Conventional benchmarks for crop type classification from optical satellite time series typically assume access to labeled data from the same year and rely on fixed calendar-day sampling. This limits generalization across seasons, where crop phenology shifts due to interannual climate variability, and precludes real-time application when current-year labels are unavailable. Furthermore, uncertainty quantification is often neglected, making such approaches unreliable for crop monitoring applications. Inspired by ecophysiological principles of plant growth, we propose a simple, model-agnostic sampling strategy that leverages growing degree days (GDD), based on daily average temperature, to replace calendar time with thermal time. By uniformly subsampling time series in this biologically meaningful domain, the method emphasizes phenologically active growth stages while reducing temporal redundancy and noise. We evaluate the method on a multi-year Sentinel-2 dataset spanning all of Switzerland, training on one growing season and testing on other seasons. Compared to state-of-the-art baselines, our method delivers substantial gains in classification accuracy and, critically, produces more calibrated uncertainty estimates. Notably, our method excels in low-data regimes and enables significantly more accurate early-season classification. With only 10 percent of the training data, our method surpasses the state-of-the-art baseline in both predictive accuracy and uncertainty estimation, and by the end of June, it achieves performance similar to a baseline trained on the full season. These results demonstrate that leveraging temperature data not only improves predictive performance across seasons but also enhances the robustness and trustworthiness of crop-type mapping in real-world applications.
We propose two new methods based/inspired by machine learning for tabular data and distance-free localization to enhance the covariance estimations in an ensemble data assimilation. The main goal is to enhance the data assimilation results by mitigating loss of variance due to sampling errors. We also analyze the suitability of several machine learning models and the balance between accuracy and computational cost of the covariance estimations. We introduce two distance-free localization techniques leveraging machine learning methods specifically tailored for tabular data. The methods are integrated into the Ensemble Smoother with Multiple Data Assimilation (ES-MDA) framework. The results show that the proposed localizations improve covariance accuracy and enhance data assimilation and uncertainty quantification results. We observe reduced variance loss for the input variables using the proposed methods. Furthermore, we compare several machine learning models, assessing their suitability for the problem in terms of computational cost, and quality of the covariance estimation and data match. The influence of ensemble size is also investigated, providing insights into balancing accuracy and computational efficiency. Our findings demonstrate that certain machine learning models are more suitable for this problem. This study introduces two novel methods that mitigate variance loss for model parameters in ensemble-based data assimilation, offering practical solutions that are easy to implement and do not require any additional numerical simulation or hyperparameter tuning.
Machine learning has significantly advanced the understanding and application of structural materials, with an increasing emphasis on integrating existing data and quantifying uncertainties in predictive modeling. This study presents a comprehensive methodology utilizing a mixed density network (MDN) model, trained on extensive experimental data from literature. This approach uniquely predicts the distribution of dislocation density, inferred as a latent variable, and the resulting stress distribution at the grain level. The incorporation of statistical parameters of those predicted distributions into a dislocation-mediated plasticity model allows for accurate stress-strain predictions with explicit uncertainty quantification. This strategy not only improves the accuracy and reliability of mechanical property predictions but also plays a vital role in optimizing alloy design, thereby facilitating the development of new materials in a rapidly evolving industry.
Modern observatories are designed to deliver increasingly detailed views of astrophysical signals. To fully realize the potential of these observations, principled data-analysis methods are required to effectively separate and reconstruct the underlying astrophysical components from data corrupted by noise and instrumental effects. In this work, we introduce a novel multi-frequency Bayesian model of the sky emission field that leverages latent-space tension as an indicator of model misspecification, enabling automated separation of diffuse, point-like, and extended astrophysical emission components across wavelength bands. Deviations from latent-space prior expectations are used as diagnostics for model misspecification, thus systematically guiding the introduction of new sky components, such as point-like and extended sources. We demonstrate the effectiveness of this method on synthetic multi-frequency imaging data and apply it to observational X-ray data from the eROSITA Early Data Release (EDR) of the SN1987A region in the Large Magellanic Cloud (LMC). Our results highlight the method's capability to reconstruct astrophysical components with high accuracy, achieving sub-pixel localization of point sources, robust separation of extended emission, and detailed uncertainty quantification. The developed methodology offers a general and well-founded framework applicable to a wide variety of astronomical datasets, and is therefore well suited to support the analysis needs of next-generation multi-wavelength and multi-messenger surveys.
