In the realm of international trade and economic development, the prediction of trade flows between countries is crucial for identifying export opportunities. Commonly used log-linear regression models are constrained due to difficulties when dealing with extensive, high-cardinality datasets, and the utilization of machine learning techniques in predictions offers new possibilities. We examine the predictive power of Graph Neural Networks (GNNs) in estimating the value of bilateral trade between countries. We work with detailed UN Comtrade data that represent annual bilateral trade in goods between any two countries in the world and more than 5000 product groups. We explore two different types of GNNs, namely Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs), by applying them to trade flow data. This study evaluates the effectiveness of GNNs relative to traditional machine learning techniques such as random forest and examines the possible effects of data drift on their performance. Our findings reveal the superior predictive capability of GNNs, suggesting their effectiveness in modeling complex trade relationships. The research presented in this work offers a data-driven foundation for decision-making and is relevant for business strategies and policymaking as it helps in identifying markets, products, and sectors with significant development potential.

Collecting massive seismic signals is a high-priority task in seismic risk evaluation, especially in densely populated areas, with cases of strong magnitude earthquake occurrence. At the same time, with the advent of the Internet of Things (IoT) paradigm, distributed and real-time environmental monitoring, supported by device interoperability, enhances the ability to collect data and make decisions especially in critical domains such as the seismic one. A crucial role is played by Semantic Web technologies that, in IoT ecosystems, promote syntactic and semantic interoperability, by enhancing the data quality that becomes ontology-annotated. This article introduces an IoT-oriented framework to collect seismic data, process and store them into a knowledge base. An ontology called Volcano Event Ontology (VEO) modeled for the seismic domain aims at gathering seismic signals collected by sensors for seismic event detection. The ontology is built on the well-known SSN/SOSA ontology, modeled to describe the systems of sensors, actuators, and observations. Seismic data have been collected by monitoring networks at Mt. Vesuvius (Naples, Italy) and Colima volcano (Mexico) and consolidated in the ontology. Moreover, the seismic data are also processed by a classification module to detect different seismic events (Volcano-Tectonic and long-period earthquakes, underwater explosions, and quarry blasts) and then stored in the knowledge base. Prompt detection and classification are, indeed, relevant to track any variation in the volcano dynamics, becoming crucial in cases of explosive crises. Finally, the VEO-driven knowledge base can be queried to get time-based seismic data and detected events, by queries.

Due to the rapid growth of knowledge graphs (KG) as representational learning methods in recent years, question-answering approaches have received increasing attention from academia and industry. Question-answering systems use knowledge graphs to organize, navigate, search and connect knowledge entities. Managing such systems requires a thorough understanding of the underlying graph-oriented structures and, at the same time, an appropriate query language, such as SPARQL, to access relevant data. Natural language interfaces are needed to enable non-technical users to query ever more complex data. The paper proposes a question-answering approach to support end users in querying graph-oriented knowledge bases. The system pipeline is composed of two main modules: one is dedicated to translating a natural language query submitted by the user into a triple of the form <subject, predicate, object>, while the second module implements knowledge graph embedding (KGE) models, exploiting the previous module triple and retrieving the answer to the question. Our framework delivers a fast OpenIE-based knowledge extraction system and a graph-based answer prediction model for question-answering tasks. The system was designed by leveraging existing tools to accomplish a simple prototype for fast experimentation, especially across different knowledge domains, with the added benefit of reducing development time and costs. The experimental results confirm the effectiveness of the proposed system, which provides promising performance, as assessed at the module level. In particular, in some cases, the system outperforms the literature. Finally, a use case example shows the KG generated by user questions in a graphical interface provided by an ad-hoc designed web application.

This work is devoted to the analysis of the background seismic noise acquired at the volcanoes (Campi Flegrei caldera, Ischia island, and Vesuvius) belonging to the Neapolitan volcanic district (Italy), and at the Colima volcano (Mexico). Continuous seismic acquisition is a complex mixture of volcanic transients and persistent volcanic and/or hydrothermal tremor, anthropogenic/ambient noise, oceanic loading, and meteo-marine contributions. The analysis of the background noise in a stationary volcanic phase could facilitate the identification of relevant waveforms often masked by microseisms and ambient noise. To address this issue, our approach proposes a machine learning (ML) modeling to recognize the “fingerprint” of a specific volcano by analyzing the background seismic noise from the continuous seismic acquisition. Specifically, two ML models, namely multi-layer perceptrons and convolutional neural network were trained to recognize one volcano from another based on the acquisition noise. Experimental results demonstrate the effectiveness of the two models in recognizing the noisy background signal, with promising performance in terms of accuracy, precision, recall, and F1 score. These results suggest that persistent volcanic signals share the same source information, as well as transient events, revealing a common generation mechanism but in different regimes. Moreover, assessing the dynamic state of a volcano through its background noise and promptly identifying any anomalies, which may indicate a change in its dynamics, can be a practical tool for real-time monitoring.

In the seismic domain, collecting seismic signal and alerting movements of earth crust is crucial for monitoring and forecasting seismic activities. At the same time, with the advent of the Internet of Things (IoT) paradigm, the device interoperability is the minimum requirement for communication among any available sensing device. Semantic web technologies promote this interoperability, by enhancing the quality of data that become ontology-annotated. The paper introduces an ontology model for describing the seismic domain, through the data collection from sensors, to gather seismic signals aimed at the seismic event recognition. The ontology has been built on the well-known SOSA and SSN ontologies, modeled to describe systems of sensors, actuators, and observations. The ontology, namely VEO (Volcano Event Ontology), has been modeled on actual data sensors, collected by a monitoring network at Mt. Vesuvius (Naples, Italy). Along with the ontology model of the seismic domain, a machine learning-based classification has been accomplished to identify seismic events (underwater explosions, quarry blasts, and thunders). A VEO-driven knowledge-base collects raw seismic data and detects events, accessible by SPARQL queries.