Geodaysit 2023

Marco Scaioni

Marco Scaioni, Civil Engineering MSc Degree (Politecnico Milano, Italy, 1995), PhD on Geodetic and Mapping Sciences (Politecnico Milano, 1999).
Full Professor of Geomatics at Politecnico Milano, Dept. of Architecture, Built Environment and Construction Engineering (ABC). Head of ABC-PhD programme.
Formerly, Full Professor in the College of Surveying and Geo-Informatics at Tongji University, Shanghai (2011-2014).
Main research interests: Photogrammetry and Laser scanning from multiple platforms, Integration GIS/BIM for buildings and infrastructures, Geomatics for Geosciences (Glaciology and Geology) and Cultural Heritage, Geodatabases for urban planning, Deep Learning classification of point clouds.
Associate Editor of Applied Geomatics (Springer) and the ISPRS Journal of Photogrammetry and Remote Sensing (Elsevier).
He published more than 310 scientific papers, including 65 papers on WoS-indexed journals (H-index: 22), 171 Scopus-indexed papers (H-index: 30) and two edited books.


Air Quality Monitoring and Prediction in Ukraine During War Crisis Using Copernicus Data and Machine Learning
Marco Scaioni, Mohammad Mehrabi, Mattia Previtali

In late February 2022, the invasion of Russia in the Ukrainian territory started. As is known, air is one of the most affected components of the environment during such exceptional circumstances. The changes in the pattern of civilian and industrial activities may cause the variation of air quality in terms of different pollutants. Hence, conducting proper air quality assessment can be of great importance in the war-affected areas. The pivotal objective of this research is to present an overview of air quality monitoring and air pollution prediction carried out for Ukrainian territory. Utilizing the Copernicus Sentinel-5P TROPOMI observations, the emissions of ozone (O3), nitrogen dioxide (NO2), formaldehyde (HCHO), and carbon monoxide (CO) in Kiev, Kharkiv, Donetsk, Kherson, and Lviv are monitored during 2022. The relevant records are compared to the same business-as-usual (BAU) periods in 2019 and 2021 to detect significant changes. Visual interpretations supported by statistical analysis proved that the ongoing war has significant impacts on the concentration of pollutants throughout Ukraine. Following this, a hybrid machine learning model is developed to predict the concentration of a well-known air quality indicator called particulate matter 2.5 (PM2.5). The prediction results indicated a reliable accuracy of the proposed methodology, as well as its superiority over benchmark models. In short, this research shows promising application of state-of-the-art technologies inducing remote sensing and artificial intelligence for solving air quality problems in during exceptional events.

AIT Contribution
Sala Biblioteca @ PoliBa
Assessment of infrastructure deformation using EGMS-InSAR data and geo-environmental factors through machine learning: Railways and highways of Lombardy Region, Italy
Marco Scaioni, Rasoul Eskandari, Ziyang Wang

Linear Infrastructures, characterized by high level of systemic vulnerability [1,2], are subject to several environmental and geological hazards. In the context of risk assessment and management, monitoring these important assets plays an important role in establishing the maintenance planning and preventive measures against the disruptive phenomenon, such as ground deformation due to natural and anthropogenic causes. In-situ and traditional infrastructure monitoring approaches, such as high-precision leveling measurements [3], are known to be costly and time-consuming. On the other hand, satellite Remote Sensing (RS) techniques, such as Synthetic Aperture Radar (SAR) Interferometry (InSAR), are recognized to be promising tools for monitoring and condition assessment of infrastructures [4].
As an essential branch of Copernicus Land Monitoring Service (CLMS), the new European Ground Motion Service (EGMS) is providing freely accessible ground deformation data spatially covering almost all European countries. The deformation time time-series contained in the datapoints are acquired based on InSAR processing of Sentinel-1 images from January 2016 up to December 2021 [5,6].
In this study, InSAR-derived deformation dataset, geo-environmental parameters, and Machine Learning (ML) techniques have been integrated to address the major causes of this complex phenomenon, specifically emphasizing railway and highway in Lombardy region, Italy. The vertical displacement velocities (mm/year) of EGMS datapoints located at the neighborhood of these infrastructures are utilized as the input ground motion data. The conditioning factors considered in this work include elevation, slope angle, slope aspect, precipitation, curvature, solar radiation, and Normalized Difference Vegetation Index (NDVI). The ML models, including Decision Tree (DT), Linear regression (LR), Light GBM (LG), XGBoost (XG), Random Forest (RF) and Extra Trees (ET), are used in this study. The Train-Test dataset ratio is considered to be 7:3, with respect to the higher performance of this ratio [7].
First, the used models have been validated using the Area Under ROC Curve (AUC), and ROC being Receiver Operating Characteristic curve. The results mostly show accep results (interval of 0.7 to 0.8) and the applicibility of the model. Then, the Relative Feature Importance (RFI) analysis is carried out to address the significant factors causing the ground deformatio. Also, the results regarding the Permutation-based and Shapley Additive Explanations (SHAP) importance decisions among the factors show that the rainfall (precipitation) and elevation are playing the most important role in the occurrence of the ground deformation detected on the infrastructures, based on the methodology adopted in this study. Also, the effect of solar radiation cannot be neglected. More detailed and further discussion of the results will be provided in the full version of this letter.

AIT Contribution
Sala Biblioteca @ PoliBa