Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/esterpantaleo/elements_exposed_to_disasters


https://github.com/esterpantaleo/elements_exposed_to_disasters

Last synced: 4 days ago
JSON representation

Awesome Lists containing this project

README 

        
Elements at risk



	Public Health

	Advanced technologies combining machine learning, satellite data, and remote sensing can generate actionable tools for urban resilience to monitor, predict, and mitigate health risks. 

	

		Quantifying and evaluating the heat-stress hazard variability

		The aim of this project is the assessment and evaluation of the urban heat island (UHI) effect.

		To address this, a daily mean temperature map has been developed for Tuscany at a fine spatial scale of 100 × 100 m, using machine learning algorithms that integrate remote sensing (satellite) temperature data with urbanization and monitoring station data. 

		A harmonized geocode database has been created by combining Earth Observation (EO) satellite data, ground-monitoring stations, and other spatiotemporal predictors for Tuscany from 2003 to 2022.

		

			Academic impact 

			Two-stage approach utilizing machine learning algorithms (gradient-boosted trees). In the first stage, missing moderate-resolution land surface temperature data from MODIS were imputed using spatiotemporal predictors (e.g., solar geometry and topography). In the second stage, spatiotemporal variations in observed ground-based Tmax and Tmin air temperature data were modeled at a 100 × 100 m resolution across Tuscany, incorporating stage-1 MODIS data and a range of variables, including topography, solar geometry, land cover, population, meteorological parameters derived from ERA5-land, and the Normalized Difference Vegetation Index (NDVI).

		

		

			Social impact 

			Populations living in cities are particularly vulnerable to non-optimal temperatures, urban areas often experience significantly warmer ambient temperatures compared to surrounding rural regions. As a result of this project, daily maps of Tmax and Tmin for Tuscany for the year 2022 have been produced.

		

		Tuscany use case: PPT


		 Francesco Sera UNIFI 

	

	

		Estimating air pollution concentration in urban areas

		This project aims at providing cities with the tools to predict and mitigate the health impacts of air pollution, ultimately enhancing overall urban resilience. This research explores the use of satellite data to create a digital twin of cities, offering real-time air quality monitoring and linking pollution levels to specific health outcomes. The intermediate product is an estimator of air pollution concentration using machine learning, XAI, and remote sensing and fine-grained weather reanalysis data. 


		

			Academic Impact 

			Advances in decadal climate predictability and the performance of regional climate models.

		

		

			Economic Impact 

			Healthcare cost saving and identification of hotspots of neurodegenerative and oncologic diseases. Increased life expectancy and quality of life. Avoided cost from prevented environmental degradation.

		

		

			Social Impact 

			Addressing UN SDG 3.9 (By 2030, substantially reduce the number of deaths and illnesses from hazardous chemicals and air, water, and soil pollution and contamination) and 11.6 (Reduce the adverse per capita environmental impact of cities, including by paying special attention to air quality).

   					

		Use case: Italy @1km & @300m PPT


		 Roberto Bellotti UNIBA 


	model, database • monitoring, socio-economic-environmental impact


	



	Property and Critical Infrastructures

	

		Buildings

		

			Extracting key features of buildings from satellite data

			Through deep learning techniques, satellite data can leveraged to extract key features of buildings, including their size, shape, function, and spatial distribution. This enables high-precision assessments of urban structures, supporting a range of applications from urban planning and development to disaster response and energy management. By automating the feature extraction process, the integration of deep learning reduces the time and cost associated with manual mapping, making it possible to analyze large, complex datasets in near real-time.


			PPT


			 Roberto Bellotti UNIBA 


			 model, database 

		

	

	

		Coastal shores

		

			Monitoring subsidence or uplifting of coastal shores

				This project proposes a workflow that effectively outlines the presence of both subsidence and uplifting. These phenomena deserve continuous monitoring, both for environmental and infrastructural purposes. Using persistent interferometry collected from satellites and clustering algorithms we highlight the presence of homogeneous patterns using an  hypothesis testing procedure to evaluate and establish the presence of significant local spatial correlations (the LISA method). The designed workflow ensures the retrieval of homogeneous clusters and a reliable anomaly detection. 


