Accurate detection and quantification of uncertainty in anomalous climate events are needed to improve our understanding of climate extremes, particularly snow and ice melt processes in the polar regions. Despite the advances in anomaly detection methods, existing frameworks often neglect uncertainties inherent in spatiotemporal processes, leading to unreliable anomaly detection. We propose an uncertainty-aware anomaly detection framework that integrates measurement uncertainty and modeling bias. Our approach leverages the Three-Cornered-Hat (3CH) error variance estimator to quantify input uncertainties and incorporate them into the anomaly detection process through an uncertainty-weighted loss function and Monte Carlo Dropout (MCD) for total predictive uncertainty estimation. Using our approach, we detect and evaluate the uncertainty associated with anomalies from three surface melt products (ERA5, MAR, GEMB) of the Greenland Ice Sheet surface. Experiments on synthetic datasets and modeling output demonstrate that our uncertainty-aware method significantly enhances anomaly detection reliability, reducing false positives and improving detection confidence. Our results across the three models provide robust insights into the simulation of ice sheet surface melt dynamics, highlighting that GEMB, which includes the most complex physical representation of snow evolution, exhibits the strongest reliability in detecting melt regions with low uncertainty. Our findings provide insights into the simulation of ice sheet surface melt dynamics and underscore the importance of uncertainty quantification in Earth system modeling.

Greenland ice loss contributes approximately 0.7 mm per year to current sea level rise, making process attribution critical for future projections. Mass balance attribution in ice sheets requires distinguishing between surface processes (accumulation, ablation) and subsurface processes (submarine melting, dynamic discharge). Existing approaches lack systematic integration of glaciological process knowledge for robust spatial attribution. We present a physics-guided multi-contextual analysis framework. We construct process-specific variables using fundamental ice sheet mass balance principles. We create spatial neighborhoods through Voronoi polygon construction and feature similarity assessment, then apply Local Indicators of Spatial Association (LISA) to identify process dominance patterns. We advance beyond conventional spatial statistics by systematically deriving physics-informed indicators that isolate distinct mass balance components. We test our framework on Southeast Greenland using 18 years of reanalysis and satellite data (2004–2021). Our results show that subsurface processes control ice loss across 37–46% of the study area, concentrated in northern regions of Southeast Greenland, while surface processes dominate only 6–7% of the area in southern locations of Southeast Greenland. When we compare our spatial findings with the documented glacier behavior from recent studies in Greenland, we find strong agreement that validates our process attribution approach.

The focus of our work is improving the interpretability of anomalies in climate models and advancing our understanding of Arctic melt dynamics. The Arctic and Antarctic ice sheets are experiencing rapid surface melting and increased freshwater runoff, contributing significantly to global sea level rise. Understanding the mechanisms driving snowmelt in these regions is crucial. ERA5, a widely used reanalysis dataset in polar climate studies, offers extensive climate variables and global data assimilation. However, its snowmelt model employs an energy imbalance approach that may oversimplify the complexity of surface melt. In contrast, the Glacier Energy and Mass Balance (GEMB) model incorporates additional physical processes, such as snow accumulation, firn densification, and meltwater percolation/refreezing, providing a more detailed representation of surface melt dynamics. In this research, we focus on analyzing surface snowmelt dynamics of the Greenland Ice Sheet using feature attribution for anomalous melt events in ERA5 and GEMB models. We present a novel unsupervised attribution method leveraging counterfactual explanation method to analyze detected anomalies in ERA5 and GEMB. Our anomaly detection results are validated using MEaSUREs ground-truth data, and the attributions are evaluated against established and new feature ranking methods, including XGBoost, Shapley values, Random Forest, and Layer-wise Relevance Propagation. Our attribution framework identifies the physics behind each model and the climate features driving melt anomalies. These findings demonstrate the utility of our attribution method in enhancing the interpretability of anomalies in climate models and advancing our understanding of Arctic melt dynamics.

We present a concept for UHF/L-band (0.5–2 GHz) remote sensing of Antarctic ice sheet internal temperature using a highly sparse synthetic aperture radiometer constellation. This concept leverages the relative stability of ice sheet thermal emission over long temporal periods to gradually assemble a collection of array baselines which are jointly transformed to develop large image facets. We formulate a calculation of minimum array complexity based on the desired sensitivity, spatial resolution, and time available for observations. We determine from this calculation that such a system can achieve 1–10-km spatial resolution (significantly finer than the program of record) over monthly to yearly timescales with as few as 10–20 elements; even fewer elements are required for observing only the ice sheet center. The inverse problem of reconstructing image facets from mixed-pointing and mixed-configuration observations is posed using a Fourier domain data constraint with a total variational regularization in the image domain. This approach enables image formation from heterogeneous observations while mitigating artifacts. We present a notional constellation design for three satellites which could accomplish the necessary baseline sampling by rotating the phase and semimajor axis of spacecraft relative positions in planar circular orbits (PCOs). We demonstrate image formation by observing system simulations leveraging predictions of Antarctica’s multiwavelength brightness temperature computed from ice sheet thermomechanical and radiative transfer models.

