Yusuke Hiraga

Mr. Yusuke Hiraga

University of California - Daivs
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
7 March 2024 in Journal of Flood Risk Management
Verified
Journal Article
Open access
KKKumudu Madhawa Kurugama
Kumudu Madhawa Kurugama
SKSo Kazama
So Kazama
YHYusuke Hiraga
Yusuke Hiraga
CSChaminda Samarasuriya
Chaminda Samarasuriya
Identifying flood‐prone areas is essential for preventing floods, reducing risks, and making informed decisions. A spatial database with 595 flood inventory and 13 flood predictors were used to implement five boosting algorithms: gradient boosting machine (GBM), extreme gradient boosting, categorical boosting, logit boost, and light gradient boosting machine (LGBM) to map flood susceptibility in Rathnapura while evaluating trained model's generalizing ability and assessing the feature importance in flood susceptibility mapping (FSM). The model performance was evaluated using the F1‐score, kappa index, and area under curve (AUC) method. The findings revealed that all the models were effective in identifying the overall flood susceptibility trends while LightGBM model had superior results (F1‐score = 0.907, Kappa value = 0.813 and AUC = 0.970), securing the top scores across all performance metrics compared to the other models (for testing dataset). Based on kappa evaluation, most of the models had finer performance (AUC min = 0.737) while LightGBM had moderate performance for predictions beyond the training region. According to the results, regions with lower altitudes and topographic roughness values, moderate rainfall, and proximity to rivers are more susceptible to flooding. This framework can be adapted for rapid FSM in data‐deficient regions.

1 January 2023 in Journal of Hydrologic Engineering
Verified
Journal Article
Closed access
PDF file
YHYusuke Hiraga
Yusuke Hiraga
YIYoshihiko Iseri
Yoshihiko Iseri
MWMichael D. Warner
Michael D. Warner
CFChris D. Frans
Chris D. Frans
ADAngela M. Duren
Angela M. Duren
MKM. Levent Kavvas
M. Levent Kavvas
In recent years, there has been an increase in interest in estimating probable maximum precipitation (PMP) by numerical weather model (NWM)-based precipitation maximization methods, mainly, the moisture optimization method, storm transposition method, and their combination. This study addresses a quantitative comparison of the effectiveness of each precipitation maximization method regarding the increase in precipitation depths and a discussion on their functions for maximizing precipitation depths. To achieve such a comparison, this study conducted a numerical experiment using the moisture optimization method, which proportionally increases relative humidity using the integrated water vapor transport criterion, and the storm transposition method, which geospatially shifts atmospheric boundary conditions in the weather research and forecasting (WRF) model to maximize atmospheric river (AR)-induced precipitation depths over the Columbia River Basin. Our findings suggest that the storm transposition method should also be considered an essential method in the NWM-based precipitation maximization rather than relying solely on optimizing atmospheric moisture. This study also found that even for ARs with historically small amounts of precipitation over a specified basin, it is possible to increase precipitation depths significantly over the basin by using the storm transposition method. This finding implies that, for maximizing precipitation using the storm transposition method, it is important to select storms that historically did not directly hit the basin but were located around the basin as well, unlike the conventional approach of selecting storms solely based on precipitation depth over the basin. This finding also suggests that the storm transposition method is essential, particularly for estimating long-duration PMP that may cover a whole season, given the contribution of precipitation increase in each single storm event to the snowpack accumulation and reservoir storage for a long duration. Lastly, this study has shown that including the transposition method together with the moisture optimization method can increase precipitation amounts and give a higher upper bound for NWM-based precipitation maximization, especially in AR-dominated regions.

18 April 2024 in Journal of Flood Risk Management
Verified
Journal Article
Open access
YHYusuke Hiraga
Yusuke Hiraga
YIYoshihiko Iseri
Yoshihiko Iseri
MWMichael D. Warner
Michael D. Warner
ADAngela M. Duren
Angela M. Duren
JEJohn F. England
John F. England
MKM. Levent Kavvas
M. Levent Kavvas
This study proposes a model‐based methodology to estimate design precipitation for long durations during the winter and spring seasons (October to June) through its application to the drainage areas of two dams in the Columbia River Basin, United States. For basins with large reservoir storage or snowpack, design precipitation and floods need to be estimated based on long‐duration processes rather than focusing only on flood peaks or single storm durations. This study used the advanced research version of weather research and forecasting (WRF) model to maximize the target precipitation over the drainage areas by means of the Atmospheric Boundary Condition Shifting and Relative Humidity Perturbation with relaxed moisture flux thresholds. The greatest cumulative basin‐average precipitation depths during Oct–Jun were estimated to be 1220.5 and 1595.4 mm for the drainage areas of Bonneville and Libby Dams, respectively. The 95% confidence interval (CI) of the exceedance probabilities of the estimated design precipitation depths were found to range from 10−3 to 10−5 at Bonneville Dam's drainage area. Those orders were found to be comparable with the documented exceedance probabilities of PMP/PMF in the US. The estimated design precipitation and corresponding atmospheric/land‐surface fields together will drive a physical model to estimate the design flood.

23 July 2025 in Climate
Verified
Journal Article
Open access
PDF file
JMJacqueline Muthoni Mbugua
Jacqueline Muthoni Mbugua
YHYusuke Hiraga
Yusuke Hiraga
This review examines advancements and methodologies in long-term wind-speed and -power forecasting. It emphasizes the importance of these techniques in integrating wind energy into power systems. Covering a range of forecasting timeframes from monthly to multiyear projections, this paper highlights the diversity of applications and approaches. These applications and approaches are essential for managing the inherent variability and unpredictability of wind energy. Various forecasting methods, including statistical models, machine-learning techniques, and hybrid models, are discussed in detail. The review demonstrates how these methods improve forecast accuracy and reliability across different temporal and geographical scales. It also identifies significant challenges such as model complexity, data limitations, and the need to accommodate regional variations. Future improvements in wind forecasting include enhancing model integration, employing higher resolution data, and fostering collaborative research to further refine forecasting methodologies. This comprehensive analysis aims to advance knowledge on wind forecasting, facilitate the efficient integration of wind power into global energy systems, and contribute to sustainable energy development goals.

1 June 2024 in Journal of Hydrologic Engineering
Verified
Journal Article
Closed access
YHYusuke Hiraga
Yusuke Hiraga
YIYoshihiko Iseri
Yoshihiko Iseri
MWMichael D. Warner
Michael D. Warner
ADAngela M. Duren
Angela M. Duren
JEJohn F. England
John F. England
MKM. Levent Kavvas
M. Levent Kavvas

1 August 2018 in Journal of Hydrology: Regional Studies
Verified
Journal Article
Open access
YHYusuke Hiraga
Yusuke Hiraga
SKSo Kazama
So Kazama
CEChaiwat Ekkawatpanit
Chaiwat Ekkawatpanit
YTYoshiya Touge
Yoshiya Touge