				Sibari (CS) and Metaponto (MT) use case: PPT


				 Roberto Bellotti UNIBA 


				 model  • landslides • hazard 

			

			

				Coastal Evolution Impact

				CEI relies on detailed projections of the future sea level from a high-resolution model of the Mediterranean Sea, on the best available digital terrain model of the Italian coasts, and on the most advanced satellite-derived data of ground motion, provided by the European Ground Motion Service of Copernicus. To obtain a reliable understanding of coastal evolution, future sea level projections and estimates of the future vertical ground motion based on the currently available data have been combined and spread over the digital terrain model, using a GIS-based approach (Cappucci et al., 2024).


				case study: PPT


				Sergio Cappucci ENEA 


				 model  • climate change • vulnerability, socio-economic-environmental impact 

		

	

	

		Roads, bridges and transportation systems

		Transportation systems are essential for industrial production, and economic stability, with bridges and viaducts playing a crucial role in transportation networks. However, aging bridges present a significant challenge for urban resilience, requiring continuous monitoring and proper maintenance to ensure their durability, efficiency, and safety. Effective bridge classification and structural health monitoring are therefore vital for timely interventions, risk mitigation, and long-term preservation.

		

			Bridge classification

			BridgesClassification - This study proposes a simplified mathematical method for the preliminary assessment of bridges, assigning a risk factor index based on inspections and surveys, with values from 1 to 5, in line with the new Italian Guidelines for existing bridges (LG2020. Linee Guida per la Classificazione e Gestione del Rischio, la Valutazione della Sicurezza ed il Monitoraggio dei Ponti Esistenti; Ministero delle Infrastrutture e dei Trasporti: Rome, Italy, 2020). Polynomial functions combine these indices to obtain a multi-risk index, ensuring a more objective and efficient classification. The method does not replace in-depth evaluations but supports the planning of maintenance actions. Applicable to all bridges, it represents an improvement over current guidelines while maintaining a methodology adaptable worldwide.


			PPT


			Chiara Ormando ENEA 

			 model • earthquake, landslide, flood model • risk, prevention

		

		

			Bridge monitoring 

			StrSalus - Bridge monitoring using sensor data to predict and prevent potential structural failures in key infrastructure. 

			Fernando Saitta ENEA PPT

			 model, tool • all phenomena • monitoring, prevention, anomaly detection, Unsupervised Learning

		

		

			Model of traffic congestion

			This project develops numerical models that simulate traffic congestion and evacuation scenarios on road networks. It uses advanced algorithms (like Chebyshev polynomials) to predict and manage traffic flow during emergencies, improving evacuation efficiency in urban areas. PPT


			Sabrina Francesca Pellegrino POLIBA


			 model • monitoring, environmental impact

		

		

			Resilience of road networks

		    The overarching objective of this analysis is to deepen our understanding of the road network's resilience amidst various challenges and to devise pragmatic strategies for fortifying its strength and durability. Through meticulous examination and analysis, this study endeavors to contribute to the enhancement of Italy's critical infrastructures, ensuring their capacity to withstand and recover from adversities effectively. It focuses on the national road network in relation to environmental hazards, accounting for the mobility flux between Italian cities. The project includes constructing a high-resolution road network, associating municipalities with the nearest road nodes, and transforming the network into a weighted graph based on ISTAT mobility matrix values. 
Apulia use case: PPT


            Roberto Bellotti UNIBA

		

	

	

		Utilities 

		Power and water distribution networks ensure the continuous supply of electricity and clean water to households, industries, and critical services. 

		Strengthening their resilience requires enhancing their capacity to withstand disruptions, recover quickly, and minimize service interruptions and economic losses. 

		This can be achieved through real-time monitoring, rapid response strategies, and the integration of distribution network data, mathematical models, and data-driven analytics.

		 

			Water supply systems

			QuakeSimFlow - Assessing how water supply systems respond to earthquakes and other natural disasters, ensuring continuous supply in times of crisis. 
PPT 
 Lorenzo De Biase ENEA

			 tool • earthquake, all phenomena • resilience

		

		 

			Power distribution networks

 			recsim - Simulating the repair sequence for large-scale electrical grids, helping Distribution System Operators (DSOs) restore service after failures. This tool optimizes the repair process using mathematical models for parallel scheduling.

