http://hdl.handle.net/11422/58 2026-05-06T22:59:51Z 2026-05-06T22:59:51Z Pereira Neto, Antonio Vicente http://hdl.handle.net/11422/29067 2026-04-17T06:39:40Z 2026-03-03T00:00:00Z

Title: Do determinístico ao aprendizado de máquina: uma nova abordagem para estimar a turbulência atmosférica Author(s)/Inventor(s): Pereira Neto, Antonio Vicente Advisor: França, Gutemberg Borges Abstract: The representation of atmospheric turbulence in the Planetary Boundary Layer is one of the main sources of uncertainty in numerical weather and climate models. In this work, the use of artificial neural networks of the Multi-Layer Perceptron type is proposed as surrogate models to emulate the Holtslag–Boville turbulence parameterization scheme in the Brazilian one-dimensional model BAM-1D. The neural networks were trained using data generated by BAM-1D simulations forced by observations from the GoAmazon 2014/15 campaign, using normalized atmospheric variables as inputs and turbulent coefficients (kvm, kvh) and counter-gradient terms (cgs, cgh), as well as the Planetary Boundary Layer height, as outputs. The implementation of the networks was carried out directly in Fortran, allowing their integration as drop-in replacements for the original physical scheme. The results indicate that the neural network reproduces with high fidelity the vertical structure and temporal variability of the turbulent coefficients, presenting high coefficients of determination for kvm and kvh, as well as low statistical errors (RMSE, MAE, and bias). The analysis of temperature and wind profiles demonstrates that replacing the HB scheme does not compromise the thermodynamic and dynamic consistency of the model, with differences mainly concentrated near the surface and in highly convective regimes. Additionally, the evaluation of precipitation as an integrated metric indicates that the neural network preserves the occurrence and temporal phase of events, although differences in the intensity of convective peaks are observed, reflecting the nonlinear nature of the process. From a computational perspective, the machine learning-based approach shows potential for cost reduction while maintaining physical consistency. The results confirm the feasibility of using neural networks as surrogate models in atmospheric parameterizations, opening perspectives for the development of more efficient and accurate hybrid models. Publisher: Universidade Federal do Rio de Janeiro Type: Tese

2026-03-03T00:00:00Z Mello, Ivan Bitar Fiuza de http://hdl.handle.net/11422/29066 2026-04-17T06:40:27Z 2026-03-01T00:00:00Z

Title: Previsão de turbulência de céu claro utilizando modelo híbrido sobre o sul do Brasil Author(s)/Inventor(s): Mello, Ivan Bitar Fiuza de Advisor: França, Gutemberg Borges Abstract: In this study, the application of machine learning (ML) algorithms is evaluated using simulations based on outputs from the Global Forecast System (GFS) and the Weather Research and Forecasting (WRF) models, with the objective of developing an optimized hybrid model for forecasting clear-air turbulence (CAT) over southern Brazil. Fourteen atmospheric predictors were used, extracted between the 500–200 hPa isobaric levels, initially derived from GFS forecast data and subsequently from WRF forecast data, with the latter driven by GFS analysis fields. These attributes were simulated at different spatial resolutions in order to train and validate 15 distinct machine learning models. The model development and comparison methodology involved stratified sampling, feature engineering, hyperparameter optimization, and robust validation of statistical metrics, including Probability of Detection of CAT events (PODy), Probability of Detection of non-events (PODn), True Skill Statistic (TSS), F-measure, Area Under the Receiver Operating Characteristic Curve (AUC), and the Relative Percentage Difference of AUC between WRF and GFS ((AUC_WRF–AUC_GFS)/AUC_GFS) × 100. Among the evaluated algorithms, the Bagging classifier showed the best overall performance when considering AUC values obtained from both GFS and WRF forecast datasets. Although Extra Trees model achieved a slightly higher AUC than Bagging when using WRF data, vi the AUC difference between the two models in the GFS simulations was marginally larger than that observed for WRF. Thus, Bagging stood out for its more consistent performance across the combined dataset, while Extra Trees exhibited marginally superior performance when applied specifically to WRF forecasts. The KNN classifier showed the greatest gain in Relative Percentage Difference of AUC in the comparison between GFS and WRF-based models. The predictor exclusion method confirmed that potential temperature (Θ) and vertical wind shear / wind speed difference indicators (VWS, DWS) were the attributes that best represented effective CAT detection, while turbulent kinetic energy (TKE) and turbulence indices did not achieve satisfactory performance. The results demonstrate the potential of regionally training ML techniques with numerical weather prediction models—emphasizing the use of higher spatial resolution physical models—to substantially improve CAT detection compared to traditional diagnostic methods. In the operational context, the Bagging and Extra Trees models showed more satisfactory performance for issuing more accurate clear-air turbulence (CAT) alerts in the upper air corridor between the cities of São Paulo and Porto Alegre, within the Curitiba Flight Information Region (FIR-CW). Consequently, reliance on the subjectivity of aircraft turbulence reports is reduced, enhancing flight safety and lowering operational costs. Future research should focus on using datasets with higher spatial and temporal resolution, exploring additional turbulence diagnostics, and selecting different study areas and seasonal periods to further improve CAT predictive capability for operational applications. Publisher: Universidade Federal do Rio de Janeiro Type: Tese

