Kei Ishida

Kei Ishida
Kumamoto University | Kumadai · Center for Water Cycle Marine Environment and Disaster Management

About

85
Publications
12,086
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
771
Citations
Additional affiliations
October 2020 - present
Kumamoto University
Position
  • Professor (Associate)
March 2017 - September 2020
Kumamoto University
Position
  • Professor (Assistant)
October 2015 - February 2017
University of California, Davis
Position
  • Researcher

Publications

Publications (85)
Article
Full-text available
The aggregation and dispersion of metals and organic matter are an important morphological alteration process for their transportation and bioavailability in coastal areas. However, variable mixing behaviours can be observed for some substances (e.g. Mn and Cu) due to the variable interaction systems in natural systems. In this study, riverine fres...
Article
Microplastics have received increasing attention as substances of potential risk due to their adverse effect on ecosystems and human health in recent year. Membrane bioreactors (MBRs) have excellent microplastic removal performance compared to conventional WWTPs. Meanwhile, there is a possibility that the membrane materials themselves become the so...
Article
Full-text available
In this paper, we perform the super-resolution of sea surface temperature data with the enhanced super-resolution generative adversarial network (ESRGAN), which is a deep neural network-based single-image super-resolution (SISR) method that uses a generative adversarial network (GAN). We generate high-quality super-resolution data with ESRGAN and w...
Preprint
Deep learning has been utilized for the statistical downscaling of climate data. Specifically, a two-dimensional (2D) convolutional neural network (CNN) has been successfully applied to precipitation estimation. This study implements a three-dimensional (3D) CNN to estimate watershed-scale daily precipitation from 3D atmospheric data and compares t...
Article
Membrane bioreactors (MBRs) have been recognized as a promising wastewater treatment technique because of their superior solid–liquid separation performance; however, fouling development remains a concern. In this study, the relationship between membrane pore size and fouling development is investigated using originally prepared chlorinated polyvin...
Preprint
An architecture consisting of a serial coupling of the one-dimensional convolutional neural network (1D-CNN) and the long short-term memory (LSTM) network, which is referred as CNNsLSTM, was proposed for hourly-scale rainfall-runoff modeling in this study. In CNNsLTSM, the CNN component receives the hourly meteorological time series data for a long...
Article
Full-text available
This study proposes two effective approaches to reduce the required computational time of the training process for time-series modeling through a recurrent neural network (RNN) using multi-time-scale time-series data as input. One approach provides coarse and fine temporal resolutions of the input time-series data to RNN in parallel. The other conc...
Article
Study region Kuma River Watershed in Japan. Study focus High-quality precipitation information is desirable in hydrological modeling and water resources management. This study aimed to generate long-term fine-resolution precipitation datasets over the study region. A hybrid downscaling framework that integrates a dynamical approach by the Weather...
Article
Full-text available
Future climate projections are valuable datasets to investigate the impacts of future climate changes on natural disasters such as intense precipitation, severe flood, and drought. However, they are too coarse depending on the purpose, and downscaling is required in such a case. There is nowadays a downscaling technique using deep learning such as...
Article
Full-text available
Groundwater is a very important water resource at Kumamoto City. Kumamoto City is the capital city of Kumamoto Prefecture, which is located in the Kyushu region, Japan. All domestic water is obtained from groundwater in Kumamoto City. Modeling groundwater is a difficult issue. Conditions under the ground are complex, and difficult to be obtained. E...
Article
Full-text available
In recent years, rainfall-runoff modelling using LSTM has shown high adaptability. However, LSTM requires far more computational costs than traditional RNN. In addition, a different type of RNN, GRU, has been developed to solve this issue of LSTM. Therefore, this study compares the accuracy of the deep learning methods for rainfall-runoff modelling...
Article
50 days' free access to the article is available at https://authors.elsevier.com/c/1dfCDB8ccq-6e .This study investigates the relationships which deep learning methods can identify between the input and output data. As a case study, rainfall-runoff modeling in a snow-dominated watershed by means of a long short-term memory (LSTM) network is selecte...