Estimating the governing equation parameter values is essential for integrating experimental data with scientific theory to understand, validate, and predict the dynamics of complex systems. In this work, we propose a new method for structural system identification (SI), uncertainty quantification, and validation directly from data. Inspired by generative modeling frameworks, a neural network maps random noise to physically meaningful parameters. These parameters are then used in the known equation of motion to obtain fake accelerations, which are compared to real training data via a mean square error loss. To simultaneously validate the learned parameters, we use independent validation datasets. The generated accelerations from these datasets are evaluated by a discriminator network, which determines whether the output is real or fake, and guides the parameter-generator network. Analytical and real experiments show the parameter estimation accuracy and model validation for different nonlinear structural systems.
The uncertainty quantification of sensor measurements coupled with deep learning networks is crucial for many robotics systems, especially for safety-critical applications such as self-driving cars. This paper develops an uncertainty quantification approach in the context of visual localization for autonomous driving, where locations are selected based on images. Key to our approach is to learn the measurement uncertainty using light-weight sensor error model, which maps both image feature and semantic information to 2-dimensional error distribution. Our approach enables uncertainty estimation conditioned on the specific context of the matched image pair, implicitly capturing other critical, unannotated factors (e.g., city vs highway, dynamic vs static scenes, winter vs summer) in a latent manner. We demonstrate the accuracy of our uncertainty prediction framework using the Ithaca365 dataset, which includes variations in lighting and weather (sunny, night, snowy). Both the uncertainty quantification of the sensor+network is evaluated, along with Bayesian localization filters using unique sensor gating method. Results show that the measurement error does not follow a Gaussian distribution with poor weather and lighting conditions, and is better predicted by our Gaussian Mixture model.
In ride-hailing systems, drivers decide whether to accept or reject ride requests based on factors such as order characteristics, traffic conditions, and personal preferences. Accurately predicting these decisions is essential for improving the efficiency and reliability of these systems. Traditional models, such as the Random Utility Maximization (RUM) approach, typically predict drivers' decisions by assuming linear correlations among attributes. However, these models often fall short because they fail to account for non-linear interactions between attributes and do not cater to the unique, personalized preferences of individual drivers. In this paper, we develop a method for learning personalized utility functions using hypernetwork and ensemble learning. Hypernetworks dynamically generate weights for a linear utility function based on trip request data and driver profiles, capturing the non-linear relationships. An ensemble of hypernetworks trained on different data segments further improve model adaptability and generalization by introducing controlled randomness, thereby reducing over-fitting. We validate the performance of our ensemble hypernetworks model in terms of prediction accuracy and uncertainty estimation in a real-world dataset. The results demonstrate that our approach not only accurately predicts each driver's utility but also effectively balances the needs for explainability and uncertainty quantification. Additionally, our model serves as a powerful tool for revealing the personalized preferences of different drivers, clearly illustrating which attributes largely impact their rider acceptance decisions.
Deep object pose estimators are notoriously overconfident. A grasping agent that both estimates the 6-DoF pose of a target object and predicts the uncertainty of its own estimate could avoid task failure by choosing not to act under high uncertainty. Even though object pose estimation improves and uncertainty quantification research continues to make strides, few studies have connected them to the downstream task of robotic grasping. We propose a method for training lightweight, deep networks to predict whether a grasp guided by an image-based pose estimate will succeed before that grasp is attempted. We generate training data for our networks via object pose estimation on real images and simulated grasping. We also find that, despite high object variability in grasping trials, networks benefit from training on all objects jointly, suggesting that a diverse variety of objects can nevertheless contribute to the same goal.
