Open source

Code & data

Open-source code behind my papers and datasets. Everything here is public on GitHub.

Research code

Transformer framework for generalizable streamflow modeling across space and time from distributed inputs.

Basin-centric embeddings for transferable hydrologic prediction in unseen basins (WACV 2027).

Pipeline for the 40-year distributed hydrology dataset of 9,067 U.S. basins (Scientific Data, 2026).

Explainable, distributed CNN–LSTM hydrologic model (Environmental Modelling & Software, 2026).

Graph neural networks over river networks for distributed streamflow prediction.

Continental-scale data acquisition for foundation-model training.

Transfer-learning architecture for scalable visual quality inspection (ICAI 2022).

Tutorials for configuring and training Detectron2 object-detection models.

More on GitHubExplore all repositories at github.com/Muhammad-Talha-MT

</a>