Seeing Inside the Storm: Improving Nowcasting by Integrating Meteorological Drivers
Minghui Qiu, Jun Chen, Lin Chen, Weifeng Chen, Shuxin Zhong, Zhidan Liu, Yu Zhang, Kaishun Wu
https://arxiv.org/abs/2605.24067 https://arxiv.org/pdf/2605.24067 https://arxiv.org/html/2605.24067
arXiv:2605.24067v1 Announce Type: new
Abstract: Most nowcasting systems, built on radar reflectivity, focus on current precipitation, ignoring the atmospheric precursors -- such as low-level convergence, turbulent eddies, and latent heating -- that offer a fleeting window to foresee storm birth. We introduce MeteoLogist, a physics-inspired radar intelligence framework that models the full life cycle of convection -- from its precursors to organized storm evolution. However, exploiting these precursors is non-trivial: they originate from multiple meteorological drivers -- thermodynamic, kinematic, and microphysical -- that evolve asynchronously (C1) and remain spatially fragmented (C2). To this end, MeteoLogist designs three tightly integrated components. The Physics-Tailored Encoders process radar echoes according to their intrinsic physical scales and semantics, forming thermodynamic, kinematic, and microphysical streams that capture distinct dynamical regimes. The Temporal-Phase Aligner addresses C1 by leveraging causal temporal attention to capture when and how different drivers interact and activate. The Cross-Field Spatial Aggregator addresses C2 through cross-regional fusion, aligning weak and scattered precursors across neighboring cells to expose upstream triggers and enforce spatial coherence. Evaluated on 3D-NEXRAD (2020--2022, US-wide), MeteoLogist boosts high-impact detection (CSI40) by 9.7% over strong baselines, and achieves a remarkable 37.67% gain during the storm-developing stage -- demonstrating true foresight in sensing storms before they appear. The code can be found in the supplementary material.
toXiv_bot_toot
Hey Seattle/Portland friends.
Look out for information about this missing person. She was found, nearly dead, in the water near Vancouver BC in 2022. She died the next day, unidentified.
New analysis of pollen on her clothing indicates she might have just arrived to BC from the Seattle or Portland areas.
Apparently BC RCMP will be doing a news conference in the USA in the near future to try to find anyone who might recognize her.
#MissingPerson #Vancouver #YVR #Seattle #Portland #TheKayaker
Lost Not Stolen--The Conservative Case that Trump Lost and Biden Won the 2020 Presidential Election (July 2022).pdf - Google Drive
https://drive.google.com/file/d/1aqorZ61AYFqZU-EDQBBzjqfvAoC5nKcB/view
The CFTC files alongside Gemini to nullify Gemini's $5M settlement in January 2025, arguing that the agency's current management wouldn't have pursued the case (Jesse Hamilton/CoinDesk)
https://www.coindesk.com/policy/2026/05/27
In 2022, I won the Arizona governorship by 0.7 points
against a candidate who refused to concede and still claims I stole the election.
I’m Katie Hobbs.
I know what election denial looks like up close
– it looked like Kari Lake standing outside my office telling her followers I was a criminal.
Now Andy Biggs wants my job.
Biggs didn’t just question the 2020 results. He voted against certifying them.
He called Arizona state lawmakers to find ways to …
at_migrations: Austrian internal migrations (2002-2022)
A network of migrations between municipalities in Austria, from 2002 to 2022. A weighted directed link from source to target indicates a migration flow from these two municipalities. Edges are annotated with migration volume (number of people), nationality, sex, and year.
This network has 2115 nodes and 2908569 edges.
Tags: Social, Economic, Travel, Weighted, Politlcal, Timestamps, Metadata
faculty_hiring_us: Faculty hiring networks in the US (2022)
Networks of faculty hiring for all PhD-granting US universities over the decade 2011–2020. Each node is a PhD-granting institution, and a directed edge (i,j) indicates that a person received their PhD from node i and was tenure-track faculty at node j during time of collection (2011-2020). This dataset is divided into separate networks for all 107 fields, as well as aggregate networks for 8 domains, and an overall network for …
@arXiv_physicsaoph_bot@mastoxiv.page
