AI4Water v1.0: an open-source python package for modeling hydrological time series using data-driven methods

Ather Abbas; Laurie Boithias; Yakov Pachepsky; Kyunghyun Kim; Jong Ahn Chun; Kyung Hwa Cho

doi:10.5194/gmd-15-3021-2022

AI4Water v1.0: an open-source python package for modeling hydrological time series using data-driven methods

Ather Abbas, Laurie Boithias, Yakov Pachepsky, Kyunghyun Kim, Jong Ahn Chun^*, Kyung Hwa Cho^*

^*Corresponding author for this work

Physical Sciences and Engineering

Research output: Contribution to journal › Article › peer-review

17 Scopus citations

Abstract

Machine learning has shown great promise for simulating hydrological phenomena. However, the development of machine-learning-based hydrological models requires advanced skills from diverse fields, such as programming and hydrological modeling. Additionally, data pre-processing and post-processing when training and testing machine learning models are a time-intensive process. In this study, we developed a python-based framework that simplifies the process of building and training machine-learning-based hydrological models and automates the process of pre-processing hydrological data and post-processing model results. Pre-processing utilities assist in incorporating domain knowledge of hydrology in the machine learning model, such as the distribution of weather data into hydrologic response units (HRUs) based on different HRU discretization definitions. The post-processing utilities help in interpreting the model's results from a hydrological point of view. This framework will help increase the application of machine-learning-based modeling approaches in hydrological sciences.

Original language	English (US)
Pages (from-to)	3021-3039
Number of pages	19
Journal	Geoscientific Model Development
Volume	15
Issue number	7
DOIs	https://doi.org/10.5194/gmd-15-3021-2022
State	Published - Apr 8 2022

Bibliographical note

Funding Information:
Acknowledgements. This study was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Korean Ministry of Education (no. 2017R1D1A1B04033074), as well as the Korea Environment Industry and Technology Institute (KEITI) through the Aquatic Ecosystem Conservation Research Program funded by Korean Ministry of Environment (MOE) (no. 2020003030003). The authors also thank Campus France (PHC STAR 41510WH) for their financial support.

Funding Information:
Financial support. This study was supported by Basic Science

Publisher Copyright:
© Copyright:

ASJC Scopus subject areas

Modeling and Simulation
General Earth and Planetary Sciences

Access to Document

10.5194/gmd-15-3021-2022

Cite this

@article{b34f6fe91fc14426a7562e3221737eee,

title = "AI4Water v1.0: an open-source python package for modeling hydrological time series using data-driven methods",

abstract = "Machine learning has shown great promise for simulating hydrological phenomena. However, the development of machine-learning-based hydrological models requires advanced skills from diverse fields, such as programming and hydrological modeling. Additionally, data pre-processing and post-processing when training and testing machine learning models are a time-intensive process. In this study, we developed a python-based framework that simplifies the process of building and training machine-learning-based hydrological models and automates the process of pre-processing hydrological data and post-processing model results. Pre-processing utilities assist in incorporating domain knowledge of hydrology in the machine learning model, such as the distribution of weather data into hydrologic response units (HRUs) based on different HRU discretization definitions. The post-processing utilities help in interpreting the model's results from a hydrological point of view. This framework will help increase the application of machine-learning-based modeling approaches in hydrological sciences.",

author = "Ather Abbas and Laurie Boithias and Yakov Pachepsky and Kyunghyun Kim and Chun, {Jong Ahn} and Cho, {Kyung Hwa}",

note = "Funding Information: Acknowledgements. This study was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Korean Ministry of Education (no. 2017R1D1A1B04033074), as well as the Korea Environment Industry and Technology Institute (KEITI) through the Aquatic Ecosystem Conservation Research Program funded by Korean Ministry of Environment (MOE) (no. 2020003030003). The authors also thank Campus France (PHC STAR 41510WH) for their financial support. Funding Information: Financial support. This study was supported by Basic Science Publisher Copyright: {\textcopyright} Copyright: ",

year = "2022",

month = apr,

day = "8",

doi = "10.5194/gmd-15-3021-2022",

language = "English (US)",

volume = "15",

pages = "3021--3039",

journal = "Geoscientific Model Development",

issn = "1991-959X",

publisher = "European Geosciences Union",

number = "7",

}

TY - JOUR

T1 - AI4Water v1.0

T2 - an open-source python package for modeling hydrological time series using data-driven methods

AU - Abbas, Ather

AU - Boithias, Laurie

AU - Pachepsky, Yakov

AU - Kim, Kyunghyun

AU - Chun, Jong Ahn

AU - Cho, Kyung Hwa

N1 - Funding Information: Acknowledgements. This study was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Korean Ministry of Education (no. 2017R1D1A1B04033074), as well as the Korea Environment Industry and Technology Institute (KEITI) through the Aquatic Ecosystem Conservation Research Program funded by Korean Ministry of Environment (MOE) (no. 2020003030003). The authors also thank Campus France (PHC STAR 41510WH) for their financial support. Funding Information: Financial support. This study was supported by Basic Science Publisher Copyright: © Copyright:

PY - 2022/4/8

Y1 - 2022/4/8

N2 - Machine learning has shown great promise for simulating hydrological phenomena. However, the development of machine-learning-based hydrological models requires advanced skills from diverse fields, such as programming and hydrological modeling. Additionally, data pre-processing and post-processing when training and testing machine learning models are a time-intensive process. In this study, we developed a python-based framework that simplifies the process of building and training machine-learning-based hydrological models and automates the process of pre-processing hydrological data and post-processing model results. Pre-processing utilities assist in incorporating domain knowledge of hydrology in the machine learning model, such as the distribution of weather data into hydrologic response units (HRUs) based on different HRU discretization definitions. The post-processing utilities help in interpreting the model's results from a hydrological point of view. This framework will help increase the application of machine-learning-based modeling approaches in hydrological sciences.

AB - Machine learning has shown great promise for simulating hydrological phenomena. However, the development of machine-learning-based hydrological models requires advanced skills from diverse fields, such as programming and hydrological modeling. Additionally, data pre-processing and post-processing when training and testing machine learning models are a time-intensive process. In this study, we developed a python-based framework that simplifies the process of building and training machine-learning-based hydrological models and automates the process of pre-processing hydrological data and post-processing model results. Pre-processing utilities assist in incorporating domain knowledge of hydrology in the machine learning model, such as the distribution of weather data into hydrologic response units (HRUs) based on different HRU discretization definitions. The post-processing utilities help in interpreting the model's results from a hydrological point of view. This framework will help increase the application of machine-learning-based modeling approaches in hydrological sciences.

UR - http://www.scopus.com/inward/record.url?scp=85128778783&partnerID=8YFLogxK

U2 - 10.5194/gmd-15-3021-2022

DO - 10.5194/gmd-15-3021-2022

M3 - Article

AN - SCOPUS:85128778783

SN - 1991-959X

VL - 15

SP - 3021

EP - 3039

JO - Geoscientific Model Development

JF - Geoscientific Model Development

IS - 7

ER -

AI4Water v1.0: an open-source python package for modeling hydrological time series using data-driven methods

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this