# Explainable GeoAI: Can saliency maps help interpret artificial intelligence's learning process? An empirical study on natural feature detection

arXiv: https://arxiv.org/abs/2303.09660 · HTML: https://mlsanity.com/paper/2303.09660/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 62 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 25 of 25)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Using Deep Learning and Google Street View to Estimate the Demographic Makeup of the US](https://mlsanity.com/paper/1702.06683/) (2017)
- [Fast Axiomatic Attribution for Neural Networks](https://mlsanity.com/paper/2111.07668/) (2021)
- [Exascale Deep Learning for Climate Analytics](https://mlsanity.com/paper/1810.01993/) (2018)
- [Application of Multi-channel 3D-cube Successive Convolution Network for Convective Storm Nowcasting](https://mlsanity.com/paper/1702.04517/) (2017)

## Built on by (most cited first, 14 of 14)

- [Assessment of a new GeoAI foundation model for flood inundation mapping](https://mlsanity.com/paper/2309.14500/) (2023)
- [Towards Generative Location Awareness for Disaster Response: A Probabilistic Cross-view Geolocalization Approach](https://mlsanity.com/paper/2512.20056/) (2025)
- [Improving Interpretability of Deep Active Learning for Flood Inundation Mapping Through Class Ambiguity Indices Using Multi-spectral Satellite Imagery](https://mlsanity.com/paper/2404.19043/) (2024)
- [GeoAI Reproducibility and Replicability: a computational and spatial perspective](https://mlsanity.com/paper/2404.10108/) (2024)
- [Enhancing Explainability in Mobility Data Science through a combination of methods](https://mlsanity.com/paper/2312.00380/) (2023)
- [Inference Attacks Against Graph Generative Diffusion Models](https://mlsanity.com/paper/2601.03701/) (2026)
- [Towards eXplainable AI for Mobility Data Science](https://mlsanity.com/paper/2307.08461/) (2023)
- [A comprehensive GeoAI review: Progress, Challenges and Outlooks](https://mlsanity.com/paper/2412.11643/) (2024)
- [Combi-CAM: A Novel Multi-Layer Approach for Explainable Image Geolocalization](https://mlsanity.com/paper/2603.24117/) (2026)
- [Interpretable Cross-Sphere Multiscale Deep Learning Predicts ENSO Skilfully Beyond 2 Years](https://mlsanity.com/paper/2503.21211/) (2025)
- [Geospatial Artificial Intelligence for Satellite-Based Flood Extent Mapping: Concepts, Advances, and Future Perspectives](https://mlsanity.com/paper/2504.02214/) (2025)
- [Reinforcement-Guided Hyper-Heuristic Hyperparameter Optimization for Fair and Explainable Spiking Neural Network-Based Financial Fraud Detection](https://mlsanity.com/paper/2508.16915/) (2025)
- [Geography According to ChatGPT -- How Generative AI Represents and Reasons about Geography](https://mlsanity.com/paper/2603.18881/) (2026)
- [Evaluating the Alignment Between GeoAI Explanations and Domain Knowledge in Satellite-Based Flood Mapping](https://mlsanity.com/paper/2604.26051/) (2026)

## Abstract (arXiv)

Improving the interpretability of geospatial artificial intelligence (GeoAI) models has become critically important to open the "black box" of complex AI models, such as deep learning. This paper compares popular saliency map generation techniques and their strengths and weaknesses in interpreting GeoAI and deep learning models' reasoning behaviors, particularly when applied to geospatial analysis and image processing tasks. We surveyed two broad classes of model explanation methods: perturbation-based and gradient-based methods. The former identifies important image areas, which help machines make predictions by modifying a localized area of the input image. The latter evaluates the contribution of every single pixel of the input image to the model's prediction results through gradient backpropagation. In this study, three algorithms-the occlusion method, the integrated gradients method, and the class activation map method-are examined for a natural feature detection task using deep learning. The algorithms' strengths and weaknesses are discussed, and the consistency between model-learned and human-understandable concepts for object recognition is also compared. The experiments used two GeoAI-ready datasets to demonstrate the generalizability of the research findings.