Preprint
This study investigates the relationships which deep learning methods can identify between the input and output data. As a case study, rainfall-runoff modeling in a snow-dominated watershed by means of a long- and short-term memory (LSTM) network is selected. Daily precipitation and mean air temperature were used as model input to estimate daily fl...
Article
Data scarcity is one of the major constraints for hydrological modeling at a mountainous region with complex terrains. In this study, WRF (Weather Research and Forecasting model) model was configured to produce high-resolution atmospheric data for spatial modeling of snow at seven watersheds in central/southern Sierra Nevada. The configured WRF mod...
Article
Full-text available
Long-term climate change may strongly affect the aquatic environment in mid-latitude water resources. In particular, it can be demonstrated that temporal variations in surface water temperature in a reservoir have strong responses to air temperature. We adopted deep neural networks (DNNs) to understand the long-term relationships between air temper...
Preprint
This study proposes two straightforward yet effective approaches to reduce the required computational time of the training process for time-series modeling through a recurrent neural network (RNN) using multi-time-scale time-series data as input. One approach provides coarse and fine temporal resolutions of the input time-series to RNN in parallel....
Article
Membrane bioreactors (MBRs) are promising treatment techniques, especially for wastewater, including dense suspension and high salinity. However, membrane fouling is still a critical problem for continuous application. The hydrophilicity of a membrane has so far been considered as one of the important factors contributing to the fouling phenomena....
Article
Streamflow data are important for river maintenance, water resources planning, and flood forecasting. However, the flow data may be missing due to various reasons. Therefore, this study proposed a novel method using deep learning to complement missing data of flow discharge time series. This study utilized hourly flow data before and after missing...
Article
Extreme flood events are disastrous and can cause serious damages to society. Flood frequency obtained based on historical flow records may also be changing under future climate conditions. The associated flood inundation and environmental transport processes will also be affected. In this study, an integrated numerical modeling framework is propos...
Article
In this study, a coastal sea level estimation model was developed at an hourly temporal scale using the long short-term memory (LSTM) network, which is a type of recurrent neural networks. The model incorporates the effects of various phenomena on the coastal sea level such as the gravitational attractions of the sun and the moon, seasonality, stor...
Article
The objective of this study is to investigate characteristics of precipitation downscaling by means of a deep learning method, which have not been revealed well so far. This study utilized atmospheric variabes as input, and watershed-scale precipitation as the targeted data. CNN was seleted as a deep learing method for precipitation downscaling. Th...
Article
In Kumamoto, Japan, about one-million people depend for all their water on groundwater resources. Paddy fields and rice farming in the middle river watershed area make a large contribution to the groundwater recharge. In our research, an environmental measure (artificial flooding for groundwater recharge) conducted by local governments is evaluated...
Article
Full-text available
In this study, a regional climate model was used to dynamically downscale 15 future climate projections from three GCMs covering four emission scenarios (SRES B1, A1FI, A1B, A2) based on Coupled Model Intercomparison Project phase 3 (CMIP3) datasets to 6-km horizontal resolution over the whole Peninsular Malaysia. Impacts of climate change in the 2...
Article
This study investigated the effects of activating convective parameterization (CP) in higher-resolution domains of a regional climate model, the Weather and Research Forecast (WRF) model, on watershed-scale precipitation by means of sensitivity analysis. The sensitivity analysis was conducted over three watersheds in the Hokkaido region, Japan. Thr...
Article
Can be downloaded from link below (50 days' free access): "https://authors.elsevier.com/c/1ZAI2_17GgHSA8 ". A point-location-based analysis of future climate change impacts on snow accumulation and melting processes was conducted over three study watersheds in Northern California during a 90-year future period by means of snow regime projections....
