arXiv subjects

Claudio Rossi

Publications and source records attributed to Claudio Rossi.

17 recordsLinked to original sources

arXiv2026

GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation

Geospatial foundation models aim to learn representations that transfer across regions and sensors, yet evaluating them on specific tasks requires large, high-quality, multi-modal benchmarks that measure how well such models extract value from data. Concerning flood mapping, existing datasets rarely combine bi-temporal SAR and co-registered optical imagery at scale, leaving the value of foundation models for this downstream task largely untested. We introduce GEOID-Flood, a large-scale multi-modal flood segmentation benchmark, derived from Copernicus Emergency Management Service activations, spanning 219 events across 65 countries over ten years. The dataset provides more than 14,000 tiles with co-registered pre- and post-event Sentinel-1, in GRD and RTC format, pre-event Sentinel-2 composite, and DEM, including manually validated labels that separate background from permanent water and flooded water. Using this benchmark, we evaluate foundation models against conventional encoders across single-image, multi-temporal, and multi-modal protocols. We report three main findings: foundation models offer a consistent but modest advantage; optical-SAR fusion with finetuning best resolves transient flooding; and models trained on GEOID-Flood transfer to unseen events better than those trained on existing datasets. Dataset and code available at https://github.com/links-ads/geoid-flood.

cs.CV↗

arXiv2025

ARise: an Augmented Reality Mobile Application to Improve Cultural Heritage Resilience

The preservation of cultural heritage faces increasing threats from climate change effects and environmental hazards, demanding innovative solutions that can promote awareness and resilience. This paper presents ARise, an Augmented Reality mobile application designed to enhance public engagement with cultural sites while raising awareness about the local impacts of climate change. Based on a user-centered co-creative methodology involving stakeholders from five European regions, ARise integrates multiple data sourcess - a Crowdsourcing Chatbot, a Social Media Data Analysis tool, and an AI-based Artwork Generation module - to deliver immersive and emotionally engaging experiences. Although formal user testing is forthcoming, this prototype demonstrates the potential of AR to support education, cultural sustainability, and climate adaptation.

cs.HC↗

arXiv2024

Maximum Temperature Prediction Using Remote Sensing Data Via Convolutional Neural Network

Urban heat islands, defined as specific zones exhibiting substantially higher temperatures than their immediate environs, pose significant threats to environmental sustainability and public health. This study introduces a novel machine-learning model that amalgamates data from the Sentinel-3 satellite, meteorological predictions, and additional remote sensing inputs. The primary aim is to generate detailed spatiotemporal maps that forecast the peak temperatures within a 24-hour period in Turin. Experimental results validate the model's proficiency in predicting temperature patterns, achieving a Mean Absolute Error (MAE) of 2.09 degrees Celsius for the year 2023 at a resolution of 20 meters per pixel, thereby enriching our knowledge of urban climatic behavior. This investigation enhances the understanding of urban microclimates, emphasizing the importance of cross-disciplinary data integration, and laying the groundwork for informed policy-making aimed at alleviating the negative impacts of extreme urban temperatures.

cs.AI↗

arXiv2024

Urban Air Pollution Forecasting: a Machine Learning Approach leveraging Satellite Observations and Meteorological Forecasts

Air pollution poses a significant threat to public health and well-being, particularly in urban areas. This study introduces a series of machine-learning models that integrate data from the Sentinel-5P satellite, meteorological conditions, and topological characteristics to forecast future levels of five major pollutants. The investigation delineates the process of data collection, detailing the combination of diverse data sources utilized in the study. Through experiments conducted in the Milan metropolitan area, the models demonstrate their efficacy in predicting pollutant levels for the forthcoming day, achieving a percentage error of around 30%. The proposed models are advantageous as they are independent of monitoring stations, facilitating their use in areas without existing infrastructure. Additionally, we have released the collected dataset to the public, aiming to stimulate further research in this field. This research contributes to advancing our understanding of urban air quality dynamics and emphasizes the importance of amalgamating satellite, meteorological, and topographical data to develop robust pollution forecasting models.