We introduce an anomaly detection method for multivariate time series data with the aim of identifying critical periods and features influencing extreme climate events like snowmelt in the Arctic. This method leverages Variational Autoencoder (VAE) integrated with dynamic thresholding and correlationbased feature clustering. This framework enhances the VAE’s ability to identify localized dependencies and learn the temporal relationships in climate data, thereby improving the detection of anomalies as demonstrated by its higher F1-score on benchmark datasets. The study’s main contributions include the development of a robust anomaly detection method, improving feature representation within VAEs through clustering, and creating a dynamic threshold algorithm for localized anomaly detection. This method offers explainability of climate anomalies across different regions.

The warming of the Arctic, also known as Arctic amplification, is led by several atmospheric and oceanic drivers. However, the details of its underlying thermodynamic causes are still unknown. Inferring the causal effects of atmospheric processes on sea ice melt using fixed treatment effect strategies leads to unrealistic counterfactual estimations. Such methods are also prone to bias due to time-varying confoundedness. Further, the complex non-linearity in Earth science data makes it infeasible to perform causal inference using existing marginal structural techniques. In order to tackle these challenges, we propose TCINet - Time-series Causal Inference Network to infer causation under continuous treatment using recurrent neural networks and a novel probabilistic balancing technique. More specifically, we propose a neural network based potential outcome model using the long-short-term-memory (LSTM) layers for time-delayed factual and counterfactual predictions with a custom weighted loss. To tackle the confounding bias, we experiment with multiple balancing strategies, namely TCINet with the inverse probability weighting (IPTW), TCINet with stabilized weights using Gaussian Mixture Model (GMMs) and TCINet without any balancing technique. Through experiments on synthetic and observational data, we show how our research can substantially improve the ability to quantify leading causes of Arctic sea ice melt, further paving paths for causal inference in observational Earth science.

We discuss an approach to measuring high-resolution maps of Antarctic ice sheet temperatures using repeat-pass sparsely sampled microwave interferometry. This approach follows from the inference that the relative invariance of ice sheet temperatures on annual timescales obviates the need for high snapshot sensitivity imposed as a requirement for observing more variable regions of the Earth system with interferometers such as SMOS. Such measurements could hypothetically be conducted with spatial resolutions less than 10 km using a small constellation of satellites. We discuss specifically how modifications to sheet-base geothermal heat flux could manifest as observable thermal signatures and a strategy to form images from a mosaic of multiple heterogeneous sparsely sampled observations, and we conclude with comments on necessary areas for future investigations.

Climate data related to polar regions has been extensively studied through model simulations, remote sensed images, and statistical analysis. Knowledge discovery tasks, if applied to the Arctic data, can capture the associations, anomalies, and interesting patterns and trends that exist in the data to inform the polar scientists. This can help improve the certainty in the models with better local information. In this study, we propose a framework that develops multi-contextual spatiotemporal neighborhoods, addressing spatial autocorrelation and heterogeneity taking into account data from multiple views or contexts, to identify local homogeneous regions across the entire Greenland Ice Sheet. Using these neighborhoods, we study how local regions in the Greenland ice sheet evolve over time. This framework can expand to include additional contextual variables and help polar scientists study local ice surface melt phenomena across multiple contexts. Novelty of our approach lies in its ability to consider the Greenland data from spatial, temporal and semantic contexts that allows us to build a comprehensive understanding of a specific phenomenon such as snowmelt.

Due to their larger penetration and sensing depth, low frequency microwave measurements have been recently employed to detect ice sheet melt events. In this paper, the response of NASA's SMAP (Soil Moisture Active Passive) L-band measurements to surface melting of the Greenland ice sheet from 2015 through 2021 is investigated. SMAP covers virtually the entire Greenland ice sheet twice a day with its L-band (1.4 GHz) radiometer. The results show that the ice sheet experienced unusually strong surface melting on August 14,2021, which extended the melt area across much of dry snow zone over a period of two days. Moreover, the observational results agree well with model simulations conducted using Glacier Energy and Mass Balance (GEMB) module within the Ice-sheet and Sea-level System Model (ISSM).