In this paper, we propose a promising approach for the application-oriented content classification of space-borne radar imagery that presents an interesting alternative to popular current machine learning algorithms. In the following, we consider the problem of unsupervised feature-free satellite image classification as an explainable data mining problem for regions with no prior information. Three important issues are addressed here: explainability, unsupervision and feature-independence. There is an increasing demand towards explainable machine learning models as they strive to meet the “right to explanation”. The importance of feature-free classification stems from the problem that different classification outcomes are obtained from using different features and the complexity of computing sophisticated image primitive features. Developing unsupervised discovery techniques helps overcome the limitations in object discovery due to the lack of labelled data and the dependence on features. In this paper, we demonstrate the applicability of the Latent Dirichlet Allocation (LDA) model, one of the most established unsupervised probabilistic methods, in discovering the latent structure of synthetic aperture radar (SAR) data. The idea is to use LDA as an explainable data mining tool to discover scientifically explainable semantic relations. The suitability of the approach as an explainable model is discussed and interpretable topic representation maps are produced which practically demonstrate the idea of “interpretability” in the explainable machine learning paradigm. LDA discovers the latent structure in the data as a set of topics. We create the interpretable visualizations of the data utilizing these topics and compute the topic distributions for each land-cover class.

Machine learning methods have shown tremendous success in understanding earth observation data, however, recently, there is a rising claim towards explainable machine learning approaches. Concerned researchers found interpretable visualizations to be greatly helpful in understanding how a model works. In this research, we propose a framework for interactive and interpretable visualization of remote sensing data using two machine learning models and an Elasticsearch database. Two explainable machine learning models, namely, Bag-of-Visual-Words (BoVW) and Latent Dirichlet Allocation (LDA) are chosen to model the data in an unsupervised manner, and give a textual representation. The textualized remote sensing data is stored in an Elasticsearch database. This framework offers several fast content-based search functionalities exploiting the full-text query capabilities of Elasticsearch based on the respective representations, and also offers an efficient storage mechanism for the data.

Openly available Satellite Image Time Series (SITS) are considered an important resource for spatiotemporal change monitoring. However, obtaining semantically annotated datasets for such tasks is an expensive affair. To alleviate this problem, this paper presents a novel framework to model and understand the image dynamics by discovering latent information in Sentinel-1 SITS, even with limited ground truth data. The framework suggests how to use visualizations to efficiently integrate domain knowledge both for execution and evaluation of the machine learning pipeline in the absence from ground truth data in SITS change studies. In a case study at a Polar region, we extend a limited amount of ground truth data and then discover its temporal evolution at image patch level, in an unsupervised manner. The trustworthiness of the framework is ensured by integration of domain knowledge and intelligent visual verification strategies. A visualization tool is also implemented for this purpose. The proposed framework contains two modules: a classifier, and a change modeler. Our experiments show that a domain knowledge-based classifier gives the best accuracy. The classifier semantically labelled the complete dataset of 24 study months, containing 153,600 patches with a size of 256 × 256 pixels by extending the available semantic labels from just three months. The temporal sequence of these sematic labels are then recorded and fed to a Bayesian model called Latent Dirichlet Allocation (LDA) to discover the underlying patterns. LDA generates a change map containing the dominant dynamic patterns, to give a consolidated view of the evolution without having to browse the whole dataset. Further, color-coded change signatures explain the change classes.

