JMJose Antonio Mantovani

Jose Antonio Mantovani

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jose Antonio Mantovani has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Predicting Regional Hourly Traffic Flow and Speed from Open Data: Machine Learning Framework and Cross-City Transferability

    by Sergio Ibarra Espinosa, Igor Tiburcio, Iara Da Silva, João Pedro Magri Martins, José Antonio Mantovani Júnior, Pedro de Melo, Rizzieri Pedruzzi, Leonardo Hoinaski, Taciana Toledo de Almeida Albuquerque, Edmilson Dias de Freitas, et al.

    Modeling traffic by vehicle type and speed at street level across all hours remains a global challenge. We predicted hourly traffic flow and speed over southeastern and southern Brazil using XGBoost regression on 200,420 OpenStreetMap road segments. Training data combined toll plaza counts from the São Paulo State Regulatory Agency for Delegated Public Transport Services (ARTESP; 464 stations, March 4–10, 2024), EMME/2 travel demand model outputs from the São Paulo Company of Traffic Engineering (CET) and São Paulo Transporte (SPTRANS) (47,894 urban segments), Traffic Engineering Company of Rio de Janeiro (CET-Rio) loop detectors (967 sensors, used for speed training and cross-city validation), and TomTom probe speed data (14,703 segments). Spatial covariates included DMSP-OLS nighttime lights, IBGE population density, ESA WorldCover land cover, and road density at three buffer scales. The passenger car model achieved R² = 0.728 on held-out temporal data (Thursday-Sunday), with R² = 0.79 on weekdays degrading to 0.56 on Sundays. Motorcycles (R² = 0.611), light commercial vehicles (R² = 0.549), and trucks (R² = 0.559) followed similar spatial patterns. Buses follow fixed transit routes and were reconstructed from GTFS schedule interpolation instead of spatial modeling. The speed model achieved R² = 0.92 (MAE = 5.8 km/h) on held-out data. Cross-city validation against CET-Rio data in Rio de Janeiro, about 400 km from the training data coverage, showed that spatial relationships transfer between cities but absolute magnitudes do not: the uncalibrated model overpredicts Rio traffic by 1.6–1.8×, while blending a minimal local temporal sample (three days) recovers R² = 0.54-0.62 with bias within ±5%. We provide the complete VEIN-ready dataset (five classes × 24 hours × weekday/weekend) for all 200,420 road segments.

  • Open Access

    Impact of PBL Schemes on the Simulation of PBL Height in the Central Amazon Basin

    by José Antonio Mantovani, Rayonil Carneiro, Camilla Kassar Borges, Sergio Ibarra-Espinosa, José Antonio Aravéquia, Gilberto Fisch, Dirceu Luis Herdies

    This study evaluates the performance of eleven Planetary Boundary Layer (PBL) schemes within the Weather Research and Forecasting (WRF) model over the Central Amazon Basin, focusing on contrasting wet and dry season conditions observed during the GoAmazon2014/5 campaign. High-resolution (1 km) simulations were conducted for representative periods in each season and validated against in situ observations. Model performance was assessed using multiple statistical metrics with the explicit separation of daytime convective and nighttime stable PBL regimes. Results reveal substantial variability among PBL schemes, strongly modulated by the season and diurnal cycle. Overall performance was higher during the wet period, whereas dry period simulations exhibited larger uncertainties, particularly under nocturnal conditions. The Shin–Hong (SH) PBL scheme had the best skill on average to reproduce the observed PBL height (PBLH) during the wet period, while the University of Washington (UW) PBL scheme was the best during the dry period. The Mellor–Yamada–Janjic (MYJ) PBL scheme had the best skill for daytime PBLH in both periods. Spatial analysis demonstrated how PBL schemes impact the PBLH distribution over the Central Amazon Basin, revealing a river-influenced pattern. These findings highlight the strong sensitivity of the Amazon PBL depth to PBL schemes and underscore the importance of appropriate PBL parameterizations and the vertical resolution for tropical applications.


  • Open Access

    Analysis of an extreme precipitation event on the coast of São Paulo in Brazil using the MPAS model

    by José Antonio Mantovani, Julio Pablo Reyes Fernandez, José Antonio Aravéquia, Silvio Nilo Figueroa, William Coelho, Éder Paulo Vendrasco, Enver Ramirez, Anahi Sobral, Jayant Pendharkar, Matheus José Arruda Lyra, et al.