The increasing use of generative ML foundation models for image restoration tasks such as super-resolution calls for robust and interpretable uncertainty quantification methods. We address this need by presenting a novel approach based on conformal prediction techniques to create a 'confidence mask' capable of reliably and intuitively communicating where the generated image can be trusted. Our method is adaptable to any black-box generative model, including those locked behind an opaque API, requires only easily attainable data for calibration, and is highly customizable via the choice of a local image similarity metric. We prove strong theoretical guarantees for our method that span fidelity error control (according to our local image similarity metric), reconstruction quality, and robustness in the face of data leakage. Finally, we empirically evaluate these results and establish our method's solid performance.
Uncertainty quantification (UQ) for foundation models is essential to identify and mitigate potential hallucinations in automatically generated text. However, heuristic UQ approaches lack formal guarantees for key metrics such as the false discovery rate (FDR) in selective prediction. Previous work adopts the split conformal prediction (SCP) framework to ensure desired coverage of admissible answers by constructing prediction sets, but these sets often contain incorrect candidates, limiting their practical utility. To address this, we propose COIN, an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question under user-specified FDR constraints. COIN estimates the empirical error rate on a calibration set and applies confidence interval methods such as Clopper-Pearson to establish a high-probability upper bound on the true error rate (i.e., FDR). This enables the selection of the largest uncertainty threshold that ensures FDR control on test data while significantly increasing sample retention. We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data across both general and multimodal text generation tasks. Furthermore, we show that employing alternative upper bound constructions and UQ strategies can further boost COIN's power performance, which underscores its extensibility and adaptability to diverse application scenarios.
Graph Neural Networks (GNNs) have shown remarkable performance in the healthcare domain. However, what remained challenging is quantifying the predictive uncertainty of GNNs, which is an important aspect of trustworthiness in clinical settings. While Bayesian and ensemble methods can be used to quantify uncertainty, they are computationally expensive. Additionally, the disagreement metric used by ensemble methods to compute uncertainty cannot capture the diversity of models in an ensemble network. In this paper, we propose a novel method, based on knowledge distillation, to quantify GNNs' uncertainty more efficiently and with higher precision. We apply self-distillation, where the same network serves as both the teacher and student models, thereby avoiding the need to train several networks independently. To ensure the impact of self-distillation, we develop an uncertainty metric that captures the diverse nature of the network by assigning different weights to each GNN classifier. We experimentally evaluate the precision, performance, and ability of our approach in distinguishing out-of-distribution data on two graph datasets: MIMIC-IV and Enzymes. The evaluation results demonstrate that the proposed method can effectively capture the predictive uncertainty of the model while having performance similar to that of the MC Dropout and ensemble methods. The code is publicly available at https://github.com/tailabTMU/UQ_GNN.
Neural Networks have high accuracy in solving problems where it is difficult to detect patterns or create a logical model. However, these algorithms sometimes return wrong solutions, which become problematic in high-risk domains like medical diagnosis or autonomous driving. One strategy to detect and mitigate these errors is the measurement of the uncertainty over neural network decisions. In this paper, we present a novel post-hoc framework for measuring the uncertainty of a decision based on retrieved training cases that have a similar activation vector to the query for each layer. Based on these retrieved cases, we propose two new metrics: Decision Change and Layer Uncertainty, which capture changes in nearest-neighbor class distributions across layers. We evaluated our approach in a classification model for two datasets: CIFAR-10 and MNIST. The results show that these metrics enhance uncertainty estimation, especially in challenging classification tasks, outperforming softmax-based confidence.
