Tessera
Folgen

Martin Gauch

@gauchm.bsky.social

Deep learning & earth science @ Google Research

14 Posts80 Follower111 Folgt
Frederik Kratzert@kratzert.bsky.social · 5mo ago

Excited to announce Groundsource - an open-source dataset of historic flood events! This has easily been one of the coolest projects I've worked on recently! Thread 🧵 for details and all relevant links. 1/n

A worldmap of the spatial distribution of extracted flood events in the Groundsource dataset. The map displays the total number of flood events extracted by the LLM-based pipeline aggregated per grid cell. The data are visualized using a Robinson projection, with event counts represented by a logarithmic color scale. Red points indicate the spatial centroids of reference flood events from the GDACS database.
Martin Gauch@gauchm.bsky.social · 7mo ago

New #NeuralHydrology release 🎉 Some news from v1.13.0: * CAMELS-IND & CAMELS-DE support * AORC hourly forcing support * xLSTM supportSupport for embedding layers in MTS-LSTMs ...and various other improvements and fixes. The full release notes: github.com/neuralhydrol... Thanks to all contributors!

Release v1.13.0 · neuralhydrology/neuralhydrology

Setup changes As of #279, NeuralHydrology switched from using conda environments to uv. This has several advantages (e.g., it's much faster to create environments, and we'll be able to get up-to-da...

github.com

Martin Gauch@gauchm.bsky.social · 9mo ago

It's (finally) published: hess.copernicus.org/articles/29/... Looking forward to all the different ways the title will be messed up by indexing tools!

How to deal w___ missing input data

Abstract. Deep learning hydrologic models have made their way from research to applications. More and more national hydrometeorological agencies, hydro power operators, and engineering consulting comp...

hess.copernicus.org

Martin Gauch@gauchm.bsky.social · last yr.

Starting on bsky with a new preprint: "How to deal w___ missing input data" doi.org/10.31223/X50... Missing input data is a very common challenge in deep learning for hydrology: weather providers have outages, some data products start later than others, some only exist for certain regions, etc.

Different scenarios for missing input data: outages at individual time steps (top), data products starting at different points in time (middle), and local data products that are not available for all basins (bottom). All of these scenarios reduce the number of training samples for models that cannot cope with missing data (yellow, small box), while the models presented in this paper can be trained on all samples with valid targets (purple, large box).
Frederik Kratzert@kratzert.bsky.social · last yr.

Now on HESSD for open discussion: egusphere.copernicus.org/preprints/20... They even let us keep the paper title (for now?!) 🙄

How to deal w___ missing input data

Abstract. Deep learning hydrologic models have made their way from research to applications. More and more national hydrometeorological agencies, hydro power operators, and engineering consulting comp...

egusphere.copernicus.org

Martin Gauch@gauchm.bsky.social · last yr.

Starting on bsky with a new preprint: "How to deal w___ missing input data" doi.org/10.31223/X50... Missing input data is a very common challenge in deep learning for hydrology: weather providers have outages, some data products start later than others, some only exist for certain regions, etc.

Different scenarios for missing input data: outages at individual time steps (top), data products starting at different points in time (middle), and local data products that are not available for all basins (bottom). All of these scenarios reduce the number of training samples for models that cannot cope with missing data (yellow, small box), while the models presented in this paper can be trained on all samples with valid targets (purple, large box).
Martin Gauch@gauchm.bsky.social · last yr.

Starting on bsky with a new preprint: "How to deal w___ missing input data" doi.org/10.31223/X50... Missing input data is a very common challenge in deep learning for hydrology: weather providers have outages, some data products start later than others, some only exist for certain regions, etc.

Different scenarios for missing input data: outages at individual time steps (top), data products starting at different points in time (middle), and local data products that are not available for all basins (bottom). All of these scenarios reduce the number of training samples for models that cannot cope with missing data (yellow, small box), while the models presented in this paper can be trained on all samples with valid targets (purple, large box).