Opening the Black-Box: A Systematic Review on Explainable AI in Remote Sensing
arXiv:2402.13791 · doi:10.1109/MGRS.2024.3467001
Abstract
In recent years, black-box machine learning approaches have become a dominant modeling paradigm for knowledge extraction in remote sensing. Despite the potential benefits of uncovering the inner workings of these models with explainable AI, a comprehensive overview summarizing the explainable AI methods used and their objectives, findings, and challenges in remote sensing applications is still missing. In this paper, we address this gap by performing a systematic review to identify the key trends in the field and shed light on novel explainable AI approaches and emerging directions that tackle specific remote sensing challenges. We also reveal the common patterns of explanation interpretation, discuss the extracted scientific insights, and reflect on the approaches used for the evaluation of explainable AI methods. As such, our review provides a complete summary of the state-of-the-art of explainable AI in remote sensing. Further, we give a detailed outlook on the challenges and promising research directions, representing a basis for novel methodological development and a useful starting point for new researchers in the field.
References in corpus (30)
- Deep learning in remote sensing: a review
- Graph Convolutional Networks for Hyperspectral Image Classification
- Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
- Explainable Machine Learning for Scientific Insights and Discoveries
- From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
- Self-attention for raw optical Satellite Time Series Classification
- Everything is Connected: Graph Neural Networks
- Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
- Prototype selection for interpretable classification
- Contrastive Explanation: A Structural-Model Approach
- Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI
- From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
- Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing
- Extreme Gradient Boosting for Yield Estimation compared with Deep Learning Approaches
- GLocalX -- From Local to Global Explanations of Black Box AI Models
- Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
- Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset
- Deep Learning for Satellite Image Time Series Analysis: A Review
- Physically Explainable CNN for SAR Image Classification
- Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience
- Towards a Collective Agenda on AI for Earth Science Data Analysis
- Enabling Explainable Fusion in Deep Learning with Fuzzy Integral Neural Networks
- Explaining and Interpreting LSTMs
- Hyperspectral Image Classification With Contrastive Graph Convolutional Network
- Explainable deep learning for insights in El Niño and river flows
- Explainable AI Integrated Feature Selection for Landslide Susceptibility Mapping using TreeSHAP
- Spatial machine-learning model diagnostics: a model-agnostic distance-based approach
- Considerations When Learning Additive Explanations for Black-Box Models
- Transforming Feature Space to Interpret Machine Learning Models
- Adaptive LASSO estimation for functional hidden dynamic geostatistical model