Deep neural networks often learn and rely on spurious correlations, i.e., superficial associations between non-causal features and the targets. For instance, an image classifier may identify camels based on the desert backgrounds. While it can yield high overall accuracy during training, it degrades generalization on more diverse scenarios where such correlations do not hold. This problem poses significant challenges for out-of-distribution robustness and trustworthiness. Existing methods typically mitigate this issue by using external group annotations or auxiliary deterministic models to learn unbiased representations. However, such information is costly to obtain, and deterministic models may fail to capture the full spectrum of biases learned by the models. To address these limitations, we propose Evidential Alignment, a novel framework that leverages uncertainty quantification to understand the behavior of the biased models without requiring group annotations. By quantifying the evidence of model prediction with second-order risk minimization and calibrating the biased models with the proposed evidential calibration technique, Evidential Alignment identifies and suppresses spurious correlations while preserving core features. We theoretically justify the effectiveness of our method as capable of learning the patterns of biased models and debiasing the model without requiring any spurious correlation annotations. Empirical results demonstrate that our method significantly improves group robustness across diverse architectures and data modalities, providing a scalable and principled solution to spurious correlations.
Vehicle state estimation presents a fundamental challenge for autonomous driving systems, requiring both physical interpretability and the ability to capture complex nonlinear behaviors across diverse operating conditions. Traditional methodologies often rely exclusively on either physics-based or data-driven models, each with complementary strengths and limitations that become most noticeable during critical scenarios. This paper presents a novel consensus multi-model Kalman filter framework that integrates heterogeneous model types to leverage their complementary strengths while minimizing individual weaknesses. We introduce two distinct methodologies for handling covariance propagation in data-driven models: a Koopman operator-based linearization approach enabling analytical covariance propagation, and an ensemble-based method providing unified uncertainty quantification across model types without requiring pretraining. Our approach implements an iterative consensus fusion procedure that dynamically weighs different models based on their demonstrated reliability in current operating conditions. The experimental results conducted on an electric all-wheel-drive Equinox vehicle demonstrate performance improvements over single-model techniques, with particularly significant advantages during challenging maneuvers and varying road conditions, confirming the effectiveness and robustness of the proposed methodology for safety-critical autonomous driving applications.
Modern large language models (LLMs) are often deployed as agents, calling external tools adaptively to solve tasks. Rather than directly calling tools, it can be more effective for LLMs to write code to perform the tool calls, enabling them to automatically generate complex control flow such as conditionals and loops. Such code actions are typically provided as Python code, since LLMs are quite proficient at it; however, Python may not be the ideal language due to limited built-in support for performance, security, and reliability. We propose a novel programming language for code actions, called Quasar, which has several benefits: (1) automated parallelization to improve performance, (2) uncertainty quantification to improve reliability and mitigate hallucinations, and (3) security features enabling the user to validate actions. LLMs can write code in a subset of Python, which is automatically transpiled to Quasar. We evaluate our approach on the ViperGPT visual question answering agent, applied to the GQA dataset, demonstrating that LLMs with Quasar actions instead of Python actions retain strong performance, while reducing execution time when possible by 42%, improving security by reducing user approval interactions when possible by 52%, and improving reliability by applying conformal prediction to achieve a desired target coverage level.
This paper introduces GUST (Generative Uncertainty learning via Self-supervised pretraining and Transfer learning), a framework for quantifying free-form geometric uncertainties inherent in the manufacturing of metamaterials. GUST leverages the representational power of deep generative models to learn a high-dimensional conditional distribution of as-fabricated unit cell geometries given nominal designs, thereby enabling uncertainty quantification. To address the scarcity of real-world manufacturing data, GUST employs a two-stage learning process. First, it leverages self-supervised pretraining on a large-scale synthetic dataset to capture the structure variability inherent in metamaterial geometries and an approximated distribution of as-fabricated geometries given nominal designs. Subsequently, GUST employs transfer learning by fine-tuning the pretrained model on limited real-world manufacturing data, allowing it to adapt to specific manufacturing processes and nominal designs. With only 960 unit cells additively manufactured in only two passes, GUST can capture the variability in geometry and effective material properties. In contrast, directly training a generative model on the same amount of real-world data proves insufficient, as demonstrated through both qualitative and quantitative comparisons. This scalable and cost-effective approach significantly reduces data requirements while maintaining the effectiveness in learning complex, real-world geometric uncertainties, offering an affordable method for free-form geometric uncertainty quantification in the manufacturing of metamaterials. The capabilities of GUST hold significant promise for high-precision industries such as aerospace and biomedical engineering, where understanding and mitigating manufacturing uncertainties are critical.
