AI for science & health

AI applied to biology, chemistry, physics, medicine, climate and other sciences

67 articles · page 2 of 2

AI for science & health

Neural surrogates accelerate linear radiation transport simulations on key benchmarks

The authors benchmarked two neural surrogate architectures, Transolver and BSMS-MGN, as end-to-end approximations of the final-time particle concentration for the two-dimensional linear radiation transport equation on canonical Lattice and Hohlraum benchmarks. They found that both surrogates generally outperform coarse conventional solvers, but that architectural choices such as Fourier features and region-weighted loss must be tuned per model family for optimal accuracy.

·2 min
AI for science & health

QiYao-I models irregular timing and asynchronous variables in one forecaster

Wang and colleagues introduce QiYao-I, a foundation model for forecasting multivariate time series whose measurements are unevenly spaced and not synchronized across variables. The authors report that it outperforms both general time-series foundation models and specialized irregular forecasting systems, including in zero-shot and few-shot evaluations, although the supplied text does not include numerical results.

·2 min
AI for science & health

Diagnosis-first framework boosts solver performance across numerical domains

The authors introduce ADSD, a diagnosis-first framework that separates solver improvement into three stages: observing behavior, diagnosing underlying numerical conditions, and discovering targeted methods packaged as reusable skills. Across four challenging numerical domains, ADSD consistently improves solver accuracy, robustness, and efficiency, with a 71x error reduction on the GOC-500 power flow benchmark and transfer to unseen topologies.

·3 min
AI for science & health

Soft routing among process experts helps PDE forecasting, but gains prove seed-dependent

The authors propose COSMOS, a neural operator that densely mixes four process-biased specialists with a learned continuous gate instead of sparse top-K expert selection. On PDEBench families, a locked three-seed run beat a tuned FNO on diffusion-reaction and matched it on Navier-Stokes, but an 11-seed audit showed the diffusion-reaction gain was unstable. Soft routing beat hard top-1 routing by 2.2x in error, yet replacing the learned gate with the generator's true mixture weights further lowered error, and routing labels did not align with physical mechanisms.

·3 min
AI for science & health

SCOPE recovers complete PDE fields from sparse observations via mask-conditioned latent prediction.

The authors propose SCOPE, a deterministic single-pass model that reconstructs complete PDE fields from sparse measurements by coupling full-target latent prediction with a shared physical decoder. Across five PDE settings, SCOPE outperformed mask-aware neural operators on all ten tasks and reported lower errors than diffusion-based solvers DiffusionPDE and FunDPS. A quadratic risk decomposition shows why optimal latent prediction need not yield optimal field reconstruction, and a separate bound characterizes when decoder improvements transfer.

·2 min
AI for science & health

Ocean emulator runs on unstructured mesh, beating baselines for currents

The authors present HClimRep-Ocean, a machine-learning emulator that operates directly on the unstructured computational mesh of the FESOM2 ocean model. Trained on a 209-year control simulation, the model forecasts ocean currents more accurately than all reference methods at 30-day lead times, though temperature and salinity predictions are less skilled than a simple damped-anomaly persistence forecast. The authors also demonstrate competitive performance on the OceanBench benchmark against a reanalysis product.

·3 min
AI for science & health

Joint deterministic-generative model extends reliable extreme-precipitation nowcasting to six hours

The authors present MW-Nowcast, a six-hour ensemble radar nowcasting model that jointly learns a deterministic predictor for organized precipitation structure and a generative flow-matching model for local residuals. The model doubles the available warning time for the most intense rainfall, delivering 6 h forecasts with skill previously confined to 3 h for the leading generative baseline.

·3 min
AI for science & health

Real tumor board discussions expose gaps in medical language models

Li and colleagues built OpenTumorBoard from recordings of real multidisciplinary cancer discussions, preserving the sequence of questions, specialist responses and consensus decisions. Testing 14 general-purpose and medical language models showed that even the strongest systems remained substantially below full clinical equivalence, although supervised finetuning and reinforcement learning improved results on held-out cases.

·2 min
AI for science & health

Incomplete inputs impose unavoidable limits on blind radiomap prediction

Li et al. develop a population-level theory for predicting radio coverage maps from incomplete descriptions of environments and base stations, without field measurements. They show that deterministic models optimally target the conditional mean radiomap, and report that their RadioDecomp framework improves two different propagation-prior baselines across random, unseen-configuration, and unseen-environment tests.

·2 min
AI for science & health

Dual-layer knowledge graph connects fragmented pharmaceutical process-development documents

Amirmoshiri, Sahneh and Jangjou built an agentic platform that transforms heterogeneous Chemistry, Manufacturing and Controls documents into a queryable, provenance-linked knowledge graph. On 505 questions drawn from 38 reports for one Sanofi small-molecule program, the lexical retrieval layer performed strongly on direct questions but weakened on comparative and corpus-wide queries.

·2 min
AI for science & health

Paper-derived rubrics improve AI generation of scientific research plans

The authors turn 20,000 scientific papers into training environments for research-plan generation, deriving prompts from each paper’s goals and background while extracting evaluation criteria from its methods and experiments. Across three Qwen3 model sizes, their rubric-centered training schedule produced higher benchmark scores than supervised fine-tuning, either training stage alone, or the same stages in reverse order.

·2 min
AI for science & health

Learned sepsis score tracks hourly severity without hourly outcome labels

The authors trained a 0–10 sepsis severity index from 43 routinely charted variables collected over 72 hours, using treatment-level mortality to rank trajectories rather than assigning mortality labels to every hour. In held-out testing, the score provided hourly prognostic information, correlated with changes in lactate and other physiological measures, and showed partial transfer between hospital systems.

·2 min