Home »
Academic Articles »
C »
Identifying private pumping wells in a land subsidence area in Taiwan using deep learning technology and street view images
Identifying private pumping wells in a land subsidence area in Taiwan using deep learning technology and street view images
Chun-Wei Huang
(General Education Center, Ming Chi University of Technology, New Taipei City 243303, Taiwan; Corresponding author.)
Si Ying Yau
(Department of Geography, National Taiwan University, Taipei 10617, Taiwan; Graduate Institute of Applied Geology, National Central University, Zhongli District, Taoyuan City 320317, Taiwan)
Chiao-Ling Kuo
(Department of Geography, National Taiwan University, Taipei 10617, Taiwan; Research Center for Humanities and Social Sciences, Academia Sinica, Taipei 115024, Taiwan)
Tsai-Yu Kuan
(Interdisciplinary Practical Elite Program, College of Environment and Resources, Ming Chi University of Technology, New Taipei City 24301, Taiwan)
Si-Yu Lin
(BES Engineering Corporation, Taipei 105412, Taiwan)
Ching-Shih Tsou
(Institute of Information and Decision Sciences, National Taipei University of Business, 10051, Taipei City, Taiwan)
Chuen-Fa Ni
(Graduate Institute of Applied Geology, National Central University, Zhongli District, Taoyuan City 320317, Taiwan)
Yuan-Chien Lin
(Department of Civil Engineering, National Central University, No. 300, Zhongda Rd., Zhongli District, Taoyuan City 32001, Taiwan)
Liang-Cheng Chang
(Department of Civil Engineering, National Yang Ming Chiao Tung University, Hsinchu City 300093, Taiwan)
Study region: The Choushui River Fan, Taiwan. Study focus: Groundwater overdraft has led to not only groundwater depletion but also environmental disasters, such as subsidence and seawater intrusion in the Choushui River Alluvial Fan, Taiwan. The influence of land subsidence is gradually shifting from the coast to the center of the fan and threatening Taiwan high-speed rail. However, it remains a great challenge to manage and model the groundwater aquifer due to numerous unregulated wells. This study maps and locates private wells using deep learning technologies. We trained and validated convolutional-based deep learning neural networks (DNNs), using street view images. We applied the DNNs to a land subsidence area along the Taiwan high-speed rail, termed the Golden Corridor in Taiwan. The results showed that DNNs can recognize pumping wells with at least 90% accuracy. The testing cases showed their capability to recall all the pumping wells in three road segments along the Golden Corridor. Finally, we spatially estimated potential pumping of a subsidence area using the fine-trained DNNs. New hydrological insights for the region: Given the prevalence of unknown private pumping in the Choushui River Fan, our image data-driven computer vision approach not only eases labor-intensive private well investigations but also advances hydrologic understanding for groundwater modeling. We enhance comprehension of unknown sinks and provide their spatial distribution to improve groundwater modeling.
Chun-Wei Huang, Si Ying Yau, Chiao-Ling Kuo, et al. (2024). "Identifying private pumping wells in a land subsidence area in Taiwan using deep learning technology and street view images". Journal of Hydrology: Regional Studies. https://doi.org/10.1016/j.ejrh.2023.101636