Article
Full-text available
Tropical cyclones (TCs) are intense atmospheric vortices that form over the warm tropical oceans. They are recognized for their ability to generate intense precipitation that may in turn create disastrous floods. This article first assesses the suitability of a regional atmospheric model, the Weather Research and Forecasting (WRF) model, to simulat...
Article
The impacts of climate change on snow distribution through the 21st century were investigated over three mountainous watersheds in Northern California by means of a physically-based snow distribution model. The future climate conditions during a 90-year future period from water year 2010 to 2100 were obtained from 13 future climate projection reali...
Article
Full-text available
Impact of future climate change on watershed-scale precipitation was investigated over Northern California based on future climate projections by means of the dynamical downscaling approach. Thirteen different future climate projection realizations from two general circulation models (GCMs: ECHAM5 and CCSM3) based on four emission scenarios (SRES A...
Article
Estimation of the extreme precipitation over a target watershed under a changing climate would be necessary to design safe large hydraulic structures. For this purpose, the Maximum Precipitation (MP) estimation approach was applied to the American River watershed (ARW) in Northern California under several future climate conditions over 90 water yea...
Article
The Gediz Basin is a Mediterranean watershed along the Aegean coast of Turkey, in which the most important economic activity is agriculture. Over the last few decades, this basin has been experiencing water-related problems such as water scarcity and competing use of water. This study assesses the impact of future climate change on the availability...
Conference Paper
Mesoscale convective systems (MCSs) are large clusters of thunderstorms that act as a single system generating localized extreme precipitation and causing disastrous flooding and destruction in the central United States. To enhance our modeling of such storm events, especially under future climate projections, this study focuses on modeling MCSs th...
Conference Paper
The purpose of this study is to reconstruct atmospheric conditions over Ishikari River Basin (IRB) in Japan during a historical period. Although observation data of near-surface atmospheric variables including precipitation are available for at least several decades in Japan, they are not sufficient to analyze causes of precipitation over IRB. Ther...
Article
Full-text available
Soil properties play an important role in watershed hydrology and environmental modeling. In order to model realistic hydrologic processes, it is necessary to obtain compatible soil data. This study introduces a new method that integrates global soil databases with land use/land cover (LULC) databases to better represent saturated hydraulic conduct...
Article
Full-text available
California's interconnected water system is one of the most advanced water management systems in the world, and understanding of long-term trends in atmospheric and hydrologic behavior has increasingly being seen as vital to its future well-being. Knowledge of such trends is hampered by the lack of long-period observation data and the uncertainty s...
Article
Full-text available
One of the major challenges in water resources research is to understand the impact of climate change on hydrology. In Thailand, upper Ping river basin is one of the major resources supply water to a major rice bowl, Chao Phraya basin area. In this study, the effects of climate change on hydrology was utilized by using SRES-climate scenarios during...
Article
Full-text available
It is important to assess the reliability of high-resolution climate variables used as input to hydrologic models. High-resolution climate data is often obtained through the downscaling of Global Climate Models and/or historical reanalysis, depending on the application. In this study, the performance of dynamically downscaled precipitation from the...
Article
The impacts of climate change on watershed-scale precipitation through the 21st century were investigated over eight study watersheds in Northern California based on dynamically downscaled CMIP5 future climate projections from three GCMs (CCSM4, HadGEM2-ES, and MIROC5) under the RCP4.5 and RCP8.5 future climate scenarios. After evaluating the model...
Conference Paper
Estimating maximum precipitation (MP) over a watershed is a necessary process to estimate maximum flood which is used in the planning and design of dams. Major storms in Northern California are caused by so called atmospheric rivers (ARs), which are narrow, but rich moisture atmospheric flows from the tropics. To estimate the MP over the Shasta Dam...
Conference Paper
As population and infrastructure continue to increase, our society has become more vulnerable to extreme events. Flood is an example of a hydro-meteorological disaster that has a strong societal impact. Tropical cyclones are recognized for their ability to generate intense precipitation that may in turn create disastrous floods. In the context of c...
