[HTML][HTML] Exploding the myths: An introduction to artificial neural networks for prediction and forecasting

HR Maier, S Galelli, S Razavi, A Castelletti… - … modelling & software, 2023 - Elsevier
Abstract Artificial Neural Networks (ANNs), sometimes also called models for deep learning,
are used extensively for the prediction of a range of environmental variables. While the …

Review of soil and water assessment tool (SWAT) applications in Brazil: Challenges and prospects

D de Almeida Bressiani, PW Gassman… - International Journal of …, 2015 - ijabe.org
The geographical extent of Brazil exceeds 8.5 million km2 and encompasses a complex mix
of biomes and other environmental conditions. Multiple decision support tools are needed to …

[HTML][HTML] Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets

F Kratzert, D Klotz, G Shalev… - Hydrology and Earth …, 2019 - hess.copernicus.org
Regional rainfall–runoff modeling is an old but still mostly outstanding problem in the
hydrological sciences. The problem currently is that traditional hydrological models degrade …

Global-scale evaluation of 22 precipitation datasets using gauge observations and hydrological modeling

HE Beck, N Vergopolan, M Pan… - Hydrology and Earth …, 2017 - hess.copernicus.org
We undertook a comprehensive evaluation of 22 gridded (quasi-) global (sub-) daily
precipitation (P) datasets for the period 2000–2016. Thirteen non-gauge-corrected P …

Time to update the split‐sample approach in hydrological model calibration

H Shen, BA Tolson, J Mai - Water Resources Research, 2022 - Wiley Online Library
Abstract Model calibration and validation are critical in hydrological model robustness
assessment. Unfortunately, the commonly used split‐sample test (SST) framework for data …

The CAMELS data set: catchment attributes and meteorology for large-sample studies

N Addor, AJ Newman, N Mizukami… - Hydrology and Earth …, 2017 - hess.copernicus.org
We present a new data set of attributes for 671 catchments in the contiguous United States
(CONUS) minimally impacted by human activities. This complements the daily time series of …

Caravan-A global community dataset for large-sample hydrology

F Kratzert, G Nearing, N Addor, T Erickson, M Gauch… - Scientific Data, 2023 - nature.com
High-quality datasets are essential to support hydrological science and modeling. Several
CAMELS (Catchment Attributes and Meteorology for Large-sample Studies) datasets exist …

[HTML][HTML] Benchmarking data-driven rainfall–runoff models in Great Britain: a comparison of long short-term memory (LSTM)-based models with four lumped conceptual …

T Lees, M Buechel, B Anderson, L Slater… - Hydrology and Earth …, 2021 - hess.copernicus.org
Long short-term memory (LSTM) models are recurrent neural networks from the field of deep
learning (DL) which have shown promise for time series modelling, especially in conditions …

[HTML][HTML] The CAMELS-CL dataset: catchment attributes and meteorology for large sample studies–Chile dataset

C Alvarez-Garreton, PA Mendoza… - Hydrology and Earth …, 2018 - hess.copernicus.org
We introduce the first catchment dataset for large sample studies in Chile. This dataset
includes 516 catchments; it covers particularly wide latitude (17.8 to 55.0∘ S) and elevation …

Global‐scale regionalization of hydrologic model parameters

HE Beck, AIJM van Dijk, A De Roo… - Water Resources …, 2016 - Wiley Online Library
Current state‐of‐the‐art models typically applied at continental to global scales (hereafter
called macroscale) tend to use a priori parameters, resulting in suboptimal streamflow (Q) …