Sign in

David Montero Loaiza

@dmlmont.bsky.social
104 followers 29 following 1 posts

Creator of #AwesomeSpectralIndices | #eemont | #spectral PhD Student @RSC4Earth #EarthEngine GDE

PostsRepliesMedia
David Montero Loaiza @dmlmont.bsky.social · 22/01/2024
BIG NEWS! 😁 I'm happy to announce that cubo v2024.1.0 can create cubes from Google Earth Engine in addition to STAC catalogues! gh: github.com/ESDS-Leipzig... Check the tutorial here: cubo.readthedocs.io/en/latest/tu...
1101
Reposted by David Montero Loaiza
Maximilian Söchting @soechting.bsky.social · 18/01/2024
Big news from #Lexcube! 🌍 We have released Lexcube for Jupyter, an open-source Jupyter notebook extension that allows everyone to visualize their own 3D data as interactive data cubes, right in their notebooks! And the best part: it is as easy as plotting a 2D figure! github.com/msoechting/l...
193
Reposted by David Montero Loaiza
Miguel D. Mahecha @miguelmahecha.bsky.social · 11/12/2023
The Planetary Boundary concept is based on a strong visualisation. However, we argue that (1) the PB figure exaggerate via quadratic scaling of effect sizes, (2) colour gradations are highly non-linear, and (1)+(2) amplifies the perception of high-risk areas: egusphere.copernicus.org/preprints/20...
2113
Reposted by David Montero Loaiza
Lily-belle Sweet @lilybellesweet.bsky.social · 16/10/2023
Researchers often use interpretable machine learning tools like feature importances to identify drivers, but cross-validation strategy used can affect these results: Our open access study in AIES doi.org/10.1175/AIES... (with co-authors Jakob Zscheischler, Christoph Müller, Mohit Anand)
doi.org
Cross-Validation Strategy Impacts the Performance and Interpretation of Machine Learning Models
Abstract Machine learning algorithms are able to capture complex, nonlinear, interacting relationships and are increasingly used to predict agricultural yield variability at regional and national scal...
092
Reposted by David Montero Loaiza
Miguel D. Mahecha @miguelmahecha.bsky.social · 18/10/2023
My amazing PhD student Maximilan Söchting published his first paper on a fully interactive viewer for very large Earth data: www.lexcube.org Please try it out! Paper published in IEEE Computer Graphics and Applications ieeexplore.ieee.org/document/102...
051
Reposted by David Montero Loaiza
Miguel D. Mahecha @miguelmahecha.bsky.social · 18/10/2023
Happy for PhD cand Francesco Martinuzzi for having is paper in discussion comparing various RNNs in modelling vegetation responses ... there are still arguments for #ESNs, but all models struggled to capture impact of extremes. More research needed! 🌱🌍 🔗https://doi.org/10.5194/egusphere-2023-2368
063