Conference Paper
Watershed Environmental Hydrology Hydro-Climate Model (WEHY-HCM) was used to simulate the surface flows of the Upper Middle Fork (UMF) Watershed under different climate conditions. Long-term historical atmospheric conditions over the Middle Fork Feather River Basin were reconstructed for the 63-year period between October 1950 and September 2013 by...
Conference Paper
The physical upper bound of precipitation, referred to as the maximum precipitation (MP), was estimated over the American River Watershed in Northern California under future climate conditions by means of a physically-based regional atmospheric model. Severe storm events over ARW are mainly caused by an atmospheric river (AR) which is a high-moistu...
Conference Paper
Mesoscale convective systems (MCSs) are known for their ability to generate localized extreme precipitation. Therefore, it is important to understand how such storm systems will evolve in the context of a changing climate. This goal can be achieved by using a numerical weather model such as the weather research and forecasting (WRF) model, forced b...
Conference Paper
The Grizzly Valley Dam is an earth and rockfill dam located in the Lake Davis Basin of the Feather River Watershed, which is in California’s northern Sierra Nevada. The dam is situated just downstream of Lake Davis, with the purposes of water supply (to Portola), fish and wildlife enhancement, streamflow enhancement, as well as recreation. Historic...
Conference Paper
California’s interconnected water system is one of the most advanced water management systems in the world, and understanding of long-term trends in atmospheric and hydrologic behavior has increasingly being seen as vital to its future well-being. Knowledge of such trends is hampered by the lack of long-period observation data and the uncertainty s...
Conference Paper
This study is designed to quantify the effects of climate change on hydrologic flow regimes in the Gediz Basin in Western Turkey during the 21st century. As the regional atmospheric model, the weather research and forecasting (WRF) Model was employed to dynamically downscale the outputs of two global climate models, HadGEM2-ES and GFDL-ESM2M, to a...
Conference Paper
Precipitation over Northern California under future climate conditions was obtained by dynamically downscaling IPCC CMIP5 future climate projection realizations. Six different future climate projection realizations from three general circulation models (GCMs: CCSM4, HadGEM2ES and MIROC5) based on two CMIP5 future climate scenarios (RCP4.5 and RCP8....
Conference Paper
Along with socioeconomic developments, and population increase, natural disasters around the world have recently increased the awareness of harmful impacts they cause. Among natural disasters, drought is of great interest to scientists due to extraordinary diversity of their severity and duration. Motivated by developing a potential approach to inv...
Conference Paper
This study performs dynamical downscaling simulations using a regional atmospheric model, WRF (the weather research and forecasting model), over the Gediz Basin at 6 km grid resolution in order to investigate changes in temperature and precipitation during the 21st century under two IPCC representative concentration pathway scenarios (RCP4.5 and RC...
Conference Paper
An estimate of the 72-hour basin-averaged maximum precipitation was calculated for five watersheds in the southern region of the Sierra Nevada in California using a physically based atmospheric model. First, the weather research and forecasting (WRF) model was calibrated and validated using the climate forecast system reanalysis (CFSR) dataset from...
Article
Full-text available
Snow is an important component of the Earth’s climate system and is particularly vulnerable to global warming. It has been suggested that warmer temperatures may cause significant declines in snow water content and snow cover duration. In this study, snowfall and snowmelt were projected by means of a regional climate model that was coupled to a phy...
Article
Improvements on nonhydrostatic atmospheric models such as MM5 in the last few decades have enhanced our understanding of the precipitation mechanism affected by topography and nonlinear dynamics of the atmosphere. This study addresses the use of such a regional atmospheric model to estimate physical maximum precipitation rates for the next generati...
Article
Full-text available
Along with socioeconomic developments, and population increase, natural disasters around the world have recently increased the awareness of harmful impacts they cause. Among natural disasters, drought is of great interest to scientists due to the extraordinary diversity of their severity and duration. Motivated by the development of a potential app...