  • Open Access

    Assessment of MPAS and WRF models for Severe Weather Forecasting in Southern Brazil

    by José Antonio Mantovani, Rafael Toshio Inouye, Sheila Paz, Reinaldo Olmar Kneib, Matheus José Arruda Lyra, Helber Barros Gomes, Fabricio Daniel dos Santos Silva, Leonardo Calvetti, César Beneti, Sérgio Ibarra Espinosa, et al.


  • Open Access

    Quantifying the Impact of High Emitters on Vehicle Emissions: An Analysis of Ecuador’s Inspection and Maintenance Program

    by Sergio Ibarra-Espinosa, Zamir Mera, Karl Ropkins, Jose Antonio Mantovani Junior

    On-road vehicles are a primary source of urban air pollution. It is known that high-emitting vehicles represent a fraction of the fleet but contribute significantly to the total emissions. Usually, road transportation emission inventories do not capture the impact of these types of vehicles, underestimating emissions. This study introduces a simple method to refine vehicle emission inventories by incorporating data from Ecuador’s Inspection and Maintenance (I/M) program. We analyzed I/M data from Quito to develop a correction factor for the Vehicular Emissions INventory (VEIN) model, accounting for the higher emissions from vehicles that fail inspection. Our analysis shows that while less than 10% of gasoline and 20% of diesel vehicles failed inspection, their emissions were substantially higher; for instance, accounting for reproved vehicles produced 60% more Carbon Monoxide (CO), 18% more Non-Methanic Volatile Organic Compounds (NMVOC), 40% more Particulate Matter with aerodynamical diameter of 2.5 µm or less (PM2.5), and 34% more or lower than 10 µm (PM10). These findings demonstrate that incorporating I/M data is crucial for accurately quantifying vehicular pollution. The proposed methodology offers a way to create more accurate emission estimates, providing a tool for policymakers to manage air quality.


  • Open Access

    Quantifying the Impact of High Emitters on Vehicle Emissions: An Analysis of Ecuador's Inspection and Maintenance Program

    by Sergio Ibarra-Espinosa, Zamir Mera, Karl Ropkins, Jose Antonio Mantovani

    On-road vehicles are a primary source of urban air pollution. It is known that high-emitting vehicles represent a fraction of the fleet but contribute significantly to the total emissions. Usually, road transportation emission inventories do not capture the impact of these types of vehicles, underestimating emissions. This study introduces a simple method to refine vehicle emission inventories by incorporating data from Ecuador's Inspection and Maintenance (I/M) program. We analyzed I/M data from Quito to develop a correction factor for the Vehicular Emissions INventory (VEIN) model, accounting for the higher emissions from vehicles that fail inspection. Our analysis shows that while less than 10% of gasoline and 20% of diesel vehicles failed inspection, their emissions were substantially higher; for instance, accounting for reproved vehicles produced 60% more CO, 18% more NMVOC, 40% more PM2.5, and 34% more PM10 . These findings demonstrate that incorporating I/M data is crucial for accurately quantifying vehicular pollution. The proposed methodology offers a way to create more accurate emission estimates, providing a tool for policymakers to manage air quality.

  • Open Access

    Evaluation of PBL Parameterization Schemes in WRF Model Predictions during the Dry Season of the Central Amazon Basin

    by José Antonio Mantovani Júnior, José Antonio Aravéquia, Rayonil Gomes Carneiro, Gilberto Fisch

    Planetary Boundary Layer (PBL) parameterization schemes are employed to handle subgrid-scale processes on atmospheric models, playing a key role in accurately representing the atmosphere. Recent studies have shown that PBL schemes are particularly fundamental to the depiction of PBL height (PBLH), especially over the Amazon. In the present study, we investigated the performance of PBL schemes on the representation of meteorological variables, turbulent fluxes, PBL vertical structures, and PBLH over the central Amazon basin under dry conditions, taking advantage of observations from the Observations and Modeling of the Green Ocean Amazon campaign (GoAmazon2014/5) for validation and evaluation. Numerical experiments were carried out within the WRF model using eight PBL schemes for two dry periods from 2014 (typical year) and 2015 (El-Niño year), and results from the 1-km resolution domain were directly compared to hourly in situ observations. In general, all PBL schemes present good performance to reproduce meteorological variables, with nonlocal (local) PBL schemes producing better performance in the 2014 (2015) study period. All PBL schemes in general overestimate (>100%) daytime turbulent fluxes. Thermodynamic (daytime) vertical structures are better predicted than mechanical (nocturnal) ones. The local MYNN2.5 scheme showed the overall best performance for PBLH prediction, mainly at night.