Weak gravitational lensing is a powerful cosmological probe that enables direct mapping of the matter distribution and precise constraints on the fundamental parameters governing structure formation in the universe. In recent years, machine learning has shown strong potential for extracting cosmological information from weak-lensing data beyond traditional summary statistics. However, progress has been limited by the lack of standardized benchmarks that capture the complexity of the dataset, simulator imperfections, and various systematic biases encountered in realistic analyses. To address this gap, we present the FAIR Universe Weak Lensing Machine Learning Uncertainty Challenge, one of the NeurIPS 2025 competitions, as a benchmark dataset and evaluation study. Our dataset reflects realistic weak-lensing observations, incorporating multiple systematic biases, and thereby providing a controlled testbed for robust cosmological inference under uncertainties. We summarize the main methodological advances developed by the winners of our challenge, including data augmentation with conditional optimal transport, an AI-agent-driven approach for parameter inference, ensemble learning, Vision Transformer-based architectures, and physics-informed feature integration. By unifying the benchmark dataset and the winning solutions, this work provides a community resource for developing and evaluating machine learning methods for weak lensing cosmology and, more broadly, for scientific inference under systematic uncertainties.
The atmospheric boundary layer (ABL) presents turbulence regimes that diverge from the classical Kolmogorov 1941 (K41) power-law spectrum widely assumed in optical atmospheric profiling, yet turbulence characterization for astronomical applications remains predominantly based on K41 assumptions. Using high-frequency sonic anemometer data from site-testing campaigns at the Giant Magellan Telescope (GMT) and Thirty Meter Telescope (TMT) sites in Chile, we apply detrended fluctuation analysis (DFA)---a technique from fractal time-series analysis---to identify the inertial sub-range and evaluate statistical isotropy in the ABL, comparing our approach with the Fourier-based algorithm for robust identification of the inertial subrange (ARIIS). Strict Kolmogorov conditions---simultaneous isotropy and $k^{-5/3}$ scaling across all fields---are satisfied in fewer than 7 per cent of observations. Temperature fields systematically decouple from velocity components under stable stratification, exhibiting Bolgiano-Obukhov scaling ($k^{-7/5}$) during nighttime hours, indicating active rather than passive scalar behaviour. DFA-detected regime transitions correlate with characteristic turbulence scales, providing objective, model-free boundaries for the inertial subrange. Comparative $C_n^2$ estimation reveals that structure function methods assuming K41 scaling diverge significantly from flux-based parameterizations under stable conditions. The rarity of true Kolmogorov conditions at these sites necessitates stratification-aware methodologies for accurate optical turbulence characterization at next-generation extremely large telescope facilities.
Space weather forecasting and heliophysics increasingly rely on machine learning models that process heterogeneous inputs such as multi-viewpoint multi-wavelength solar images and rasters, multivariate time series, spatial annotations, and tabular event-level data. However, explainability workflows remain fragmented across libraries, model interfaces, and output formats, limiting reuse and reproducibility. We present SWXAI, an open-source library that unifies explainable AI (XAI) workflows for image, time-series, and tabular data in space weather forecasting and heliophysics. SWXAI provides a common, extensible interface across commonly used vision, time-series, and tabular learning models, with validation, adaptation, and persistent explanation objects. It also includes domain-grounded examples, reproducible notebooks, tests, and documentation, enabling users to inspect outputs, swap models or explainers, and extend workflows to new heliophysics datasets. SWXAI reduces modality-specific engineering overhead and supports comparable, reusable explanations across heterogeneous scientific machine learning pipelines. A benchmark against direct backend implementations shows that SWXAI substantially reduces the code users write to produce an explanation, with no practical runtime cost.