Geology topics

Jung-Kuan Liu

Publications and source records attributed to Jung-Kuan Liu.

5 recordsLinked to original sources

USGS2025

Multi-temporal surface water mapping with high-resolution elevation and image data through weakly supervised deep learning

Monitoring the extent of surface water features (hydrography), accurately storing them in databases, and representing them on topographic maps are essential for various applications such as navigation and policy-making for legislative boundaries and permitting. In this context, hydrographic data includes features that generally have water present or image data showing signs that water is forming a terrain channel, and which would be included in 1:24,000 or larger scale topographic maps. In addition, reliable hydrographic data play a critical role to help manage environmental risks such as droughts, floods, fires, and landslides, as well as monitoring biological resources and pollutants. Inaccuracies in hydrography data can lead to modelling inaccuracies, resulting in economic, social, and environmental risks. However, generating sufficiently accurate high-resolution (HR) hydrography and terrain data for these purposes remains a substantial challenge primarily because of complex surface water dynamics and data handling limitations.

Alaska↗

USGS2024

Evaluation of classified ground points from National Agriculture Imagery program photogrammetrically derived point clouds

Studies have shown that digital surface models and point clouds generated by the United States Department of Agriculture’s National Agriculture Imagery Program (NAIP) can measure basic forest parameters such as canopy height. However, all measured forest parameters from these studies are evaluated using the differences between NAIP digital surface models (DSMs) and available lidar digital terrain models (DTMs). A survey of NAIP point cloud classification and related ground point-generated DTMs has not yet been undertaken. This study applies a Support Vector Machine (SVM) to classifying ground and nonground points from NAIP point clouds for test sites in Wyoming and Arizona, USA. Light detection and ranging (lidar) data from the U.S. Geological Survey 3D Elevation Program (3DEP) are used to validate the classified NAIP ground points and their corresponding DTMs. Comparing height differences between filtered NAIP ground points and 3DEP ground points, the SVM classifier’s results show that the vertical root mean square error value is 1.87 m and 1.69 m for the Wyoming and Arizona sites, respectively. If NAIP point clouds were continuously measured, the resulting availability of medium-resolution DTMs would benefit the application of multitemporal forest health monitoring and DTM generation.

Remote Sensing Letters↗

USGS2024

Remote sensing-based 3D assessment of landslides: A review of the data, methods, and applications

Remote sensing (RS) techniques are essential for studying hazardous landslide events because they capture information and monitor sites at scale. They enable analyzing causes and impacts of ongoing events for disaster management. There has been a plethora of work in the literature mostly discussing (1) applications to detect, monitor, and predict landslides using various instruments and image analysis techniques, (2) methodological mechanics in using optical and microwave sensing, and (3) quantification of surface geological and geotechnical changes using 2D images. Recently, studies have shown that the degree of hazard is mostly influenced by speed, type, and volume of surface deformation. Despite available techniques to process lidar and image/radar-derived 3D geometry, prior works mostly focus on using 2D images, which generally lack details on the 3D aspects of assessment. Thus, assessing the 3D geometry of terrain using elevation/depth information is crucial to determine its cover, geometry, and 3D displacements. In this review, we focus on 3D landslide analysis using RS data. We include (1) a discussion on sources, types, benefits, and limitations of 3D data, (2) the recent processing methods, including conventional, fusion-based, and artificial intelligence (AI)-based methods, and (3) the latest applications.

Remote Sensing↗

USGS2024

Automated deep learning-based point cloud classification on USGS 3DEP lidar data using transformer

The goal of the U.S. Geological Survey’s (USGS) 3D Elevation Program (3DEP) is to facilitate the acquisition of nationwide lidar data. Although data meet USGS lidar specifications, some point cloud tiles include noisy and incorrectly classified points. The enhanced accuracy of classified point clouds can improve support for many downstream applications such as hydrologic analysis, urban planning, and forest management. Despite noisy and incorrectly classified points, the current 3DEP classification specifications result in data that can be useful for Digital Terrain Model (DTM) extraction; however, the quality of the classification application can be improved to match state-of-the-art capabilities. Deep Learning (DL)-based approaches have been developed with outstanding performance for point cloud classification. This study will utilize the proven DL technologies to prepare for developing a user-friendly open-source toolkit that would automate classification to refine and enrich the results of existing and future 3DEP data.

Conference Paper↗

USGS2024

Assessing the utility of uncrewed aerial system photogrammetrically derived point clouds for land cover classification in the Alaska North Slope

Uncrewed aerial systems (UASs) have been used to collect “pseudo field plot” data in the form of large-scale stereo imagery to supplement and bolster direct field observations to monitor areas in Alaska. These data supplement field data that is difficult to collect in such a vast landscape with a relatively short field season. Dense photogrammetrically derived point clouds are created and are facilitated to extract land cover data using a support vector machine (SVM) classifier in this study. We test our approach using point clouds derived from 1-cm stereo imagery of plots in the Alaska North Slope region and compare the results to field observations. The results show that the overall accuracy of six land cover classes (bare soil, shrub, grass, forb/herb, rock, and litter) is 96.8% from classified patches. Shrub had the highest accuracy (>99%) and forb/herb achieved the lowest (<48%). This study reveals that the approach could be used as reference data to check field observations in remote areas.

Alaska↗