Applications of Explainable artificial intelligence in Earth system science
Not on the map. Why?
Abstract (arXiv)
In recent years, artificial intelligence (AI) rapidly accelerated its influence and is expected to promote the development of Earth system science (ESS) if properly harnessed. In application of AI to ESS, a significant hurdle lies in the interpretability conundrum, an inherent problem of black-box nature arising from the complexity of AI algorithms. To address this, explainable AI (XAI) offers a set of powerful tools that make the models more transparent. The purpose of this review is twofold: First, to provide ESS scholars, especially newcomers, with a foundational understanding of XAI, serving as a primer to inspire future research advances; second, to encourage ESS professionals to embrace the benefits of AI, free from preconceived biases due to its lack of interpretability. We begin with elucidating the concept of XAI, along with typical methods. We then delve into a review of XAI applications in the ESS literature, highlighting the important role that XAI has played in facilitating communication with AI model decisions, improving model diagnosis, and uncovering scientific insights. We identify four significant challenges that XAI faces within the ESS, and propose solutions. Furthermore, we provide a comprehensive illustration of multifaceted perspectives. Given the unique challenges in ESS, an interpretable hybrid approach that seamlessly integrates AI with domain-specific knowledge appears to be a promising way to enhance the utility of AI in ESS. A visionary outlook for ESS envisions a harmonious blend where process-based models govern the known, AI models explore the unknown, and XAI bridges the gap by providing explanations.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 69 of its 285 references that are in the map. First posted on arXiv 12 Jun 2024.
Builds on
69 of 285 references.
References · 69
- 2017Attention Is All You Needcited by 59,932
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2013Visualizing and Understanding Convolutional Networkscited by 2,278
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
- 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
- 2014Striving for Simplicity: The All Convolutional Netcited by 983
38 more
- 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
- 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
- 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
- 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
- 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
- 2017The (Un)reliability of saliency methodscited by 331
- 2022Diffusion Models already have a Semantic Latent Spacecited by 324
- 2018On the Robustness of Interpretability Methodscited by 310
- 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
- 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
- 2023FuXi: A cascade machine learning forecasting system for 15-day global weather forecastcited by 237
- 2016Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Modelscited by 212
- 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 165
- 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 153
- 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
- 2020Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challengescited by 120
- 2016Full-Capacity Unitary Recurrent Neural Networkscited by 90
- 2019Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruningcited by 89
- 2019DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systemscited by 59
- 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
- 2021How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanationscited by 58
- 2017A trans-disciplinary review of deep learning research for water resources scientistscited by 47
- 2019Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variabilitycited by 43
- 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
- 2019Explainable artificial intelligence model to predict acute critical illness from electronic health recordscited by 42
- 2019U-CAM: Visual Explanation using Uncertainty based Class Activation Mapscited by 36
- 2020A Survey of Deep Learning for Scientific Discoverycited by 36
- 2019Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Netcited by 35
- 2020What Do You See? Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural Backdoorscited by 32
- 2021Explainable Medical Imaging AI Needs Human-Centered Design: Guidelines and Evidence from a Systematic Reviewcited by 30
- 2019Explaining Models by Propagating Shapley Values of Local Componentscited by 29
- 2021Fast TreeSHAP: Accelerating SHAP Value Computation for Treescited by 28
- 2022Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geosciencecited by 28
- 2022Physically Constrained Generative Adversarial Networks for Improving Precipitation Fields from Earth System Modelscited by 28
- 2021Towards a Collective Agenda on AI for Earth Science Data Analysiscited by 27
- 2021Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensingcited by 26
50 most cited of 69 All 69 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.