v1.3.1

What's Changed

• Spatial tests by @nrkraabel in #55
• Update LICENSE by @kelawson48 in #56

New Contributors

• @nrkraabel made their first contribution in #55

Full Changelog: v1.3.0...v1.3.1

v1.3.0

Feature Update & Framework Refinement

Highlights

• Added framework-package duality -- dMG installs with PyPI.
• Overhauled tutorials and documentation.
• Restructured directories.
• Many bug fixes and small refinements.

What's Changed

• Module Loader Refactor by @leoglonz in #45
• Package management by @leoglonz in #48
• In pursuit of framework-package duality by @leoglonz in #49
• Dmg ngen by @leoglonz in #50
• At last, package backend by @leoglonz in #51
• Tutorial and docs update @leoglonz in #52

Full Changelog: v1.2.0...v1.2.1

v1.2.0

High-resolution differentiable model, 𝛿HBV2.0

This release incorporates the forwarding code of the high-resolution, differentiable hydrologic model, 𝛿HBV2.0UH, from Song, Yalan, Tadd Bindas, Chaopeng Shen, Haoyu Ji, Wouter Johannes Maria Knoben, Leo Lonzarich, Martyn P. Clark et al. "High-resolution national-scale water modeling is enhanced by multiscale differentiable physics-informed machine learning." Authorea Preprints (2024). https://essopenarchive.org/doi/full/10.22541/essoar.172736277.74497104. This paper is under review at Water Resources Research.

This code is built in a domain-agnostic, PyTorch-based framework for developing trainable differentiable models that merge neural networks with process-based equations. Following as a generalization of HydroDL, 𝛿MG (generic_deltaModel) aims to expand differentiable modeling and learning capabilities to a wide variety of domains where prior equations can bring in benefits. This package is maintained by the MHPI group advised by Dr. Chaopeng Shen.

The 𝛿MG package includes the lumped differentiable rainfall-runoff models, 𝛿HBV1.0, improved 𝛿HBV1.1p, and implicit adjoint-based 𝛿HBV.adj, and the high-resolution, differentiable hydrologic model, 𝛿HBV2.0. This package powers the global- and national-scale water model that provide high-quality seamless hydrologic simulations across US and the world. It also hosts global-scale ecosystem learning and simulations. Many other use cases are being developed concurrently.

v1.1.0

Introducing multiscale modeling

An initial implementation of multiscale modeling in dMG. See release v1.2.0 for production-ready implementation.

v1.0.0

𝛿MG First Release

Releasing 𝛿MG v1.0 framework, marking a formal start of the transition in differentiable modeling from hydroDL --> 𝛿MG + hydroDL2 collection of packages.

While this release is, first and foremost, in support of hydroDL and differentiable hydrology models developed by MHPI, it is just as much our goal to deliver an open source, model- and domain-agnostic framework for meaningful advancement in predictive modeling beyond hydrology.

--
Coming updates will primarily focus on documentation and tutorials, with larger refactors on the horizon after 25 Dec. 2024.