      		PPT 
 

			Alberto Tofani ENEA

			 tool • all phenomena • resilience

		

		 

			Resilience of the Italian National Transmission Grid

			The project focuses on the resilience of the Italian National Transmission Grid (NTG) managed by TERNA under climate change scenarios. It aims to analyze geotechnical hazards, such as landslides and volumetric collapses, and meteo-climatic extremes, including cyclones and intense rainfall events, that could affect the NTG over the next two to three decades. 

			

				Academic Impact

				Advances in decadal climate predictability and the performance of regional climate models.

			

			

				Economic Impact 

				Optimized climate adaptation investments for critical infrastructure. 

			

			

				Social Impact 

				Secured energy supply for vulnerable communities facing extreme climatic events. 

			

				Alberto Tofani ENEA, Roberto Bellotti UNIBA 

		

		

                        Multi-hazard assessment of Critical Infrastructure

			Earthquakes, landslides, and floods are among the natural phenomena impacting the world in recent years, particularly Italy. This led to a significant increase in global emergencies. Geographic Information Systems (GIS) can play a pivotal role in this context. Additionally, multi-criteria evaluation (MCE) techniques can effectively support addressing issues related to critical infrastructures' multi-hazard (dynamical) assessment. This tool integrates GIS and MCE to evaluate and map multi-hazards across the Italian territory for key critical infrastructure networks, including transportation, gas, and electric power. Examples of the results obtained are presented through a series of thematic maps created within the GIS environment.


			PPT 


			Maurizio Pollino ENEA

                         model • earthquake, landslide, flood • hazard, Critical Infrastructures, GIS

		

	



	Cultural Heritage

	The preservation of historical heritage is essential to protecting cultural and architectural legacy. Advanced techniques like sensor data mining and machine learning can be used to monitor and maintain the structural integrity of historical buildings and infrastructure. By analyzing historical monitoring data, these technologies can predict the structural behavior of a critical historical building, ensuring its long-term stability. 


	

		Brunelleschi's Dome

		Long-term project aimed at monitoring the stability of the monument and predicting its future response to distressing phenomena.

		A first study applies machine learning tools to unveil hidden patterns and correlations that would reveal the structural behaviour of the Dome as a whole and of its main parts. A second study investigates the impact of temperature, humidity and earthquakes on the evolution of the Brunelleschi's Dome cracks and explores the interrelations among neighboring cracks. It also examines the dynamic response of cracks to exogenous thermal shocks. 

  		

  			 Academic impact

			First effort to apply machine learning techniques and time series models (ARIMA, VAR, Impulse Response and Transfer Functions) for SHM 

  		

		

			 Economic impact

			Preventing financial losses associated with structural failures

		

		

			 Social impact

			Scalable monitoring approach to safeguard cultural heritage using rigorous statistical methods.

  		

  		PPT


		Fiammetta Menchetti UNIFI  

	



	Economy and Food supply

	

		Damage of the agricultural industry

		The sustainable management of land use plays a significant role in urban planning, influencing how land is allocated for residential, commercial, industrial, and recreational purposes. 

		

			Land use land cover change detection

			Researchers are exploring the use of AI to develop automated pipelines for land-use classification, with applications ranging from precision agriculture (e.g., monitoring crop health, such as olives and grapes) to addressing environmental issues like desertification and urbanization. AI-powered tools are being developed to monitor land-use patterns and predict their environmental impacts, helping to guide sustainable development practices.  


			BAT province use case: PPT 


			Roberto Bellotti UNIBA 


			 model, database  • exposure

		

		

			Crops vs Climatic Variations

			The sensitivity of the agricultural production system to short- and long-term climate variations significantly affects the availability and prices of food resources, raising relevant issues of sustainability and food security. 

			To evaluate the vulnerability of crop yield to short-term climate fluctuations and to determine whether it changes over time, UNIVAQ conducted a statistical analysis focusing on main crops in the Abruzzo region (central Italy), as case studies, such as wheat, olive and grape.


			Abruzzo case study: PPT


			Po plain case study


			 Marco Tallini UNIVAQ 


			 GIS, multi-parameter database, model, tool  • climatic variations, extreme events • agrometeorology, climatic analysis