2026-03-01T00:00:00Z Pinto, Ana Beatriz de Souza http://hdl.handle.net/11422/29010 2026-04-02T03:00:15Z 2025-01-01T00:00:00Z

Title: Relação entre florações de algas e ocorrência de névoas e nevoeiros marítimos durante o verão na Baía de Guanabara Author(s)/Inventor(s): Pinto, Ana Beatriz de Souza Advisor: Palmeira, Ana Cristina Pinto de Almeida Abstract: The study of interactions between algal blooms and the formation of fog and mist in Guanabara Bay aims to deepen the understanding of how environmental and meteorological variables may influence visibility reduction events in this region, which holds significant environmental and socioeconomic importance in the state of Rio de Janeiro. Variables investigated included sea surface temperature (SST), salinity, visibility, tidal conditions, and climate indices, along with algal bloom data derived from Sentinel-2 and Sentinel-3 satellite images. Days selected for analysis were focused on periods when fog or mist was observed at the Galeão and Santos Dumont airports and availability of cloud-free satellite imagery. Analyses involved Pearson correlation calculations among variables, followed by the application of Principal Component Analysis (PCA) to identify multivariate interactions and complex patterns that would not be detected by simple correlation methods. The results indicated that although direct correlations among variables were generally weak, there were signs that algal blooms, interacting with factors such as SST and salinity, may contribute to fog formation, particularly in the inner bay areas, where oceanic water circulation is less intense. The application of PCA reinforced these observations, also indicating that La Niña events appear to intensify the frequency and duration of fog events at Santos Dumont Airport, suggesting a nonlinear interaction between oceanic indices and local variables. The findings highlight the importance of integrated approaches in analyzing complex atmospheric phenomena and suggest the need for future investigations that include continuous monitoring, additional data on water quality, and characterization of algal species in blooms for a more detailed understanding of these interactions Publisher: Universidade Federal do Rio de Janeiro Type: Dissertação

2025-01-01T00:00:00Z Oliveira, Mayara Villela de http://hdl.handle.net/11422/28978 2026-03-29T03:00:14Z 2025-03-01T00:00:00Z

Title: Técnicas de inteligência computacional aplicadas à modelagem chuva vazão Author(s)/Inventor(s): Oliveira, Mayara Villela de Advisor: França, Gutemberg Borges Abstract: Rainfall-runoff modeling is fundamental for water resource management; however, its inherently non-linear nature and the influence of large-scale climatic phenomena represent a significant methodological challenge for traditional hydrological models. This work aimed to develop and evaluate a monthly flow forecasting model for the DO 3 Hydrographic District, outlet at Naque Velho, using computational intelligence techniques. The methodology adopted explored the potential of Artificial Neural Networks (ANNs) coupled with a Genetic Algorithm (GA). This was used for the global search of an optimal set of synaptic weights, aiming to overcome the vulnerability of the backpropagation algorithm to local minima and ensuring greater robustness and accuracy in network training. The results demonstrated that the model achieved median performance, converging in less than 20 generations, with a final fitness of 0.79. Flood events were fully captured within the upper predicted range, confirming that the model adequately incorporated the effect of antecedent precipitation and surface runoff memory; however, it showed superior performance during the dry season. The complete coverage of extremes (COV_ext=1) demonstrates the system's ability to handle hydrologically critical episodes without inflating average predictions. The model consolidates a hybrid approach capable of representing the uncertainty and seasonal variability of the basin. Its structure allows for a more faithful modeling of hydrological behavior, maintaining statistical robustness and operational simplicity Publisher: Universidade Federal do Rio de Janeiro Type: Dissertação

2025-03-01T00:00:00Z