Article
Full-text available
In this study several issues with the standard flood frequency analysis are discussed in the context of a changing hydro-climate in the 21st century. Among these issues the loss of statistical equilibrium in the hydro-climate of a studied region during the 21st century has serious implications on the standard frequency analysis that is discussed in...
Article
Full-text available
Impacts of climate change on the hydrologic processes under future climate change conditions were assessed over Muda and Dungun watersheds of Peninsular Malaysia by means of a coupled regional climate and physically-based hydrology model utilizing an ensemble of future climate change projections. An ensemble of 15 different future climate realizati...
Chapter
Full-text available
For the water resources planning and management studies during the last century, the necessary long-term simulations of the precipitation fields over a target region were performed by stochastic precipitation models. After the necessary advances in computational resources and modeling technologies were achieved toward the end of the 20th century, i...
Article
Impact of air temperature on the Maximum Precipitation (MP) estimation through change in moisture holding capacity of air was investigated. A series of previous studies have estimated the MP of 72-hour basin-average precipitation over the American River watershed (ARW) in Northern California by means of the Maximum Precipitation (MP) estimation app...
Article
A methodology based on long-term dynamical downscaling to analyse climate change effects on watershed-scale precipitation during a historical period is proposed in this study. The reliability and applicability of the methodology were investigated based on the long-term dynamical downscaling results. For an application of the proposed methodology, t...
Article
In snow-dominated regions surface air temperature is expected to have a substantial effect on the magnitude of a flood during a storm event. It is risky to estimate the design flood based only on the maximum precipitation while excluding other atmospheric variables like temperature and radiation. To overcome this problem, a methodology to estimate...
Conference Paper
Effect of climate change on hydrologic flow regimes, particularly extreme events, necessitates modeling of future flows in order to best inform water resources management. In this study, the future flows were simulated using global climate models (GCMs) and a regional atmospheric model in tandem with a watershed model to make a hydro-climate model...
Conference Paper
Climate change analysis on historical precipitation was conducted over two study watersheds in Northern California: the Upper Feather River watershed and the Yuba River watershed. It is difficult to obtain sufficient observed precipitation data for a long-term period over such mountainous watersheds. In this study, therefore, historical precipitati...
Conference Paper
A real-time flood forecasting system was developed over the Kızılırmak river basin (KRB) in Turkey by means of a physically-based atmospheric-hydrological model. The real-time flood forecasting system utilizes the weather research and forecasting (WRF) model and the WRF data assimilation (WRFDA) system as its atmospheric component. Real-time global...
Conference Paper
Kızılırmak river, with a drainage area of more than 75,000 km², is the longest river among the rivers which originate and end in Turkey. A coupled atmospheric-hydrologic model based real-time precipitation and flood forecasting system for Kızılırmak river basin was developed and became operational recently. This real-time forecasting system utilize...
Conference Paper
This study introduced a new method that unites a hydrologic model using physical infiltration mechanisms with a combination of a hydrologic soil group (soil) and a land use and treatment class (cover) to integrate LULC data into soil data. The new method has been incorporated into the WEHY model to simulate hydrologic conditions over the Cache Cree...
Article
Long-term water supply data are important for the current practice of water resources management at a target region. However, long-term water outflow data from reservoirs are typically limited at fine time resolution (hourly). In this study, the historical data on water supply from the Shasta Dam were reconstructed by a reservoir operation model wi...
Article
Full-text available
Effect of climate change on hydrologic flow regimes, particularly extreme events, necessitates modeling of future flows in order to best inform water resources management. This study simulated future flows in the Cache Creek watershed in California over the 21st century using a hydro-climate model (Watershed Environmental Hydrology Hydro-Climate Mo...
Conference Paper
Snow is a very important component of the Earth’s climate system and is particularly vulnerable to global warming. It has been suggested that warmer temperatures may cause significant declines in snow water content and snow cover duration. In this study, snow fall and snow melt were projected by means of Watershed Environmental Hydrology Hydro-Clim...