cs.LG↗

arXiv2024

Rapid Wildfire Hotspot Detection Using Self-Supervised Learning on Temporal Remote Sensing Data

Rapid detection and well-timed intervention are essential to mitigate the impacts of wildfires. Leveraging remote sensed data from satellite networks and advanced AI models to automatically detect hotspots (i.e., thermal anomalies caused by active fires) is an effective way to build wildfire monitoring systems. In this work, we propose a novel dataset containing time series of remotely sensed data related to European fire events and a Self-Supervised Learning (SSL)-based model able to analyse multi-temporal data and identify hotspots in potentially near real time. We train and evaluate the performance of our model using our dataset and Thraws, a dataset of thermal anomalies including several fire events, obtaining an F1 score of 63.58.

cs.CV↗

arXiv2024

FMARS: Annotating Remote Sensing Images for Disaster Management using Foundation Models

Very-High Resolution (VHR) remote sensing imagery is increasingly accessible, but often lacks annotations for effective machine learning applications. Recent foundation models like GroundingDINO and Segment Anything (SAM) provide opportunities to automatically generate annotations. This study introduces FMARS (Foundation Model Annotations in Remote Sensing), a methodology leveraging VHR imagery and foundation models for fast and robust annotation. We focus on disaster management and provide a large-scale dataset with labels obtained from pre-event imagery over 19 disaster events, derived from the Maxar Open Data initiative. We train segmentation models on the generated labels, using Unsupervised Domain Adaptation (UDA) techniques to increase transferability to real-world scenarios. Our results demonstrate the effectiveness of leveraging foundation models to automatically annotate remote sensing data at scale, enabling robust downstream models for critical applications. Code and dataset are available at \url{https://github.com/links-ads/igarss-fmars}.

cs.CV↗

arXiv2024

Landslide mapping from Sentinel-2 imagery through change detection

Landslides are one of the most critical and destructive geohazards. Widespread development of human activities and settlements combined with the effects of climate change on weather are resulting in a high increase in the frequency and destructive power of landslides, making them a major threat to human life and the economy. In this paper, we explore methodologies to map newly-occurred landslides using Sentinel-2 imagery automatically. All approaches presented are framed as a bi-temporal change detection problem, requiring only a pair of Sentinel-2 images, taken respectively before and after a landslide-triggering event. Furthermore, we introduce a novel deep learning architecture for fusing Sentinel-2 bi-temporal image pairs with Digital Elevation Model (DEM) data, showcasing its promising performances w.r.t. other change detection models in the literature. As a parallel task, we address limitations in existing datasets by creating a novel geodatabase, which includes manually validated open-access landslide inventories over heterogeneous ecoregions of the world. We release both code and dataset with an open-source license.

cs.CV↗

arXiv2023

Robust Burned Area Delineation through Multitask Learning

In recent years, wildfires have posed a significant challenge due to their increasing frequency and severity. For this reason, accurate delineation of burned areas is crucial for environmental monitoring and post-fire assessment. However, traditional approaches relying on binary segmentation models often struggle to achieve robust and accurate results, especially when trained from scratch, due to limited resources and the inherent imbalance of this segmentation task. We propose to address these limitations in two ways: first, we construct an ad-hoc dataset to cope with the limited resources, combining information from Sentinel-2 feeds with Copernicus activations and other data sources. In this dataset, we provide annotations for multiple tasks, including burned area delineation and land cover segmentation. Second, we propose a multitask learning framework that incorporates land cover classification as an auxiliary task to enhance the robustness and performance of the burned area segmentation models. We compare the performance of different models, including UPerNet and SegFormer, demonstrating the effectiveness of our approach in comparison to standard binary segmentation.

cs.CV↗

arXiv2023

A Multimodal Supervised Machine Learning Approach for Satellite-based Wildfire Identification in Europe

