neuralhydrology/neuralhydrology

Python library to train neural networks with a strong focus on hydrological applications.

What it solves

It provides a specialized Python library for training neural networks specifically tailored for hydrological applications, simplifying the process of deep learning research in water-related sciences.

How it works

Built on top of PyTorch, the library emphasizes modularity. It allows researchers to easily integrate new datasets, model architectures, loss functions, and optimizers. A key feature is the use of configuration files, which enable users to train neural networks without needing to modify the underlying source code.

Who it’s for

Researchers and practitioners in hydrology and earth science who want to apply deep learning techniques to their data.

Highlights

  • Modular design for easy integration of new components
  • Configuration-file based training to avoid code changes
  • Built on PyTorch for flexibility in research
  • Extensively used and validated in academic publications

Related

  • Project
    nschaetti/EchoTorch

    A PyTorch-based module for implementing and testing Echo State Networks and Reservoir Computing, designed for research purposes and integration into deep architectures.

  • Project
    facebookresearch/pytorch3d

    A PyTorch-based library for 3D Computer Vision research providing differentiable rendering and efficient tools for manipulating 3D meshes and point clouds.

  • Project
    pykt-team/pykt-toolkit

    A PyTorch-based library for training and benchmarking deep learning knowledge tracing models with standardized data preprocessing and multiple model implementations.

  • Project
    sktime/pytorch-forecasting

    A PyTorch-based library for time series forecasting that provides a high-level API and state-of-the-art deep learning architectures like Temporal Fusion Transformers and N-BEATS.

  • Project
    deepinv/deepinv

    DeepInverse is an open-source PyTorch-based library designed to solve imaging inverse problems using deep learning through a modular framework of operators and algorithms.