Alberto Carpentieri

pySTEPS/pysteps: pysteps v1.21.5

Daniele Nerini, Seppo Pulkkinen, Andres Perez Hortal, Carlos Velasco et autres

What's Changed fix memory usage when precip nowcast is passed to steps blending by @mats-knmi in https://github.com/pySTEPS/pysteps/pull/570 bump version to v1.21.5 by @RubenImhoff in https://github.com/pySTEPS/pysteps/pull/571 Full Changelog: https://github.com/pySTEPS/pysteps/compare/v1.21.4...v1.21.5

ch, au, fi, be, at, de, gb, us (code pays fourni par la source)

pySTEPS/pysteps: pysteps v1.21.4

Daniele Nerini, Seppo Pulkkinen, Andres Perez Hortal, Carlos Velasco et autres

What's Changed Fix issue with external ensemble nowcast for steps blending and no additional noise by @mats-knmi in https://github.com/pySTEPS/pysteps/pull/564 Fix boxplot labels for Matplotlib 3.11 by @dnerini in https://github.com/pySTEPS/pysteps/pull/567 Fix external nowcast only zeros by @mats-knmi in https://github.com/pySTEPS/pysteps/pull/566 Fix TypeError when timesteps …

ch, au, fi, be, at, de, gb, us (code pays fourni par la source)

pySTEPS/pysteps: pysteps v1.21.3

Daniele Nerini, Seppo Pulkkinen, Andres Perez Hortal, Carlos Velasco et autres

What's Changed fix: extend knmi importer with support for other projections by @mats-knmi in https://github.com/pySTEPS/pysteps/pull/562 Bump version by @mats-knmi in https://github.com/pySTEPS/pysteps/pull/565 Full Changelog: https://github.com/pySTEPS/pysteps/compare/v1.21.2...v1.21.3

ch, au, fi, be, at, de, gb, us, ca (code pays fourni par la source)

pySTEPS/pysteps: pysteps v.1.21.2

Daniele Nerini, Seppo Pulkkinen, Andres Perez Hortal, Carlos Velasco et autres

What's Changed Add complevel argument to netcdf exporter + tests by @ladc in https://github.com/pySTEPS/pysteps/pull/550 553 blending weights calculation overwrites weights of other ensemble members by @larsbonnefoy in https://github.com/pySTEPS/pysteps/pull/554 fix: removed hardcoded conditional=True for noise statistic computation by @larsbonnefoy in https://github.com/pySTEPS/pysteps/pull/556 Full Changelog: …

ch, au, fi, be, at, de, gb, us, ca (code pays fourni par la source)

pySTEPS/pysteps: pysteps v1.21.1

Daniele Nerini, Seppo Pulkkinen, Andres Perez Hortal, Carlos Velasco et autres

What's Changed Add pysteps version to netcdf source metadata. by @ladc in https://github.com/pySTEPS/pysteps/pull/547 fix only zeros when using external nowcast by @mats-knmi in https://github.com/pySTEPS/pysteps/pull/546 fix: issue with example code by @mats-knmi in https://github.com/pySTEPS/pysteps/pull/549 Full Changelog: https://github.com/pySTEPS/pysteps/compare/v1.21.0...v1.21.1

ch, au, fi, be, at, de, gb, us, ca (code pays fourni par la source)

pySTEPS/pysteps: pysteps v1.21.0

Daniele Nerini, Seppo Pulkkinen, Andres Perez Hortal, Carlos Velasco et autres

What's Changed Add Farneback motion estimation method by @dominique-brunet-eccc in https://github.com/pySTEPS/pysteps/pull/542 Support for mixed precip/noprecip input and AR order 1 by @ladc and @FelixE91 in https://github.com/pySTEPS/pysteps/pull/544 New Contributors @dominique-brunet-eccc made their first contribution in https://github.com/pySTEPS/pysteps/pull/542 Full Changelog: https://github.com/pySTEPS/pysteps/compare/v1.20.0...v1.21.0

ch, au, fi, be, at, de, gb, us, ca (code pays fourni par la source)

ML-based time interpolation of AIFS Ensemble for renewable energy forecasting

Hans Brenna Schjønberg, Riccardo Parviero, Marius Koch, Alberto Carpentieri

Recent advancements in machine learning based weather prediction (MLWP) present novel opportunities for downstream applications like forecasting of renewable energy production from intermittent sources, like wind and solar. MLWP models guarantee shorter simulation run times and lower computational costs, allowing faster updates …

us (code pays fourni par la source)

pySTEPS/pysteps: pysteps v.1.20.0

Daniele Nerini, Seppo Pulkkinen, Andres Perez Hortal, Carlos Velasco et autres

What's Changed Fix typo in fft generators kwargs by @geek-yang in https://github.com/pySTEPS/pysteps/pull/538 Fix pandas-compatible scalar assignment in tdating by @dnerini in https://github.com/pySTEPS/pysteps/pull/539 Allow for possibility to end with full NWP weight at end of blending by @RubenImhoff in https://github.com/pySTEPS/pysteps/pull/536 Add None to …

ch, au, fi, be, at, de, gb, us, ca (code pays fourni par la source)

pySTEPS/pysteps: pysteps v1.19.1

Daniele Nerini, Seppo Pulkkinen, Andres Perez Hortal, Carlos Velasco et autres

What's Changed fix: Advection of domain mask for smooth blending at domain edges in reduced-space EnKF by @m-rempel in https://github.com/pySTEPS/pysteps/pull/533 Full Changelog: https://github.com/pySTEPS/pysteps/compare/v1.19.0...v1.19.1

ch, au, fi, be, at, de, gb, ca, us (code pays fourni par la source)

Data-driven solar forecasting enables near-optimal economic decisions

Zhixiang Dai, Minghao Yin, Xuanhong Chen, Alberto Carpentieri et autres

Solar energy adoption is critical to achieving net-zero emissions. However, it remains difficult for many industrial and commercial actors to decide on whether they should adopt distributed solar-battery systems, which is largely due to the unavailability of fast, low-cost, and high-resolution irradiance …

Probabilistic solar radiation forecasting across Europe using deep learning

Angela Meyer, Kevin Schuurman, Alberto Carpentieri

Solar energy plays a major role in climate change mitigation. With rising shares of solar power in the grid, short-term forecasts of surface solar irradiance (SSI) are becoming increasingly important for grid operators to enable cost-efficient supply and demand balancing. Solar nowcast …

ch, nl (code pays fourni par la source)

Attention on the Sphere

Boris Bonev, Max Rietmann, Andrea Paris, Alberto Carpentieri et autres

We introduce a generalized attention mechanism for spherical domains, enabling Transformer architectures to natively process data defined on the two-dimensional sphere - a critical need in fields such as atmospheric physics, cosmology, and robotics, where preserving spherical symmetries and topology is essential …

ch, gb (code pays fourni par la source)