{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T16:20:26Z","timestamp":1788366026728,"version":"build-2803163510"},"reference-count":0,"publisher":"American Meteorological Society","license":[{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.ametsoc.org\/PUBSReuseLicenses"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Quasi-stationary convective bands over Kyushu, Japan, frequently trigger rainy-season disasters, and hours with \u226550 mm h\n                    <jats:sup>\u22121<\/jats:sup>\n                    rainfall are increasing. However, skillful nowcasts beyond 3 h remain limited. This study presents FlowsNet, an observation-based multisensor fusion model that learns directly from radar\/rain gauge-analyzed precipitation, surface variables from ground stations, geostationary satellite imagery, and satellite-derived precipitation context. The model targets category-4 (C4; \u226550 mm h\n                    <jats:sup>\u22121<\/jats:sup>\n                    ) rainfall and incorporates two attention mechanisms: a channel-wise module that weights informative modalities and a spatial module that aligns features with banded structures at multi-hour leads. Training uses a tail-aware ordinal loss that couples focal reweighting with an Earth Mover\u2019s Distance-based ordinal penalty to emphasize rare extremes. FlowsNet maintains a non-zero C4 Critical Success Index through 6 h. From 4 to 6 h, it matches or exceeds the Japan Meteorological Agency\u2019s very-short-range forecast, and it outperforms a leading extrapolation-based method and state-of-the-art deep learning nowcasting models. Case studies show preserved band geometry and corridor placement at long lead over complex terrain. Ablation experiments identify satellite water vapor context and near-surface humidity as key for long-lead C4 prediction; combining satellite context with surface observations stabilizes placement and reduces false alarms. By avoiding numerical weather prediction model state and objective analyses\/reanalyzes, the approach reduces latency and hardware demand, improves portability and resilience when model cycles degrade, and offers a practical route to earlier and more transferable warnings for extreme-rainfall events.\n                  <\/jats:p>","DOI":"10.1175\/aies-d-25-0117.1","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T15:54:33Z","timestamp":1788364473000},"source":"Crossref","is-referenced-by-count":0,"title":["An NWP-Free, Observation-Driven Deep Learning Approach to Heavy-Rainfall Nowcasting Beyond the Three-Hour Limit"],"prefix":"10.1175","author":[{"given":"Ryu","family":"Shimabukuro","sequence":"first","affiliation":[{"name":"a Graduate School of Science and Technology, Kumamoto University, Kumamoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomohiko","family":"Tomita","sequence":"additional","affiliation":[{"name":"b Faculty of Advanced Science and Technology, Kumamoto University, Kumamoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsuyoshi","family":"Yamaura","sequence":"additional","affiliation":[{"name":"c RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken-ichi","family":"Fukui","sequence":"additional","affiliation":[{"name":"d Faculty of Business Data Science, Kansai University, Suita, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"12","container-title":["Artificial Intelligence for the Earth Systems"],"original-title":[],"link":[{"URL":"https:\/\/journals.ametsoc.org\/view\/journals\/aies\/aop\/AIES-D-25-0117.1\/AIES-D-25-0117.1.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.ametsoc.org\/downloadpdf\/journals\/aies\/aop\/AIES-D-25-0117.1\/AIES-D-25-0117.1.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T15:54:34Z","timestamp":1788364474000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.ametsoc.org\/view\/journals\/aies\/aop\/AIES-D-25-0117.1\/AIES-D-25-0117.1.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,2]]},"references-count":0,"URL":"https:\/\/doi.org\/10.1175\/aies-d-25-0117.1","relation":{},"ISSN":["2769-7525"],"issn-type":[{"value":"2769-7525","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,2]]}}}