Caio Fonteles

Caio Fonteles

Auto-generated profile, based on publicly available information

Caio Fonteles


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
5 February 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
MCMaria Castro
Maria Castro
JPJoão Pedro Almeida Teixeira Paixão
João Pedro Almeida Teixeira Paixão
IGInês Girão
Inês Girão
BMBruno Marques
Bruno Marques
RZRune Zeitzen
Rune Zeitzen
AOAna Patrícia Oliveira
Ana Patrícia Oliveira
As climate change prospects point towards the pressing need for local-scale adaptation measures, it becomes of utmost importance to recognise intra-urban hotspots of excessive heat exposure. Accordingly, there is a pressing societal need to downscale the available near-surface air temperature predictions (reanalysis, forecasts, or projections) from the regional (kilometric) to a local (sub-kilometric) scale, to facilitate the identification of short-term critical areas within metropolitan regions of cities, where acclimatisation and public health preventive measures actions should be prioritised. This work presents a Machine Learning (ML)-based methodology for upsampling near-surface air temperature from a 2.5x2.5Km to a 125×223m (0.002x0.002°) grid, the Urban Thermal Signal Downscaling (UTS-D) model. The model was developed over four Danish Functional Urban Areas - Copenhagen, Aarhus, Aalborg and Odense - using crowdsourced data from citizen-own weather stations, along with geospatial predictors that are well-known determinants of the Urban Heat Island (UHI) effect. The best overall results were achieved with a Random Forest model with an overall Mean Absolute Error (MAE) of 0.76K for the overall test subset, 0.66K during HW and 0.85K during CW subsets, denoting the model’s good performance under extreme heat conditions. When evaluating against reference in-situ stations, the model’s accuracy shows a slight decrease compared to the background numerical weather predictor model, suggesting that, by training solely on crowdsourced stations (clustered in urban areas), there is a tendency towards overestimating rural air temperatures. Nevertheless, regarding the spatial pattern, the model captures the thermal signature of the underlying urban infrastructure, allowing to disclose neighbourhood-level details.

14 March 2026
Verified
Conference Paper
Open access
ABAndré Brito
André Brito
Ana OliveiraAna Oliveira
Ana Oliveira
BMBruno Marques
Bruno Marques
CFCaio Fonteles
Caio Fonteles
ÉPÉlio Pereira
Élio Pereira
VTVital Teresa
Vital Teresa
Climate resilience is a defining challenge of the 21st century, yet public health authorities continue to face difficulties in operationalising state-of-the-art geospatial and environmental science. In Portugal, as in Europe more broadly, extreme temperatures have already increased in frequency and severity, contributing to substantial excess mortality and morbidity. These impacts are often amplified by the simultaneous degradation of air quality. However, evidence has largely been event-specific, fragmented across case studies of individual heatwaves, cold waves, or air-quality episodes, limiting our ability to implement early-warning systems. The ESA-funded AIR4health project, developed under the Early Digital Twin Components initiative, addresses these gaps by designing innovative algorithms to predict human mortality and morbidity during compound extreme events. The project develops two Machine Learning (ML)–based AIR4health Risk Algorithms focusing on (1) Heat & Ozone and (2) Cold & Nitrogen Dioxide, using a two-decades-long, high-resolution healthcare database for mainland Portugal. These indicators will integrate EO data, in-situ air-quality records from the EEA, and CAMS/C3S model outputs. Satellite and model data are dynamically downscaled using approaches previously demonstrated for air-temperature modelling in Lisbon, enabling daily, spatially detailed (municipal-level) time series of compound extreme events. AIR4health advances beyond current country-level systems by implementing fully spatiotemporal exposure–response modelling. Its dynamic and continuous framework will deliver a prototype DTC capable of providing fine-scale early warning for combined climate and air-quality extremes. By benchmarking results against European-level datasets, AIR4health will support scalable pathways towards relevant practices in planetary health and climate-preparedness, while contributing to the broader European Digital Twin ecosystem.

25 March 2025
Verified
Conference Paper
Open access
FCFrancisco Javier Campuzano
Francisco Javier Campuzano
ANAntonio Novellino
Antonio Novellino
PGPatrick Gorringe
Patrick Gorringe
CFCaio Fonteles
Caio Fonteles
LFLuís Figueiredo
Luís Figueiredo
MAMarco Alba
Marco Alba
Rivers significantly influence coastal ecosystems by delivering freshwater, nutrients, and sediments that support biodiversity and help counteract beach erosion. However, they also act as conduits for pollution, transporting harmful chemicals and waste, including marine litter and microplastics, from inland areas to the ocean.Rivers also create complex hydrodynamic interactions with coastal circulation, affecting water movement, stratification, mixing patterns, and the formation of fronts. These dynamics intensify during extreme events like heavy rainfall, floods, and storms, which can increase the volume and speed of river flow, leading to greater impacts on coastal areas. Climate change compounds these effects by increasing the frequency and intensity of extreme weather events.For these reasons, it is crucial that state-of-the-art operational coastal numerical models incorporate near-real-time river data to improve the quality of hydrodynamic forecasts. These forecasts are essential for supporting decision-making in environmental protection and search-and-rescue operations during extreme events.To meet these needs, the EMODnet River Node has been designed to provide a dedicated hydrological service for the coastal community. It offers free access to near-real-time river data in a standardized format, adhering to the FAIR principles, all on a single platform. The system collects data from the hydrologic station nearest to each river's coastal area, excluding stations influenced by tides. The service currently provides river flow data for all stations and, where available, water temperature and water level data. It integrates information from over 1,000 stations, supplied by 40 national and regional water administrations across 22 countries on three continents: Europe, North America, and South America. In the near future, the service aims to continue expanding its coverage and include additional river data, such as biogeochemical information.

