Constructing a Large-scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates

Nagendra, S.; Manjunatha, S.; Kifer, Daniel; pei, te; li, weixin; Lawson, Kathryn; Nguyen, Hien Van; Qiu, Tong; Tran, Sarah

doi:10.36227/techrxiv.14365502.v1

Cited by 2 publications

(2 citation statements)

References 19 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) Deep Learning for Landslide Mapping: DL has been already used for landslide mapping [11], [26], [41]- [47]. Deep learning techniques do not require hand-crafted features as they perform automatic feature engineering directly from satellite imagery.…”

Section: A Landslide Mappingmentioning

confidence: 99%

Constructing a Large-Scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates

Nagendra

Kifer

Mirus

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Preparation and mitigation efforts for widespread landslide hazards can be aided by a large-scale, well-labeled landslide inventory with high location accuracy. Recent smallscale studies for pixel-wise labeling of potential landslide areas in remotely-sensed images using deep learning (DL) showed potential but were based on data from very small, homogeneous regions with unproven model transferability. In this paper we consider a more realistic and practical setting for large-scale heterogeneous landslide data collection and DL-based labeling. In this setting, remotely sensed images are collected sequentially in temporal batches, where each batch focuses on images from a particular ecoregion, but different batches can focus on different ecoregions with distinct landscape characteristics. For such a scenario, we study the following questions: (1) How well do DL models trained in homogeneous regions perform when they are transferred to different ecoregions, (2) Does increasing the spatial coverage in the data improve model performance in a given ecoregion (even when the extra data do not come from the ecoregion), and (3) Can a landslide pixel labeling model be incrementally updated with new data, but without access to the old data and without losing performance on the old data (so that researchers can share models obtained from proprietary datasets)? We address these questions by extending the Learning without Forgetting framework, which is used for incremental training of image classification models, to the setting of incremental training of semantic segmentation models (e.g., identifying all landslide pixels in an image). We call the resulting extension Task-Specific Model Updates (TSMU). TSMU semantic segmentation framework consists of an encoder shared by all ecoregions to capture the similarities between them, and ecoregion-specific decoders to capture the nuances of each ecoregion. This framework is continually updated using a threestage training procedure for each new addition of an ecoregion without having to revisit data from old ecoregions and without losing performance on them.A national compilation of landslide inventories by the U.S. Geological Survey (USGS) was used to develop database for this study. We focused on space-visible landslides within four ecoregions. These landslides were manually identified and labeled using high-resolution satellite images from Google Earth. The database contains 496 labeled and georeferenced pre-event/postevent images pairs, which corresponding to 1,918 landslide records in the USGS landslide inventory. Using the TSMU framework, we conduct extensive experiments on four ecoregions in the United States to address the aforementioned questions.

show abstract

Section: A Landslide Mappingmentioning

confidence: 99%

Constructing a Large-Scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates

Nagendra

Kifer

Mirus

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…2) Deep Learning based Approach: Deep learning (DL) has been already used for landslide mapping [11], [25], [34]- [40]. Deep learning techniques do not require hand-crafted features as they perform automatic feature engineering directly from satellite imagery.…”

Section: A Landslide Mappingmentioning

confidence: 99%

Constructing a Large-scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates

Nagendra¹,

Manjunatha²,

Kifer³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

In this article, we consider the scenario where remotely sensed images are collected sequentially in temporal batches, where each batch focuses on images from a particular ecoregion, but different batches can focus on different ecoregions with distinct landscape characteristics. For such a scenario, we study the following questions: (1) How well do DL models trained in homogeneous regions perform when they are transferred to different ecoregions, (2) Does increasing the spatial coverage in the data improve model performance in a given ecoregion (even when the extra data do not come from the ecoregion), and (3) Can a landslide pixel labelling model be incrementally updated with new data, but without access to the old data and without losing performance on the old data (so that researchers can share models obtained from proprietary datasets)? We address these questions by a framework called Task-Specific Model Updates (TSMU). The goal of this framework is to continually update a (landslide) semantic segmentation model with data from new ecoregions without having to revisit data from old ecoregions and without losing performance on them. We conduct extensive experiments on four ecoregions in the United States to address the above questions and establish that data from other ecoregions can help improve the model's performance on the original ecoregion. In other words, if one has an ecoregion of interest, one could still collect data both inside and outside that region to improve model performance on the ecoregion of interest. Furthermore, if one has many ecoregions of interest, data from all of them are needed.<br>

show abstract

Constructing a Large-scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates

Cited by 2 publications

References 19 publications

Constructing a Large-Scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates

Constructing a Large-Scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates

Constructing a Large-scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates

Contact Info

Product

Resources

About