The increasing frequency of catastrophic natural events, such as wildfires, calls for the development of rapid and automated wildfire detection systems. In this paper, we propose a wildfire identification solution to improve the accuracy of automated satellite-based hotspot detection systems by leveraging multiple information sources. We cross-reference the thermal anomalies detected by the Moderate-resolution Imaging Spectroradiometer (MODIS) and the Visible Infrared Imaging Radiometer Suite (VIIRS) hotspot services with the European Forest Fire Information System (EFFIS) database to construct a large-scale hotspot dataset for wildfire-related studies in Europe. Then, we propose a novel multimodal supervised machine learning approach to disambiguate hotspot detections, distinguishing between wildfires and other events. Our methodology includes the use of multimodal data sources, such as the ERSI annual Land Use Land Cover (LULC) and the Copernicus Sentinel-3 data. Experimental results demonstrate the effectiveness of our approach in the task of wildfire identification.

eess.IV↗

arXiv2023

Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery

Land cover (LC) segmentation plays a critical role in various applications, including environmental analysis and natural disaster management. However, generating accurate LC maps is a complex and time-consuming task that requires the expertise of multiple annotators and regular updates to account for environmental changes. In this work, we introduce SPADA, a framework for fuel map delineation that addresses the challenges associated with LC segmentation using sparse annotations and domain adaptation techniques for semantic segmentation. Performance evaluations using reliable ground truths, such as LUCAS and Urban Atlas, demonstrate the technique's effectiveness. SPADA outperforms state-of-the-art semantic segmentation approaches as well as third-party products, achieving a mean Intersection over Union (IoU) score of 42.86 and an F1 score of 67.93 on Urban Atlas and LUCAS, respectively.

cs.CV↗

arXiv2023

Category Theory for Autonomous Robots: The Marathon 2 Use Case

Model-based systems engineering (MBSE) is a methodology that exploits system representation during the entire system life-cycle. The use of formal models has gained momentum in robotics engineering over the past few years. Models play a crucial role in robot design; they serve as the basis for achieving holistic properties, such as functional reliability or adaptive resilience, and facilitate the automated production of modules. We propose the use of formal conceptualizations beyond the engineering phase, providing accurate models that can be leveraged at runtime. This paper explores the use of Category Theory, a mathematical framework for describing abstractions, as a formal language to produce such robot models. To showcase its practical application, we present a concrete example based on the Marathon 2 experiment. Here, we illustrate the potential of formalizing systems -- including their recovery mechanisms -- which allows engineers to design more trustworthy autonomous robots. This, in turn, enhances their dependability and performance.

cs.RO↗

arXiv2021

A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images

Incremental learning represents a crucial task in aerial image processing, especially given the limited availability of large-scale annotated datasets. A major issue concerning current deep neural architectures is known as catastrophic forgetting, namely the inability to faithfully maintain past knowledge once a new set of data is provided for retraining. Over the years, several techniques have been proposed to mitigate this problem for image classification and object detection. However, only recently the focus has shifted towards more complex downstream tasks such as instance or semantic segmentation. Starting from incremental-class learning for semantic segmentation tasks, our goal is to adapt this strategy to the aerial domain, exploiting a peculiar feature that differentiates it from natural images, namely the orientation. In addition to the standard knowledge distillation approach, we propose a contrastive regularization, where any given input is compared with its augmented version (i.e. flipping and rotations) in order to minimize the difference between the segmentation features produced by both inputs. We show the effectiveness of our solution on the Potsdam dataset, outperforming the incremental baseline in every test. Code available at: https://github.com/edornd/contrastive-distillation.

cs.CV↗

arXiv2021

To Charge or to Sell? EV Pack Useful Life Estimation via LSTMs, CNNs, and Autoencoders

