Sylvain Watelet

Dr. Sylvain Watelet


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 April 2022 in Sensors
Verified
Journal Article
Open access
PDF file
TBToon Bogaerts
Toon Bogaerts
SWSylvain Watelet
Sylvain Watelet
NBNiko De Bruyne
Niko De Bruyne
CTChris Thoen
Chris Thoen
TCTom Coopman
Tom Coopman
PHPeter Hellinckx
Peter Hellinckx
Road weather conditions such as ice, snow, or heavy rain can have a significant impact on driver safety. In this paper, we present an approach to continuously monitor the road conditions in real time by equipping a fleet of vehicles with sensors. Based on the observed conditions, a physical road weather model is used to forecast the conditions for the following hours. This can be used to deliver timely warnings to drivers about potentially dangerous road conditions. To optimally process the large data volumes, we show how artificial intelligence is used to (1) calibrate the sensor measurements and (2) to retrieve relevant weather information from camera images. The output of the road weather model is compared to forecasts at road weather station locations to validate the approach.

18 June 2021
Verified
Other
Open access
SWSylvain Watelet
Sylvain Watelet
JBJoris Van Den Bergh
Joris Van Den Bergh
MRMaarten Reyniers
Maarten Reyniers
WCWim Casteels
Wim Casteels
TBToon Bogaerts
Toon Bogaerts
PHPeter Hellinckx
Peter Hellinckx
For the generation of accurate warnings for dangerous road conditions, road weather models typically depend on observations from road weather stations (RWS) at fixed locations along roads and highways. Observations at higher resolution in space and time have the potential to provide more localized, real-time weather warnings. The rise of connected vehicles with onboard sensing capabilities opens up exciting new opportunities in this field. For this purpose, a heterogeneous group of industrial stakeholders and researchers consisting of more than thirty partners from seven countries including Belgium, initiated the CELTIC-NEXT project "Secure and Accurate Road Weather Services" (SARWS). The goal of SARWS is to provide real-time weather services by expanding observational data from traditional RWS sources with data from large-scale vehicle fleets. The Belgian consortium consists of Verhaert New Products & Services, Be-Mobile, Inuits, bpost, imec - IDLab (University of Antwerp) and the Royal Meteorological Institute of Belgium (RMI). Within the Belgian consortium, the focus is on the use of vehicle data to enable real-time warning services for potentially dangerous local weather and road surface conditions. The vehicle fleet consists of cars of the Belgian Post Group (bpost) in the region around Antwerp, and will consist of 15 cars by the end of summer 2021. Data on vehicle dynamics, such as wheel speed, are gathered from the vehicle's CAN bus, while an additional installed sensor box collects air temperature, relative humidity and road surface temperature observations. Data on wipers and fog light activation, and camera images are also collected.We present the Belgian SARWS setup, data flow, and the developed data distribution platform. We discuss validation results for 2021, comparing car sensor observations to close RWS and weather stations, focusing mainly on air temperature, humidity and road surface temperature, and show the need for calibration and bias correction. We also demonstrate an experimental version of the RMI road weather model that provides short-term road weather forecasts for 50-meter road segments, using car sensor data for initialization, and compare with road weather forecasts at nearby station locations. We also demonstrate machine learning approaches that are explored to detect weather information from the vehicle dynamics.

3 March 2023
Verified
Conference Paper
Open access
SWSylvain Watelet
Sylvain Watelet
LDLaurent Delobbe
Laurent Delobbe
MRMaarten Reyniers
Maarten Reyniers
In the frame of a Belgian project aiming at improving the hydrometeors classification near the ground through the use of radar observations, two dual-pol classification schemes and a single-pol one including hail are tested and compared with crowd-sourced observations. The first scheme is based on the work of Keenan (2003) and is a supervised method making use of fuzzy logic while the second one is a semi-supervised method designed by Besic et al. (2016) that includes clustering as well as fuzzy logic. The single-pol scheme follows the Waldvogel method and is the current operational method used at the Royal Meteorological Institute of Belgium (RMIB). The crowd-sourced observations are collected through the smartphone application of the RMIB. This application was released in 2019 and allows every user to report the real-time weather, including the occurrence of hail and its size. We will present the validation scores and analyse the behaviour of the three methods for several hail storms. The uncertainties will be discussed, not only related to the three classification schemes but also to the users’ reporting behaviour and the scarcity of the hail events. Finally, the short term perspectives of further improvement of the hydrometeors classification will be given.

28 June 2022
Verified
Conference Paper
Open access
SWSylvain Watelet
Sylvain Watelet
LDLaurent Delobbe
Laurent Delobbe
MRMaarten Reyniers
Maarten Reyniers
Taking place at the Royal Meteorological Institute of Belgium (RMIB), the ongoing 2-year PRECIP-TYPE project aims at improving the hydrometeor classification in Belgium through the use of dual-pol radar observations and Numerical Weather Prediction (NWP) model output. Combining these two sources of information in a fuzzy logic scheme yields an estimate of the precipitation type (rain, hail, snow,...) at the height of the measurement of the radar. This information is then further processed by using vertical temperature, humidity and pressure profiles from NWP output in order to account for the melting process that can occur before precipitation reaches the ground. The output of this precipitation type product is compared to the crowdsourced weather reports sent by the users of the RMIB smartphone app. Such user reports can include the precipitation type as well as the size of the hydrometeors. These reports are ingested in a database of the RMIB and undergo reliability checks that allow an easier discrimination between realistic and unrealistic observations. We present the step-by-step methodology followed to obtain this first product version, including an extended clutter filtering, and we demonstrate its capabilities for a few challenging cases. We discuss the identified uncertainties and the remaining open questions. Regarding the perspectives, several possibilities are considered to further enhance this preliminary precipitation type product, such as the merging of dual-pol observations obtained from several radars, the comparison with alternative schemes of hydrometeor classification or the inclusion of the citizen observations (RMIB app) within the classification scheme. An overview of these lines of research will be presented.

28 March 2022
Verified
Conference Paper
Open access
SWSylvain Watelet
Sylvain Watelet
LDLaurent Delobbe
Laurent Delobbe
MRMaarten Reyniers
Maarten Reyniers
The precipitation type (e.g. rain, snow, hail) is of great importance in many areas such as road and aviation safety, severe weather warnings, hydrology, and agriculture. The purpose of the present research at the Royal Meteorological Institute of Belgium (RMI) is to combine the weather information from several sources in order to provide a comprehensive real-time product of the precipitation type at ground in Belgium. The preliminary results, based on observations from dual-polarization weather radars as well as on NWP model outputs, will be discussed. A comparison of these results with the crowd-sourced observations gathered through the RMI smartphone application will be shown and the perspectives for further developments will be presented.