Article
Environmental Sciences
Marco Dal Molin, Dmitri Kavetski, Carlo Albert, Fabrizio Fenicia
Summary: Calibration of precipitation-streamflow models to streamflow signatures is an effective way to predict streamflow in ungauged basins. This study proposes a signature-based calibration method using an Approximate Bayesian Computation framework, which reliably estimates the uncertainty in ungauged catchments.
WATER RESOURCES RESEARCH
(2023)
Article
Water Resources
Nischal Karki, Narendra Man Shakya, Vishnu Prasad Pandey, Laxmi Prasad Devkota, Ananta Man Singh Pradhan, Suraj Lamichhane
Summary: This study assesses the strengths and weaknesses of widely used regionalization methods for simulating daily hydrograph and flow duration curve in 23 medium to small-sized watersheds across Nepal. The physical similarity method was found to be the most robust, particularly for ungauged watersheds in Nepal. The study advocates for the use of hydrological model regionalization as a promising tool for streamflow prediction in ungauged Himalayan watersheds.
JOURNAL OF HYDROLOGY-REGIONAL STUDIES
(2023)
Article
Geosciences, Multidisciplinary
Rui Tong, Juraj Parajka, Borbala Szeles, Isabella Greimeister-Pfeil, Mariette Vreugdenhil, Jurgen Komma, Peter Valent, Gunter Bloschl
Summary: This study evaluates the efficiency of different methods for transferring model parameters obtained by multiple-objective calibrations to ungauged sites and assesses the model performance in terms of runoff, soil moisture, and snow cover predictions relative to existing regionalization approaches.
HYDROLOGY AND EARTH SYSTEM SCIENCES
(2022)
Article
Automation & Control Systems
Dominik Olszewski
Summary: The study introduces an enhanced adaptive version of SOM that preserves input data structure and captures data scattering, which has been empirically proven to be superior to other data visualization techniques.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Jingchen Cong, Chun-Hsien Chen, Xuan Meng, Zhongxia Xiang, Liang Dong
Summary: As an emerging IT-driven business paradigm, smart product-service system (Smart PSS) offers both smart, connected products and generated services, making it a significant research topic. This study proposes a conceptual design method for Smart PSS by analyzing user-generated emotions/feelings. Traditional products are identified, and their public review data is used to analyze user emotions/feelings. An interactive emotion board is introduced as a design tool to organize user-generated emotions/feelings and potential design points. The AHP is utilized for evaluating the improved solution.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Engineering, Civil
Li-Chiu Chang, Wu-Han Wang, Fi-John Chang
Summary: The study compared the effectiveness of two SOM training strategies, with the S2 strategy demonstrating higher efficiency and effectiveness in constructing regional flood inundation maps.
JOURNAL OF HYDROLOGY
(2021)
Article
Engineering, Civil
Wen-yan Qi, Jie Chen, Lu Li, Chong-Yu Xu, Yi-heng Xiang, Shao-bo Zhang, Hui-Min Wang
Summary: In this study, a comprehensive evaluation was conducted using five regionalization methods, two weighting schemes, two averaging options, five efficiency thresholds, and four lumped hydrological models over 3444 catchments in North America. The results showed that the Spatial Proximity with the Inverse Distance Weighting method and the output average option generally performed better, while the global mean method performed the worst. The selection of five donors was relatively efficient for distance/attributes-based regionalization approaches with the output averaging option.
JOURNAL OF HYDROLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Leonardo A. Dias, Augusto M. P. Damasceno, Elena Gaura, Marcelo A. C. Fernandes
Summary: The study introduces a fully parallel architecture for SOM that significantly improves processing speed and resource efficiency.
Article
Environmental Sciences
Sandra Pool, Marc Vis, Jan Seibert
Summary: This study compares 19 regionalization approaches in 671 gauged catchments in the United States and finds that the evaluation of predicted hydrograph varies depending on the regionalization method. Therefore, a multi-criteria evaluation is essential for a robust assessment of regionalization performance.
WATER RESOURCES RESEARCH
(2021)
Article
Water Resources
Lakhwinder Singh, Prabhash Kumar Mishra, Santosh Murlidhar Pingale, Deepak Khare, Hitesh Prasad Thakur
Summary: This study demonstrates how machine learning methods such as support vector machine and extreme gradient boosting can be used to calibrate ungauged simulated flow, focusing on their applications in the field of hydrology.
HYDROLOGICAL SCIENCES JOURNAL
(2022)
Article
Water Resources
Saeed Golian, Conor Murphy, Hadush Meresa
Summary: The study regionalizes two hydrological models (GR4J and GR6J) to predict continuous discharge in 44 catchments across Ireland. Different regionalization methods and objective functions significantly influence the success of predicting high and low flow conditions, with all models performing well for average flow conditions.
JOURNAL OF HYDROLOGY-REGIONAL STUDIES
(2021)
Article
Geography
Brittany Krzyzanowski, Steven Manson
Summary: This article addresses the challenge of sharing finer scale protected health information (PHI) while maintaining patient privacy by using regionalization to create higher resolution Health Insurance Portability and Accountability Act (HIPAA)-compliant geographical aggregations. We compare four regionalization approaches and recommend REDCAP and the SOM variant of max-p-regions (MSOM) as the preferred methods.
