ranged from approximately zero to more than 17%, and the Dempster-Shafer model was effective in combining results from different scenarios.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2021)

Add to Collection

Article Geography, Physical

Incorporating the effect of ALS-derived DEM uncertainty for quantifying changes due to the landslide in 2011, Mt. Umyeon, Seoul

Mi-Kyeong Kim et al.

GISCIENCE & REMOTE SENSING (2020)

Add to Collection

Article Environmental Sciences

Mapping Landslides on EO Data: Performance of Deep Learning Models vs. Traditional Machine Learning Models

Nikhil Prakash et al.

REMOTE SENSING (2020)

Add to Collection

Article Environmental Sciences

Deep Learning Segmentation and Classification for Urban Village Using a Worldview Satellite Image Based on U-Net

Zhuokun Pan et al.

REMOTE SENSING (2020)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Faulty Requirements Made Valuable: On the Role of Data Quality in Deep Learning

Harshitha Challa et al.

2020 IEEE SEVENTH INTERNATIONAL WORKSHOP ON ARTIFICIAL INTELLIGENCE FOR REQUIREMENTS ENGINEERING (AIRE 2020) (2020)

Add to Collection

Article Geography, Physical

Landslide susceptibility mapping by remote sensing and geomorphological data: case studies on the Sorrentina Peninsula (Southern Italy)

Claudia Spinetti et al.

GISCIENCE & REMOTE SENSING (2019)

Add to Collection

Article Environmental Sciences

Evaluation of Different Machine Learning Methods and Deep-Learning Convolutional Neural Networks for Landslide Detection

Omid Ghorbanzadeh et al.

REMOTE SENSING (2019)

Add to Collection

Article Computer Science, Theory & Methods

A survey on Image Data Augmentation for Deep Learning

Connor Shorten et al.

JOURNAL OF BIG DATA (2019)

Add to Collection

Article Geosciences, Multidisciplinary

Two multi-temporal datasets that track the enhanced landsliding after the 2008 Wenchuan earthquake

Xuanmei Fan et al.

EARTH SYSTEM SCIENCE DATA (2019)

Add to Collection

Article Geosciences, Multidisciplinary

Comparison of Earthquake-Triggered Landslide Inventories: A Case Study of the 2015 Gorkha Earthquake, Nepal

Sansar Raj Meena et al.

GEOSCIENCES (2019)

Add to Collection

Article Geosciences, Multidisciplinary

Topographic and Seismic Constraints on the Vulnerability of Himalayan Hydropower

Wolfgang Schwanghart et al.

GEOPHYSICAL RESEARCH LETTERS (2018)

Add to Collection

Article Engineering, Geological

Spatio-temporal evolution of mass wasting after the 2008 Mw 7.9 Wenchuan earthquake revealed by a detailed multi-temporal inventory

Xuanmei Fan et al.

LANDSLIDES (2018)

Add to Collection

Article Geosciences, Multidisciplinary

Presentation and Analysis of a Worldwide Database of Earthquake-Induced Landslide Inventories

Hakan Tanyas et al.

JOURNAL OF GEOPHYSICAL RESEARCH-EARTH SURFACE (2017)

Add to Collection

Article Geosciences, Multidisciplinary

Analysing post-earthquake landslide activity using multi-temporal landslide inventories near the epicentral area of the 2008 Wenchuan earthquake

Chenxiao Tang et al.

NATURAL HAZARDS AND EARTH SYSTEM SCIENCES (2016)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Application of an evidential belief function model in landslide susceptibility mapping

Omar F. Althuwaynee et al.

COMPUTERS & GEOSCIENCES (2012)

Add to Collection

Article Geosciences, Multidisciplinary

Landslide inventory maps: New tools for an old problem

Fausto Guzzetti et al.

EARTH-SCIENCE REVIEWS (2012)

Add to Collection

Article Computer Science, Artificial Intelligence

A Survey on Transfer Learning

Sinno Jialin Pan et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2010)

Add to Collection

Article Geography, Physical

Estimating temporal probability for landslide initiation along transportation routes based on rainfall thresholds

Pankaj Jaiswal et al.

GEOMORPHOLOGY (2009)

Add to Collection

Article Computer Science, Artificial Intelligence

CLASSIFICATION OF IMBALANCED DATA: A REVIEW

Yanmin Sun et al.

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE (2009)

Add to Collection

Article Geography, Physical

Probabilistic landslide hazard assessment at the basin scale

F Guzzetti et al.

GEOMORPHOLOGY (2005)

Add to Collection

Article Engineering, Geological

Landslide hazard and risk mapping at catchment scale in the Arno River basin

F Catani et al.

LANDSLIDES (2005)

Add to Collection

Article Environmental Sciences

Remote sensing of landslides: An analysis of the potential contribution to geo-spatial systems for hazard assessment in mountainous environments

G Metternicht et al.

REMOTE SENSING OF ENVIRONMENT (2005)

Add to Collection

© Peeref 2019-2024. All rights reserved.