CAMELS USA 421 (Quilty and Jahangir, 2026)

A 421-catchment subset of the CAMELS (Catchment Attributes and MEteorology for Large-sample Studies) USA dataset as described in Quilty and Jahangir (2026): https://doi.org/10.1016/j.jhydrol.2026.134986. Sample code to train the different deep learning (DL) models from the paper are also included. The target and input data have already been pre-processed for entry into the deep learning models. The related GitHub repository (https://github.com/djmq/semicontinuousDL_camelsUSA) provides an example on how to download the data from Zenodo and train the deterministic DL model. Future releases of the code will be made available on GitHub. The MATLAB code has been tested in R2024a but is not guaranteed to work in earlier versions.