Conference Paper
Long-term hydrologic and atmospheric data such as precipitation, temperature and surface-water flow are sparse and are often limited to time periods within the past century. Currently, observational data do not exist at continuous time intervals and/or are missing entirely. Dynamic downscaling is a method that can be used on available coarse-resolu...
Conference Paper
Long-term hydrologic and atmospheric data such as precipitation, temperature and surface-water flow are sparse and are often limited to time periods within the past century. Currently, observational data do not exist at continuous time intervals and/or are missing entirely. Dynamic downscaling is a method that can be used on available coarse-resolu...
Conference Paper
A regional atmospheric model is an important tool for watershed modeling because it can provide all the atmospheric input information required by a watershed model. Among regional atmospheric models, the Weather Research and Forecasting Model (WRF) is most frequently used nowadays. The WRF was originally developed as a new version of Fifth-Generati...
Conference Paper
Long-term historical precipitation over Northern California was reconstructed for 137 water years from October, 1871 through September, 2008 by dynamical downscaling based on NOAA Twentieth Century Reanalysis version 2 (20CRv2). The annual maximum values of 6-, 12-, 24-, 48-, 72-, and 96-hour basin-average precipitation were obtained from the recon...
Conference Paper
Before investigating future climatic and hydrologic conditions over Peninsular Malaysia, preliminary climatic and hydrologic simulation results were presented in this paper. The coarse time-space resolution ECHAM5, MRI-CGCM2.3.2 and CCSM3 GCM historical control runs’ atmospheric data during the period of 1970–1999 were dynamically downscaled into 1...
Conference Paper
Climate change impacts hydrological processes by altering both spatial and temporal characteristics of water flow in a watershed. The physically-based hydro-climate model for the assessment of regional climate change is one of the most realistic modeling approaches to account for the non-stationarity in changing climate conditions of the 21st centu...
Article
Full-text available
Maximum precipitation (MP) was estimated by means of a regional atmospheric model over three watersheds in northern California [(1) the American River watershed (ARW), (2) the Yuba River watershed (YRW), and (3) the Upper Feather River watershed (UFRW)], based on the reconstruction and analyses of the historical severe storms that were recorded ove...
Article
Full-text available
Maximum precipitation during a historical period is estimated by means of a physically based regional atmospheric model over three watersheds in Northern California: the American River watershed (ARW), the Yuba River watershed (YRW), and the Upper Feather River watershed (UFRW). In Northern California, severe storm events are mostly caused by a hig...
Conference Paper
In this study the extreme precipitation under different CCSM3 GCM GHG emissions scenarios is investigated between historical period (wy1901 - wy1999) and projection period (wy2001 - wy2099) for the watersheds in northern California. For this, a regional climate model (MM5) was set up over northern California and then the precipitation was dynamical...
Article
This study is aimed at quantifying the difference in aquifer's response to recharge between some different locations in a fan aquifer and a delta aquifer for a preliminary study of revealing mechanisms of water transport in alluvial aquifer. The aquifer's response to recharge is statistically quantified with the two viewpoints: (1) timing and volum...
Conference Paper
A 72-hour precipitation in a storm event over the American River Watershed (ARW) in California is maximized using a physically-based numerical model for a regional atmosphere. A storm event over ARW is caused by a high-moisture atmosphere coming from the Pacific Ocean, called «atmospheric river.» Moreover, the path of an atmospheric river affects t...
Article
Understanding water flows in open channels is of great importance in agricultural engineering because water is necessary for farming. Although water flow is fundamentally a three-dimensional (3D) phenomenon, one-dimensional (ID) models are frequently used in numerical simulations of open channel flows because more detailed data and a greater comput...
Article
To numerically analyze the hydraulic and hydrological aspects of water environment in an alluvial area that has three-dimensional (3-D) complexity in its geological structure, a composite dimensional physically-based numerical model is developed by use of the finite volume method (FVM). The model consists of the surface and subsurface flow submodel...