ANNALS OF THE AMERICAN ASSOCIATION OF GEOGRAPHERS
(2022)
Article
Environmental Sciences
A. T. M. Sakiur Rahman, Yumiko Kono, Takahiro Hosono
Summary: A holistic understanding of hydrochemical features is essential for water resources management and protection. Machine learning techniques like self-organizing map (SOM) can provide more detailed information on hydrochemical processes than traditional approaches, particularly in complex regions. Proper application of SOM is crucial for accurate results.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Computer Science, Hardware & Architecture
Xiaofei Qu, Lin Yang, Kai Guo, Linru Ma, Meng Sun, Mingxing Ke, Mu Li
Summary: This paper provides a focused literature survey on self-organizing maps (SOM) for intrusion detection, categorizing them into static-layered and dynamic-layered architectures. HSOM reduces computational overheads and efficiently represents data hierarchy, while GHSOM is effective for online intrusion detection with low computing latency, dynamic adaptability, and self-learning capabilities.
MOBILE NETWORKS & APPLICATIONS
(2021)
Article
Environmental Sciences
Chung-Mo Lee, Hanna Choi, Yongcheol Kim, MoonSu Kim, HyunKoo Kim, Se-Yeong Hamm
Summary: This study investigated the influence of land use types on nitrate-nitrogen contamination in groundwater in a typical rural area in South Korea. The findings showed that nitrate-nitrogen mainly originated from public facilities and livestock areas, with different land use types having distinct recharge routes for nitrate-nitrogen into the groundwater system. The shallow groundwaters in the study area were classified into three clusters based on their chemical constituents and land-use properties using SOM, PCA, and HCA.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Engineering, Civil
Tsun-Hua Yang, Sheng-Chi Yang, Jui-Yi Ho, Gwo-Fong Lin, Gong-Do Hwang, Cheng-Shang Lee
JOURNAL OF HYDROLOGY
(2015)
Article
Engineering, Civil
Gwo-Fong Lin, Bing-Chen Jhong
JOURNAL OF HYDROLOGY
(2015)
Article
Environmental Sciences
Ming-Chang Wu, Gwo-Fong Lin
Article
Meteorology & Atmospheric Sciences
Gwo-Fong Lin, Tsung-Chun Wang, Lu-Hsien Chen
ADVANCES IN METEOROLOGY
(2016)
Article
Engineering, Geological
Gwo-Fong Lin, Ming-Jui Chang, Ya-Chiao Huang, Jui-Yi Ho
ENGINEERING GEOLOGY
(2017)
Article
Water Resources
Ming-Chang Wu, Gwo-Fong Lin, Hsuan-Yu Lin
HYDROLOGICAL PROCESSES
(2014)
Article
Agricultural Engineering
Chun-Ming Wang, Gwo-Fong Lin
PADDY AND WATER ENVIRONMENT
(2015)
Article
Environmental Sciences
Ming-Jui Chang, Hsiang-Kuan Chang, Yun-Chun Chen, Gwo-Fong Lin, Peng-An Chen, Jihn-Sung Lai, Yih-Chi Tan
Article
Water Resources
Ming-Jui Chang, Gwo-Fong Lin, Peng-An Chen, Fong-Zuo Lee, Jihn-Sung Lai
HYDROLOGICAL SCIENCES JOURNAL-JOURNAL DES SCIENCES HYDROLOGIQUES
(2020)
Article
Engineering, Environmental
Ming-Jui Chang, Gwo-Fong Lin, Fong-Zuo Lee, Yi-Cheng Wang, Peng-An Chen, Ming-Chang Wu, Jihn-Sung Lai
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2020)
Article
Engineering, Environmental
I-Hang Huang, Ming-Jui Chang, Gwo-Fong Lin
Summary: Reservoir inflow forecasting is crucial for disaster prevention, especially in areas prone to typhoon events like the Shihmen Reservoir in Taiwan. This study compared seven machine learning algorithms for extreme weather events, finding that integrated methods can enhance accuracy and stability.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Chemistry, Multidisciplinary
Suu-Yan Liang, Wen-Sheng Lin, Gwo-Fong Lin, Chen-Wuing Liu, Chihhao Fan
Summary: This study investigated the impact of waste decay temperatures on bentonite performance and degradation of buffer materials caused by smectite dehydration. By simulating the temperature evolution due to smectite dehydration, changes in porosity in the buffer zone and the concentration of released radionuclides were determined. The results provide insights into the long-term behavior of bentonite in high-level radioactive waste disposal repositories.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Environmental
Jhih-Huang Wang, Gwo-Fong Lin, Yun-Ru Huang, I-Hang Huang, Chieh-Lin Chen
Summary: This study proposed a two-step flood hazard zoning model based on random forest and self-organizing map to generate accurate flood hazard zoning maps. By considering the flood susceptibility values of self-pixel and surrounding pixels, the proposed model improved the assessment performance and provided optimal flood hazard zoning maps.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2023)
Article
Environmental Sciences
Ming-Jui Chang, I-Hang Huang, Chih-Tsung Hsu, Shiang-Jen Wu, Jihn-Sung Lai, Gwo-Fong Lin
Summary: Accurate real-time forecasts of inundation depth and area during typhoon flooding are crucial to disaster emergency response. In this study, a forecasting model integrating a hydrodynamic model, support vector machine-multi-step forecast, and a self-organizing map was proposed to generate accurate flood inundation maps. The model demonstrated high accuracy and feasibility in real-world applications.
Article
Environmental Sciences
Hau-Wei Wang, Gwo-Fong Lin, Chih-Tsung Hsu, Shiang-Jen Wu, Samkele Sikhulile Tfwala
Summary: This study proposes a method for predicting the range and depth of flooding using a convolutional neural network. By training a deep learning model with a large rainfall dataset and raster flood data obtained from actual flooding events, considering different rainfall distributions, simulated area mesh, and topography, the method can be applied for long-term flood forecasting.