Uncertainties of Satellite-based Essential Climate Variables from Deep Learning

Abstract

Accurate uncertainty information associated with essential climate variables (ECVs) is crucial for reliable climate modeling and understanding the spatiotemporal evolution of the Earth system. In recent years, geoscience and climate scientists have benefited from rapid progress in deep learning to advance the estimation of ECV products with improved accuracy. However, the quantification of uncertainties associated with the output of such deep learning models has yet to be thoroughly adopted. This survey explores the types of uncertainties associated with ECVs estimated from deep learning and the techniques to quantify them. The focus is on highlighting the importance of quantifying uncertainties inherent in ECV estimates, considering the dynamic and multifaceted nature of climate data. The survey starts by clarifying the definition of aleatoric and epistemic uncertainties and their roles in a typical satellite observation processing workflow, followed by bridging the gap between conventional statistical and deep learning views on uncertainties. Then, we comprehensively review the existing techniques for quantifying uncertainties associated with deep learning algorithms, focusing on their application in ECV studies. The specific need for modification to fit the requirements from both the Earth observation side and the deep learning side in such interdisciplinary tasks is discussed. Finally, we demonstrate our findings with two ECV examples, snow cover and terrestrial water storage, and provide our perspectives for future research.

References in corpus (35)

• Denoising Diffusion Probabilistic Models
• Variational Inference: A Review for Statisticians
• Deep learning in remote sensing: a review
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Ensemble deep learning: A review
• Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Explainable Machine Learning for Scientific Insights and Discoveries
• Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• Deep Ensembles: A Loss Landscape Perspective
• A General Framework for Uncertainty Estimation in Deep Learning
• Averaging Weights Leads to Wider Optima and Better Generalization
• Dense Dilated Convolutions Merging Network for Land Cover Classification
• Improving prediction of the terrestrial water storage anomalies during the GRACE and GRACE-FO gap with Bayesian convolutional neural networks
• Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictions
• The global land water storage data set release 2 (GLWS2.0) derived via assimilating GRACE and GRACE-FO data into a global hydrological model
• Partial Convolution based Padding
• An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval
• Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward
• GenCast: Diffusion-based ensemble forecasting for medium-range weather
• Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamics
• Globally Scalable Glacier Mapping by Deep Learning Matches Expert Delineation Accuracy
• A Foundation Model for the Earth System
• A Survey on Uncertainty Quantification Methods for Deep Learning
• Sources of Uncertainty in Supervised Machine Learning -- A Statisticians' View
• A Bayesian Deep Learning Approach to Near-Term Climate Prediction
• On the Foundations of Earth and Climate Foundation Models
• Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning
• Generative ensemble deep learning severe weather prediction from a deterministic convection-allowing model
• Maximum Likelihood Uncertainty Estimation: Robustness to Outliers
• Downscaling GRACE-derived ocean bottom pressure anomalies using self-supervised data fusion
• Probabilistic Artificial Intelligence
• Lightning UQ Box: A Comprehensive Framework for Uncertainty Quantification in Deep Learning
• LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks