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

Abstract

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 is 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 of hydrological data and post-processing of 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.

Machine learning assisted high-throughput screening of transition metal single atom based superb hydrogen evolution electrocatalysts

“…ML is becoming more popular for the semi-automated and quantitative discovery of data correlations in chemistry and materials science. 45,61,62,65,84 Although many data-driven strategies are being successfully utilized in heterogeneous catalysis, 79,85 ML still remains at an early stage due to numerous underexplored material data for water electrocatalysis. We adopted a stepwise multistage screening strategy for discovering promising electrocatalysts with enhanced HER activities.…”

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

“…Code and data availability. The AI4Water source code can be found in a publicly available GitHub repository (https://github.com/ AtrCheema/AI4Water, last access: 18 March 2022), and its version 1.0 is archived at https://doi.org/10.5281/zenodo.5595680 (Abbas et al, 2021). The user manual is built into the source code "Docstring" and compiled into a "read the docs" web page (https: //ai4water.readthedocs.io/en/latest/, last access: 18 March 2022) using Sphinx (Brandl, 2010) software.…”

<i>Escherichia coli</i> concentration, multiscale monitoring over the decade 2011–2021 in the Mekong River basin, Lao PDR

“…These three datasets together present a unique long-term spatiotemporal and multiscale surface water quality monitoring within the Mekong River basin. So far, the datasets have been used: (1) to describe the hydrological processes driving instream E. coli concentration during flood events (Boithias et al, 2021a;Ribolzi et al, 2016b), (2) to understand the role of land use in bacterial dissemination on small and large catchment scales, e.g., E. coli (Causse et al, 2015;Rochelle-Newall et al, 2016;Nakhle et al, 2021b;Ribolzi et al, 2011) and Burkholderia pseudomallei (Ribolzi et al, 2016a;Zimmermann et al, 2018;Liechti et al, 2021), (3) to relate stream water quality and diarrhea outbreaks (Boithias et al, 2016), and (4) to build catchment-scale numerical models focused on water quality (Kim et al, 2017(Kim et al, , 2018Abbas et al, 2021Abbas et al, , 2022.…”