{"paper":{"title":"A plug-and-play generative framework for multi-satellite precipitation estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"PRISMA learns an unconditional precipitation prior from merged satellite fields and constrains it with independently trained sensor branches to fuse infrared and microwave data without full retraining.","cross_cats":["cs.AI"],"primary_cat":"physics.ao-ph","authors_text":"Haofei Sun, Hao Li, Jun Li, Wei Han, Wei Huang, Xiaoze Xu, Xingtao Song, Xiuyu Sun, Yunfan Yang, Zhiqiu Gao","submitted_at":"2026-05-14T06:18:53Z","abstract_excerpt":"Reliable precipitation monitoring is essential for disaster risk reduction, water resources management, and agricultural decision-making. Multi-source satellite observations, particularly the combination of geostationary infrared and passive microwave measurements, have become a primary means of precipitation detection. Traditional multi-source satellite precipitation estimation methods remain computationally inefficient, and many deep learning methods lack the flexibility to incorporate new sensors without retraining the full model. Here we introduce PRISMA (Precipitation Inference from Satel"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Applied to FY-4B AGRI infrared and GPM GMI microwave observations, PRISMA improves Critical Success Index by up to 40.3% and reduces root-mean-square error by 22.6% relative to infrared-only estimation within microwave swaths, while also improving probabilistic skill.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an unconditional precipitation prior learned from IMERG Final fields can be effectively constrained by independently trained sensor-specific conditional branches without loss of accuracy or the need for joint retraining when adding new observation sources.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PRISMA introduces a plug-and-play latent generative model that improves multi-sensor precipitation estimates by learning an unconditional prior from IMERG data and constraining it with independent sensor-specific branches.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PRISMA learns an unconditional precipitation prior from merged satellite fields and constrains it with independently trained sensor branches to fuse infrared and microwave data without full retraining.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"52cb36740d448b6e7fa592b955172385cb39d14790adf458d5819fb528ee9452"},"source":{"id":"2605.14426","kind":"arxiv","version":1},"verdict":{"id":"9049df2e-ec25-46ea-a991-6eb0ee722b38","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:43:53.642080Z","strongest_claim":"Applied to FY-4B AGRI infrared and GPM GMI microwave observations, PRISMA improves Critical Success Index by up to 40.3% and reduces root-mean-square error by 22.6% relative to infrared-only estimation within microwave swaths, while also improving probabilistic skill.","one_line_summary":"PRISMA introduces a plug-and-play latent generative model that improves multi-sensor precipitation estimates by learning an unconditional prior from IMERG data and constraining it with independent sensor-specific branches.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That an unconditional precipitation prior learned from IMERG Final fields can be effectively constrained by independently trained sensor-specific conditional branches without loss of accuracy or the need for joint retraining when adding new observation sources.","pith_extraction_headline":"PRISMA learns an unconditional precipitation prior from merged satellite fields and constrains it with independently trained sensor branches to fuse infrared and microwave data without full retraining."},"references":{"count":47,"sample":[{"doi":"","year":1970,"title":"Technical Report WMO- No","work_id":"4eeceee0-c49f-4eb6-bb40-54e8ead51001","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Contribution of Work- ing Group I to the Sixth Assessment Report","work_id":"811a436d-5bb6-4877-bcb9-a1d8fb4a9c0e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Dai, T.-Y., Ushijima-Mwesigwa, H.: PrecipDiff: Leveraging image diffusion models to enhance satellite-based precipitation observations (2025)","work_id":"fcacda73-c7b7-4f1d-8487-8d39882edc45","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Brempong, E.A., Hassen, M.A., MohamedKhair, M., Dube, V., Hincapie Potes, S., Graham, O., Brik, A., McGovern, A., Huffman, G.J., Hickey, J.: Oya: Deep learning for accurate global precipitation estima","work_id":"91153eba-9d3e-4cc5-bbaa-3c14763d75e3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Technical Report WMO-No","work_id":"323c2d81-2e56-4efb-b413-444c6eeee1ca","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":47,"snapshot_sha256":"afc7403c728b2fb4e11e26b615011368944866d98bc713b0580bdeb5b3231d67","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"73f71448fa3d01a43575c593f822e277b84e59af7bb18895c914999071243820"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}