Marco Fiorucci

Deep learning methods have significantly advanced the analysis of satellite imagery, greatly enhancing the efficiency of screening extensive datasets. However, progress in the automatic identification of elements under the surface (subsoil features), detectable only through proxies like soil and vegetation alterations, has been limited. This challenge is further compounded by the significant influence of seasonal variability and land use management on their visibility. Automatic identification often requires multitemporal observations to maximise the likelihood of obtaining favourable visibility conditions and to strengthen the reliability of each identification. Additionally, the limited availability of publicly accessible specialised datasets has impeded progress in applying deep learning approaches. This paper presents the first publicly available dataset of multitemporal Sentinel-2 imagery for identifying palaeochannels, a specific category of subsoil features. We established a baseline for semantic segmentation by evaluating three architectures with various parameter configurations, specifically designed to address the unique challenges of segmenting these elongated and branched features under diverse landscape conditions at different times of the year. The results offer preliminary insights into addressing the varying visibility of subsoil features by applying deep learning to analyse temporal series. The dataset is available on Hugging Face and IIT Dataverse repositories.

Identifying changes in a pair of 3D aerial LiDAR point clouds, obtained during two distinct time periods over the same geographic region presents a significant challenge due to the disparities in spatial coverage and the presence of noise in the acquisition system. The most commonly used approaches to detecting changes in point clouds are based on supervised methods which necessitate extensive labelled data often unavailable in real-world applications. To address these issues, we propose an unsupervised approach that comprises two components: Implicit Neural Representation (INR) for continuous shape reconstruction and a Gaussian Mixture Model for categorising changes. INR offers a grid-agnostic representation for encoding bi-temporal point clouds, with unmatched spatial support that can be regularised to enhance high-frequency details and reduce noise. The reconstructions at each timestamp are compared at arbitrary spatial scales, leading to a significant increase in detection capabilities. We apply our method to a benchmark dataset comprising simulated LiDAR point clouds for urban sprawling. This dataset encompasses diverse challenging scenarios, varying in resolutions, input modalities and noise levels. This enables a comprehensive multi-scenario evaluation, comparing our method with the current state-of-the-art approach. We outperform the previous methods by a margin of 10% in the intersection over union metric. In addition, we put our techniques to practical use by applying them in a real-world scenario to identify instances of illicit excavation of archaeological sites and validate our results by comparing them with findings from field experts.

Machine Learning-based workflows are being progressively used for the automatic detection of archaeological objects (intended as below-surface sites) in remote sensing data. Despite promising results in the detection phase, there is still a lack of a standard set of measures to evaluate the performance of object detection methods, since buried archaeological sites often have distinctive shapes that set them aside from other types of objects included in mainstream remote sensing datasets (e.g., Dataset of Object deTection in Aerial images, DOTA). Additionally, archaeological research relies heavily on geospatial information when validating the output of an object detection procedure, a type of information that is not normally considered in regular machine learning validation pipelines. This paper tackles these shortcomings by introducing two novel automatic evaluation measures, namely ‘centroid-based’ and ‘pixel-based’, designed to encode the salient aspects of the archaeologists’ thinking process. To test their usability, an experiment with different object detection deep neural networks was conducted on a LiDAR dataset. The experimental results show that these two automatic measures closely resemble the semi-automatic one currently used by archaeologists and therefore can be adopted as fully automatic evaluation measures in archaeological remote sensing detection. Adoption will facilitate cross-study comparisons and close collaboration between machine learning and archaeological researchers, which in turn will encourage the development of novel human-centred archaeological object detection tools.

How can we separate structural information from noise in large graphs? To address this fundamental question, we propose a graph summarization approach based on Szemer\'edi's Regularity Lemma, a well-known result in graph theory, which roughly states that every graph can be approximated by the union of a small number of random-like bipartite graphs called `regular pairs'. Hence, the Regularity Lemma provides us with a principled way to describe the essential structure of large graphs using a small amount of data. Our paper has several contributions: (i) We present our summarization algorithm which is able to reveal the main structural patterns in large graphs. (ii) We discuss how to use our summarization framework to efficiently retrieve from a database the top-k graphs that are most similar to a query graph. (iii) Finally, we evaluate the noise robustness of our approach in terms of the reconstruction error and the usefulness of the summaries in addressing the graph search task.

Statistical analysis of large and sparse graphs is a challenging problem in data science due to the high dimensionality and nonlinearity of the problem. This paper presents a fast and scalable algorithm for partitioning such graphs into disjoint groups based on observed graph distances from a set of reference nodes. The resulting partition provides a low-dimensional approximation of the full distance matrix which helps to reveal global structural properties of the graph using only small samples of the distance matrix. The presented algorithm is inspired by the information-theoretic minimum description principle. We investigate the performance of this algorithm for selected real data sets and for synthetic graph data sets generated using stochastic block models and power-law random graphs, together with analytical considerations for sparse stochastic block models with bounded average degrees.

Statistical analysis of large and sparse graphs is a challenging problem in data science due to the high dimensionality and nonlinearity of the problem. This paper presents a fast and scalable algorithm for partitioning such graphs into disjoint groups based on observed graph distances from a set of reference nodes. The resulting partition provides a low-dimensional approximation of the full distance matrix which helps to reveal global structural properties of the graph using only small samples of the distance matrix. The presented algorithm is inspired by the information-theoretic minimum description principle. We investigate the performance of this algorithm for selected real data sets and for synthetic graph data sets generated using stochastic block models and power-law random graphs, together with analytical considerations for sparse stochastic block models with bounded average degrees.