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

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 led by Ather Abbas, PhD student at UNIST, a python-based framework was developed to simplify the process of building and training machine-learning-based hydrological models and to automatize pre-processing of hydrological data and post-processing of model results. This framework, partly tested on M-TROPICS data collected in Lao PDR, will help increase the application of machine-learning-based modeling approaches in hydrological sciences.

The paper was published open access in the journal Geoscientific Model Development.

More news

Articles

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

Bacterial pathogens in surface waters may threaten human health, especially in developing countries, where untreated surface water is often used for domestic needs. The objective of the long-term multiscale monitoring of Escherichia coli concentration in stream water, and that of associated variables (temperature, electrical conductance, dissolved oxygen concentration and saturation, pH, oxidation-reduction potential, turbidity, and […]

25.06.2022

Articles

Groundwater irrigation reduces overall poverty but increases socioeconomic vulnerability in a semiarid region of southern India

The development of irrigation is generally considered an efficient way to reduce poverty in rural areas, although its impact on the inequality between farmers is more debated. In fact, assessing the impact of water management on different categories of farmers requires resituating it within the different dimensions of the local socio-technical context. This study, led […]

13.06.2022

Articles

Distribution of Burkholderia pseudomallei within a 300‑cm deep soil profile: implications for environmental sampling

The environmental distribution of Burkholderia pseudomallei, the causative agent of melioidosis, remains poorly understood. This study performed in Lao PDR and supervised by Alain Pierret (IRD-iEES Paris) and Olivier Ribolzi (IRD-GET), in the frame of the PhD of Khemngeun Pongmala, provides novel information about a putative association of soil biogeochemical heterogeneity and the vertical distribution […]

25.05.2022

Search