arXiv subjects

Saptarishi Dhanuka

Publications and source records attributed to Saptarishi Dhanuka.

5 recordsLinked to original sources

arXiv2026

Steering Diffusion Priors with Sparse Observations for High-Resolution Temperature Downscaling

Local heatwave hazard depends on fine-scale air temperature, but ground stations are sparse and reanalysis products such as ERA5 cannot resolve the terrain and land-surface contrasts that shape real heat exposure. We present a conditional diffusion emulator for high-resolution 2-m temperature downscaling, conditioned on static geography, a training climatology, exact-time ERA5 temperature, and solar and temporal features, guided at inference by score-based data assimilation (SDA): a differentiable Gaussian observation likelihood steers the diffusion score toward sparse revealed temperature observations without any retraining. On a controlled 32-case synthetic-grid protocol over AORC, guidance improves hidden-cell reconstruction over both ERA5 and a strong observation-proximal nearest-neighbor baseline once observation density reaches 1\% (RMSE 0.318 vs.\ 0.431~K, winning all 32 cases), while sparser regimes still favor direct interpolation. We further map the full guidance-strength landscape across three observation densities, showing that the optimal strength shifts systematically with density and that over-guiding causes sharp, predictable degradation -- giving a concrete operating recipe rather than a single untuned setting. The resulting fields are intended as a temperature layer for downstream heatwave-hazard products such as threshold exceedance and cumulative heat-burden. The present evidence is a controlled synthetic-grid validation; station-network and held-out-year evaluations are the next steps toward deployment.

physics.ao-ph↗

arXiv2026

GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG

The Indian Summer Monsoon (ISM) is one of the most dynamically complex components of the global climate system, yet its accurate prediction remains challenging for both physics-based and emerging AI weather models. We present a climatological evaluation of Google's GraphCast against ERA5 reanalysis and the Integrated Multi-satellitE Retrievals for GPM (IMERG) precipitation dataset during the boreal summer (June-September, JJAS) for 2021-2024. Deterministic GraphCast forecasts initialized at 00 UTC are composited to evaluate +24 h, +48 h, and +72 h lead times over the full ISM domain. The analysis examines the climatological mean state (rainfall, surface temperature, and low-level winds), rainfall intensity distribution, thermodynamic structure (tropospheric temperature gradient, DTT; apparent heat source and moisture sink, Q1 and Q2), monsoon dynamics (vertical wind shear), and rainfall variability across intraseasonal, synoptic, and spectral timescales. GraphCast reproduces the broad spatial pattern and seasonal evolution of monsoon rainfall with good fidelity at short lead times but exhibits a domain-averaged wet bias over the core monsoon region. It also substantially suppresses rainfall variability across nearly all timescales (regional power-spectrum variance ratio of 0.14 relative to IMERG) and produces a compressed rainfall intensity distribution, overestimating moderately heavy rainfall (95th percentile) while systematically underrepresenting the most extreme events. These biases are accompanied by a deficient lower-tropospheric Q1 profile and weaker northward-propagating intraseasonal variability. Together, the results reveal a consistent deterministic-smoothing signature in GraphCast's precipitation forecasts and provide benchmark diagnostics for evaluating next-generation AI weather models for tropical medium-range forecasting (+24 h to +72 h).

physics.ao-ph↗

arXiv2026

Aircast-Mars: A Mars Foundation Model for Global Weather Forecasting with HEALPix-Aware Convolutions

Foundation models for planetary atmospheres promise fast, lightweight surrogates of expensive general circulation models (GCMs) for mission planning and scientific inquiry. Here we present Aircast-Mars, a deep-learning weather prediction system for Mars trained on the Ensemble Mars Atmosphere Reanalysis System (EMARS) v1.0. We regrid temperature, zonal wind, and meridional wind fields across 28 vertical levels onto a hierarchical equal-area isolatitude pixelization (HEALPix) mesh at Nside = 64 (~110 km resolution) and train a HEALPix-aware 2D U-Net inspired by the DLESyM architecture to predict the next hourly atmospheric state. The model employs custom inter-face padding that respects the topology of the 12-face HEALPix sphere and modern ConvNeXt residual blocks with capped Gaussian Error Linear Unit (GELU) activations. While containing 4.3 million trainable parameters, a compact size compared to terrestrial weather foundation models, the network achieves a best validation Mean Squared Error (MSE) of 1.58e-5 in normalized units. Recursive autoregressive rollouts remain stable and physically coherent for 25 hours (one Martian sol), with Root Mean Square Error (RMSE) growing monotonically from ~0.004 at t + 1 h to ~0.031 at t + 25 h without divergence. Compared to a baseline 3D U-Net, the HEALPix-aware architecture reduces validation loss by more than an order of magnitude while using fewer parameters. The model generates a one-hour forecast in approximately 0.5 seconds on a single GPU, offering several orders-of-magnitude speedup over traditional numerical GCMs. These results demonstrate that parsimonious, geometry-respecting neural architectures can capture synoptic-scale Martian atmospheric dynamics and provide a foundation for planetary-scale weather forecasting.

physics.ao-ph↗

arXiv2026

AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret

Recent advances in machine learning have produced probabilistic weather forecasting models comparable to state-of-the-art numerical weather predictors. But no model consistently dominates spatio-temporally, and relative performance is highly context-dependent. This motivates adaptive methods for combining multiple forecasts to obtain improvements and robustness. While combined forecasts have been proposed in the literature, these are achieved either through supervised learning or through prediction with expert advice methods. We introduce AdaWeather, an adaptive framework that combines many probabilistic forecasts using both machine learning as well as mixture of experts to arrive at a unified improved probabilistic forecast. While traditional expert methods develop the regret bounds with respect to the best single expert in hindsight, we extend the algorithm and analysis to show our method has logarithmic regret compared to the best static mixture of experts in hindsight. Empirically, we focus on forecasting temperature, and observe improvements over existing methods.

cs.LG↗

arXiv2026

AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion

Operational weather prediction at kilometer scales remains computationally prohibitive for traditional numerical weather prediction (NWP) models, limiting forecast access for applications in energy, agriculture, and disaster management that require fine-grained spatiotemporal detail. Here we introduce AirCast-SR, a foundation model for atmospheric super-resolution that downscales global AI weather forecasts from 0.25 degree (~28 km) to 1 km horizontal resolution at hourly temporal resolution, producing 67-hour forecasts of eight coupled surface variables simultaneously. EarthMind-SR employs a three-dimensional U-Net conditioned within a Latent Consistency Model (LCM) diffusion framework, trained on patch-based samples over the contiguous United States (CONUS) using GraphCast forecasts as input and NOAA's Analysis of Record for Calibration (AORC) as the target. The model achieves near-zero bias across all variables and lead times, and its radial power spectral density analysis demonstrates preservation of fine-scale atmospheric structure at wavelengths of 10 km to 100 km where coarser models lose spectral power. We validate EarthMind-SR across three CONUS case studies spanning winter, summer, and spring seasons, and demonstrate zero-shot global transferability over India and Germany using independent surface station observations without any retraining or fine-tuning. As an open-weights foundation model, EarthMind-SR establishes a new paradigm for kilometer-scale AI weather prediction and provides a platform for regional fine-tuning, distillation, and downstream applications in climate services and hazard forecasting.

cs.LG↗