For many years, image classification – mainly based on pixel brightness statistics – has been among themost popular remote sensing applications. However, during recent years, many users were more andmore interested in the application-oriented semantic labelling of remotely sensed image objects beingdepicted in given images.In parallel, the development of deep learning algorithms has led to several powerful imageclassification and annotation tools that became popular in the remote sensing community. In mostcases, these publicly available tools combine efficient algorithms with expert knowledge and/orexternal information ingested during an initial training phase, and we often encounter two alternativetypes of deep learning approaches, namely Autoencoders (AEs) and Convolutional Neural Networks(CNNs). Both approaches try to convert the pixel data of remote sensing images into semantic maps ofthe imaged areas.In our case, we made an attempt to provide an efficient new semantic annotation tool that helps inthe semantic interpretation of newly recorded images with known and/or possibly unknown content.Typical cases are remote sensing images depicting unexpected and hitherto uncharted phenomenasuch as flooding events or destroyed infrastructure. When we resort to the commonly applied AE orCNN software packages we cannot expect that existing statistics, or a few initial ground-truthannotations made by an image interpreter, will automatically lead to a perfect understanding of theimage content. Instead, we have to discover and combine a number of additional relationships thatdefine the actual content of a selected image and many of its characteristics.Our approach consists of a two-stage domain-change approach where we first convert an image intoa purely mathematical ‘topic representation’ initially introduced by Blei [1]. This representationprovides statistics-based topics that do not yet require final application-oriented labelling describingphysical categories or phenomena and support the idea of explainable machine learning [2]. Then,during a second stage, we try to derive physical image content categories by exploiting a weightedmulti-level neural network approach that converts weighted topics into individual application-orientedlabels. This domain-changing learning stage limits label noise and is initially supported by an imageinterpreter allowing the joint use of pixel statistics and expert knowledge [3]. The activity of the imageinterpreter can be limited to a few image patches.We tested our approach on a number of different use cases (e.g., polar ice, agriculture, naturaldisasters) and found that our concept provides promising results.  [1] D.M. Blei, A.Y. Ng, and M.I. Jordan, (2003). Latent Dirichlet Allocation, Journal of Machine LearningResearch, Vol. 3, pp. 993-1022.[2] C. Karmakar, C.O. Dumitru, G. Schwarz, and M. Datcu (2020). Feature-free explainable data miningin SAR images using latent Dirichlet allocation, IEEE Journal of Selected Topics in Applied EarthObservations and Remote Sensing, Vol. 14, pp. 676-689.[3] C.O. Dumitru, G. Schwarz, and M. Datcu (2021). Semantic Labelling of Globally Distributed Urbanand Non-Urban Satellite Images Using High-Resolution SAR Data, IEEE Journal of Selected Topics inApplied Earth Observations and Remote Sensing, Vol. 15, pp. 6009-6068.

Due to changes in global climate, coastal erosion is a common phenomenon, leading to flooding, habitat loss, property damage, and economic impacts. Large-scale automatic monitoring of coastlines is feasible by processing satellite images with Artificial Intelligence (AI) models; however, it is often constrained by scarce labels and model opacity. We present an explainable, fully unsupervised framework that first converts multi-year Sentinel-2 image series into pixel-wise land–water maps with attached model certainty and then discovers change patterns in the temporal structures of these land-water masks over a specified study period. Throughout the pipeline, we used the Normalized Difference Water Index (NDWI), computed from Sentinel-2 Green (B3) and NIR (B8), as our primary spectral indicator of surface water. We leverage two probabilistic models independently to select the best: (i) a Latent Dirichlet Allocation (LDA) model on a bag-of-visual-words to discover interpretable topics (e.g., foam, water, vegetation) that provide semantic segmentation with transparency, and (ii) a Gaussian Mixture Model (GMM) in pixel feature space to produce per-pixel probabilistic clustering and segmentation. Both models create multiple binary land-water segmentation maps from static images and then a single time-series evolution map from these multi-year land-water segmentation maps. The shoreline was automatically extracted as the boundary land pixels in binary maps with a threshold-based certainty score. We summarize changes with three methods and a score to define the amount of changes: the scene-level water fraction p_w, shoreline-normal displacement (SND) along fixed transects, and the low-confidence proportion Uτ that localizes ambiguity to physically dynamic interfaces. A Hamming score was computed to provide a quick and quantitative overview of the time-series evolution over a 7-year period. The pipeline delivers clear coastlines, interpretable segmentation maps, and uncertainty visualizations to help domain experts in auditing decisions. The result is a label-free, scalable, and explainable workflow in which every decision is accompanied by a confidence score, supporting reliable coastal monitoring and downstream scientific and application-oriented use.