Vine copulas are sophisticated models for multivariate distributions and are increasingly used in machine learning. To facilitate their integration into modern ML pipelines, we introduce the vine computational graph, a DAG that abstracts the multilevel vine structure and associated computations. On this foundation, we devise new algorithms for conditional sampling, efficient sampling-order scheduling, and constructing vine structures for customized conditioning variables. We implement these ideas in torchvinecopulib, a GPU-accelerated Python library built upon PyTorch, delivering improved scalability for fitting, sampling, and density evaluation. Our experiments illustrate how gradient flowing through the vine can improve Vine Copula Autoencoders and that incorporating vines for uncertainty quantification in deep learning can outperform MC-dropout, deep ensembles, and Bayesian Neural Networks in sharpness, calibration, and runtime. By recasting vine copula models as computational graphs, our work connects classical dependence modeling with modern deep-learning toolchains and facilitates the integration of state-of-the-art copula methods in modern machine learning pipelines.
State estimation in stochastic dynamical systems with noisy measurements is a challenge. While the Kalman filter is optimal for linear systems with independent Gaussian white noise, real-world conditions often deviate from these assumptions, prompting the rise of data-driven filtering techniques. This paper introduces Recursive KalmanNet, a Kalman-filter-informed recurrent neural network designed for accurate state estimation with consistent error covariance quantification. Our approach propagates error covariance using the recursive Joseph's formula and optimizes the Gaussian negative log-likelihood. Experiments with non-Gaussian measurement white noise demonstrate that our model outperforms both the conventional Kalman filter and an existing state-of-the-art deep learning based estimator.
We introduce an approach to topic modelling with document-level covariates that remains tractable in the face of large text corpora. This is achieved by de-emphasizing the role of parameter estimation in an underlying probabilistic model, assuming instead that the data come from a fixed but unknown distribution whose statistical functionals are of interest. We propose combining a convex formulation of non-negative matrix factorization with standard regression techniques as a fast-to-compute and useful estimate of such a functional. Uncertainty quantification can then be achieved by reposing non-parametric resampling methods on top of this scheme. This is in contrast to popular topic modelling paradigms, which posit a complex and often hard-to-fit generative model of the data. We argue that the simple, non-parametric approach advocated here is faster, more interpretable, and enjoys better inferential justification than said generative models. Finally, our methods are demonstrated with an application analysing covariate effects on discourse of flavours attributed to Canadian beers.
Quantifying uncertainties for machine learning (ML) models is a foundational challenge in modern data analysis. This challenge is compounded by at least two key aspects of the field: (a) inconsistent terminology surrounding uncertainty and estimation across disciplines, and (b) the varying technical requirements for establishing trustworthy uncertainties in diverse problem contexts. In this position paper, we aim to clarify the depth of these challenges by identifying these inconsistencies and articulating how different contexts impose distinct epistemic demands. We examine the current landscape of estimation targets (e.g., prediction, inference, simulation-based inference), uncertainty constructs (e.g., frequentist, Bayesian, fiducial), and the approaches used to map between them. Drawing on the literature, we highlight and explain examples of problematic mappings. To help address these issues, we advocate for standards that promote alignment between the \textit{intent} and \textit{implementation} of uncertainty quantification (UQ) approaches. We discuss several axes of trustworthiness that are necessary (if not sufficient) for reliable UQ in ML models, and show how these axes can inform the design and evaluation of uncertainty-aware ML systems. Our practical recommendations focus on scientific ML, offering illustrative cases and use scenarios, particularly in the context of simulation-based inference (SBI).