YU-EN YANG

Mr. YU-EN YANG

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 July 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
TYTeng-To Yu
Teng-To Yu
YLYen-Chun Lin
Yen-Chun Lin
SLShyh-Chin Lan
Shyh-Chin Lan
YYYU-EN YANG
YU-EN YANG
PWPei-Yun Wu
Pei-Yun Wu
JLJo-Chi Lin
Jo-Chi Lin
Locating and calculating the number of asbestos-cement corrugated roofing tiles is the first step in the demolition process. In this work, archived image cubes of Taiwan served as the fundamental data source used via machine learning approach to identify the existence of asbestos-cement corrugated roofing tiles with more than 85% accuracy. An adequate quantity of ground-truth data covering all the types of roofs via aerial hyperspectral scan was the key to success for this study. Twenty randomly picked samples from the ground-truth group were examined by X-ray refraction detection to ensure correct identification of asbestos-cement corrugated roofing tiles with remote sensing. To improve the classifying accuracy ratio, two different machine learning algorithms were applied to gather the target layers individually using the same universal training model established from 400 ground-truth samples. The agreement portions within the overlapping layers of these two approaches were labeled as the potential targets, and the pixel growth technique was performed to detect the roofing boundary and create the polygon layer with size information. Exacting images from aerial photos within the chosen polygon were compared to up-to-date Sentinel-1 images to find the temporal disagreements and remove the mismatched buildings, identified as non-asbestos roofs, from the database to reflect the actual condition of present data. This automatic matching could be easily performed by machine learning to resolve the information lag while using archived data, which is an essential issue when detecting targets with non-simultaneous acquired images over a large area. To meet the 85% kappa accuracy requirement, the recurring processes were applied to find the optimal parameters of the machine learning model. Meanwhile, this study found that the support vector machine method was easier to handle, and the convolution neuro network method offered better accuracy in automatic classification with a universal training model for vast areas. This work demonstrated a feasible approach using low-cost and low-resolution archived images to automatically detect the existence of asbestos-cement corrugated roofing tiles over large regions. The entire work was completed within 16 months for an area of 36,000 km2, and the detected number of asbestos-cement corrugated roofing tiles was more than three times the initial estimation by statistics method from two small-area field surveys.

1 November 2024 in Terrestrial, Atmospheric and Oceanic Sciences
Verified
Journal Article
Open access
PDF file
YYYU-EN YANG
YU-EN YANG
TYTeng-To Yu
Teng-To Yu
CCChun-Yuan Chen
Chun-Yuan Chen
This research introduces an effective framework for automatically detecting landslide impact areas using Google Earth Engine (GEE). The Asia–Pacific region frequently experiences earthquakes and heavy rainfall, leading to frequent landslides that cause loss of life and property. Focusing on landslide catalogues from Taiwan and Japan, the study proposes an automatic landslide detection process using a new method termed multi-bitemporal images (MBTIs), which involves the collection of accumulated changes over time. First, set the event date and collect all images before and after the event. Second, analyse the change pixels in bi-temporal images. Third, review all change pixels to determine the total amount of accumulated changes. This method includes all bi-temporal image sets in the analysis, unlike traditional methods that only use single pairs of bi-temporal images. Clouds are filtered using a pixel-based approach and machine learning techniques. The landslide areas are analysed statistically, and appropriate thresholds for automatic landslide detection are suggested. Using reproducibility, which indicates the percentage of bi-temporal images that detect vegetation loss in mountainous areas, the proposed method achieves a 99% reduction in false positives with a reproducibility requirement of 24.21%, while maintaining true positives at 66.89%. This study analyzed 28–720 bi-temporal image sets from various regions using Sentinel-2 data, revealing that subsequent landslides can be 7–293 times larger than co-seismic landslides. In comparison, subsequent landslides were found to be 3–12 times larger than rainfall-induced landslides. Additionally, the impact of earthquake event on subsequent landslides is 2.3–24.4 times greater than that of rainfall-induced event. By using GEE, the accumulation of hundreds of satellite images can be completed within 15 min, depending on the processing requirements.

21 June 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YLYen-Chun Lin
Yen-Chun Lin
TYTeng-To Yu
Teng-To Yu
YYYU-EN YANG
YU-EN YANG
JLJo-Chi Lin
Jo-Chi Lin
GLGuang-Wen Lien
Guang-Wen Lien
SLShyh-Chin Lan
Shyh-Chin Lan
This study proposes a practical integration of an existing deep learning model (YOLOv9-E) and social participation GIS using multi-source remote sensing data to identify asbestos-containing materials located on the side of a building affected by light occlusions. These objects are often undetectable by traditional vertical or oblique photogrammetry, yet their precise localization is essential for effective removal planning. By leveraging the mobility and responsiveness of citizen investigators, we conducted fine-grained surveys in community spaces that were often inaccessible using conventional methods. The YOLOv9-E model demonstrated robustness on mobile-captured images, enriched with geolocation and orientation metadata, which improved the association between detections and specific buildings. By comparing results from Google Street View and field-based social imagery, we highlight the complementary strengths of both sources. Rather than introducing new algorithms, this study focuses on an applied integration framework to improve detection coverage, spatial precision, and participatory monitoring for environmental risk management. The dataset comprised 20,889 images, with 98% being used for training and validation and 2% being used for independent testing. The YOLOv9-E model achieved an mAP50 of 0.81 and an F1-score of 0.85 on the test set.