Electric vehicles (EVs) are spreading fast as they promise to provide better performance and comfort, but above all, to help face climate change. Despite their success, their cost is still a challenge. Lithium-ion batteries are one of the most expensive EV components, and have become the standard for energy storage in various applications. Precisely estimating the remaining useful life (RUL) of battery packs can encourage their reuse and thus help to reduce the cost of EVs and improve sustainability. A correct RUL estimation can be used to quantify the residual market value of the battery pack. The customer can then decide to sell the battery when it still has a value, i.e., before it exceeds the end of life of the target application, so it can still be reused in a second domain without compromising safety and reliability. This paper proposes and compares two deep learning approaches to estimate the RUL of Li-ion batteries: LSTM and autoencoders vs. CNN and autoencoders. The autoencoders are used to extract useful features, while the subsequent network is then used to estimate the RUL. Compared to what has been proposed so far in the literature, we employ measures to ensure the method's applicability in the actual deployed application. Such measures include (1) avoiding using non-measurable variables as input, (2) employing appropriate datasets with wide variability and different conditions, and (3) predicting the remaining ampere-hours instead of the number of cycles. The results show that the proposed methods can generalize on datasets consisting of numerous batteries with high variance.

cs.LG↗

arXiv2020

Ferromagnetic contamination of Ultra-Low-Field-NMR sample containers. Quantification of the problem and possible solutions

The presence of a weak remanence in Ultra-Low-Field (ULF) NMR sample containers is investigated on the basis of proton precession. The high-sensitivity magnetometer used for the NMR detection, enables simultaneously the measurement of the static field produced in the sample proximity by ferromagnetic contaminants. The presence of the latter is studied by high resolution chemical analyses of the surface, based on X-ray fluorescence spectroscopy and secondary ions mass spectroscopy. Methodologies to reduce the contamination are explored and characterized. This study is of relevance in any ULF-NMR experiment, as in the ULF regime spurious ferromagnetism becomes easily a dominant cause of artefacts.

physics.ins-det↗

arXiv2017

Simultaneous Detection of H and D NMR Signals in a micro-Tesla Field

We present NMR spectra of remote-magnetized deuterated water, detected in an unshielded environment by means of a differential atomic magnetometer. The measurements are performed in a $μ$T field, while pulsed techniques are applied -following the sample displacement- in a 100~$μ$T field, to tip both D and H nuclei by controllable amounts. The broadband nature of the detection system enables simultaneous detection of the two signals and accurate evaluation of their decay times. The outcomes of the experiment demonstrate the potential of ultra-low-field NMR spectroscopy in important applications where the correlation between proton and deuteron spin-spin relaxation rates as a function of external parameters contains significant information.

physics.chem-ph↗

arXiv2016

Microtesla NMR J-coupling spectroscopy with an unshielded atomic magnetometer

We present experimental data and theoretical interpretation of NMR spectra of remotely magnetized samples, detected in an unshielded environment by means of a differential atomic magnetometer. The measurements are performed in an ultra-low-field at an intermediate regime, where the J-coupling and the Zeeman energies have comparable values and produce rather complex line sets, which are satisfactorily interpreted.

physics.chem-ph↗

arXiv2011

An Energy Efficient Protocol for Gateway-Centric Federated Residential Access Networks

The proliferation of overlapping, always-on IEEE 802.11 Access Points (APs) in urban areas can cause spectrum sharing conflicts, inefficient bandwidth usage and power waste. Cooperation among APs could address these problems (i) by allowing under-used devices to hand over their clients to nearby APs and temporarily switch off, (ii) by balancing the load of clients among APs and thus offloading congested APs. The federated houses model provides an appealing backdrop to implement cooperation among APs. In this paper, we outline a framework that, assuming the presence of a multipurpose gateway with AP capabilities in every household, allows such cooperation through the monitoring of local wireless resources and the triggering of offloading requests toward other federated gateways. We then present simulation results in realistic settings that provide some insight on the capabilities of our framework.

cs.NI↗