25 October 2026 in Urban Science
Verified
Journal Article
Open access
PDF file
VMVitor F. V. V. de Miranda
Vitor F. V. V. de Miranda
MCMaria Castro
Maria Castro
JPJoão Pedro Almeida Teixeira Paixão
João Pedro Almeida Teixeira Paixão
IGInês Girão
Inês Girão
BMBruno Marques
Bruno Marques
Ana OliveiraAna Oliveira
Ana Oliveira
Intra-urban air temperature is highly heterogeneous, and coarse-resolution products cannot resolve the neighbourhood-scale variability that urban heat management requires. The objective of this study is to assess whether the Urban Thermal Signal Downscaling (UTS-D) methodology, previously developed and tested over Danish Functional Urban Areas (FUAs) with the DAnish ReAnalysis (DANRA), can be re-implemented with a pan-European reanalysis and retrained in cities with contrasting climates, and to quantify the incremental value of a vegetation-seasonality predictor. The approach is applied to four European FUAs spanning contrasting climate zones, i.e., Copenhagen (Denmark), Lisbon (Portugal), Seville (Spain) and Athens (Greece). Two modifications were introduced: the regional weather component was replaced with the pan-European Copernicus Regional Reanalysis (CERRA), enabling application beyond Denmark, and a monthly climatological Normalized Difference Vegetation Index (NDVI) was added as a non-fixed predictor to capture the seasonality of vegetation cooling. A Random Forest model was trained to predict the residual bias between CERRA 2 m air temperature and quality-controlled observations from citizen-owned weather stations, combined with static landscape and urban predictors. Using a 2019–2022 training/cross-validation strategy and an independent 2023 test year, the downscaled model substantially outperformed raw CERRA in all four cities, reducing the test-year mean absolute error from 1.02–1.99 °C to 0.69–1.06 °C (a 32–55% reduction) and reaching R2 of 0.94–0.98. Absolute error reductions were particularly relevant on hot days (HD) (0.52–1.21 °C); however, such periods are also the ones during which CERRA errors tend to be largest, indicating that the hot-day added value mainly reflects the correction of a larger reanalysis bias. NDVI provided only a marginal additional improvement (≤0.02 °C; ≤2%), statistically significant but negligible in practical terms. Errors were lowest in Copenhagen, which has the densest citizen-station network, and highest in Seville, which has the sparsest; however, a network-thinning experiment showed that station density explains only part of these differences, pointing to the combined role of station density, the magnitude of the reanalysis error, climate and urban morphology. These results show that UTS-D is methodologically transferable, i.e., it can be retrained successfully with CERRA wherever sufficiently dense citizen-station observations exist, and provide a basis for future heat-health and urban adaptation applications.

18 March 2025
Verified
Conference Paper
Open access
JRJerimar Vasquez Rojas
Jerimar Vasquez Rojas
JCJuan Carbone
Juan Carbone
IAIzquierdo Alfredo
Izquierdo Alfredo
JGJavier Benavente González
Javier Benavente González
JEJesús Gómez Enri
Jesús Gómez Enri
FCFrancisco Javier Campuzano
Francisco Javier Campuzano
The main objective of the OceanUCA project is the modernization of the technological infrastructure of the University of Cadiz in relation to atmospheric and hydrodynamic numerical modeling specifically configured to simulate physical processes on the coast of Andalusia (Spain).The initiative focuses on the improvement of modeling systems (oceanographic and atmospheric) and the modernization of servers, mainly THREDDS and ERDDAP. THREDDS facilitates connectivity between scientific data providers and end users, while ERDDAP simplifies the sharing and visualization of time series data through common formats, graphics and maps. The project aims to optimize access, organization and storage of data, create a complete data bank and standardize protocols.For the storage of data from numerical models, a file server is acquired that allows the custody of large volumes of information related to simulated physical processes, especially focused on the Andalusian coasts. In the future, this server will also facilitate the storage of data from other sources for further calculation, processing and sampling. This acquisition contributes to centralizing the files, currently distributed across different storage sources, and to improving communication across the THREDDS/ERDDAP servers.The project includes a web application that presents the models in a user-friendly and interpretable format, especially for the scientific community, through the visualization of images.The technological infrastructure will allow significant advances by facilitating the download of numerical data and taking advantage of graphical processing and high-performance computing to process large data sets. This approach improves the scalability and resolution of forecasts, making them more accessible to the public. By adopting an open-source framework, the project promotes collaboration and knowledge sharing at national and international scales, empowering both the scientific community and the public to use coastal and atmospheric data for informed decision-making and sustainable resource management.

1 September 2026 in Applied Ocean Research
Verified
Journal Article
Open access
Christos StefanakosChristos Stefanakos
Christos Stefanakos
IAIñigo Aguilera
Iñigo Aguilera
CFCaio Fonteles
Caio Fonteles
ØKØyvind Knutsen
Øyvind Knutsen