AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolants

Martin Andrae, Erik Wikingsson, So Takao, Tomas Landelius, Fredrik Lindsten

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Data assimilation from sparse observations · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add inverse sampling of forecast ensemble before guided sampling (ablation)DAISI · L63RMSE: 5.90 -> 2.03Improved
tune tmin (instead of tmin near 0) with eps=0 (ablation)DAISI · L63RMSE: 7.04 -> 2.44Improved
tmin near 0 and eps=0 without tuning (ablation)DAISI · L63CRPS: 7.17 (no inversion) -> 11.9Hurt
add nonzero eps in addition to tuned tmin (ablation)DAISI · L63SSR: 0.32 -> 1.08Improved
add nonzero eps in addition to tuned tmin (ablation)DAISI · L63CRPS: 3.19 -> 2.61Improved
add nonzero eps in addition to tuned tmin (ablation)DAISI · L63RMSE: 2.05 -> 2.03No clear effect
intermediate tmin (0.3) versus 0.01 or 0.6 (ablation)DAISI · 1D toy problemMMD: 0.15 / 0.29 -> 0.03Improved
use DAISI instead of FlowDAS filteringSQG forecast model · SQG SparseCRPS: 3.34 -> 1.73Improved
replace numerical model with FlowDAS learned forecast model (DAISI-ML) (ablation)DAISI · SQG SparseCRPS: 1.73 -> 1.72No clear effect
DAISI vs LETKF under saturating arctan observationsSQG Saturating · SQG SaturatingCRPS: 5.24 -> 1.54Improved
DAISI vs EnSF under saturating observationsSQG Saturating · SQG SaturatingCRPS: 1.33 (EnSF) vs 1.54No clear effect
DAISI vs LETKF with noisy linear observationsSQG Noisy · SQG NoisyCRPS: 1.34 -> 1.32No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy