Marcio Fontana

Marcio Fontana

Auto-generated profile, based on publicly available information

Marcio Fontana

Federal University of Bahia,Salvador,Brazil, Brazil

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
25 December 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
ECErbet Almeida Costa
Erbet Almeida Costa
CRCarine Menezes Rebello
Carine Menezes Rebello
MFMárcio Fontana
Márcio Fontana
LSLeizer Schnitman
Leizer Schnitman
Idelfonso Bessa dos Reis NogueiraIdelfonso Bessa dos Reis Nogueira
Idelfonso Bessa dos Reis Nogueira
Robust learning is an important issue in Scientific Machine Learning (SciML). There are several works in the literature addressing this topic. However, there is an increasing demand for methods that can simultaneously consider all the different uncertainty components involved in SciML model identification. Hence, this work proposes a comprehensive methodology for uncertainty evaluation of the SciML that also considers several possible sources of uncertainties involved in the identification process. The uncertainties considered in the proposed method are the absence of a theory, causal models, sensitivity to data corruption or imperfection, and computational effort. Therefore, it is possible to provide an overall strategy for uncertainty-aware models in the SciML field. The methodology is validated through a case study developing a soft sensor for a polymerization reactor. The first step is to build the nonlinear model parameter probability distribution (PDF) by Bayesian inference. The second step is to obtain the machine learning model uncertainty by Monte Carlo simulations. In the first step, a PDF with 30,000 samples is built. In the second step, the uncertainty of the machine learning model is evaluated by sampling 10,000 values through Monte Carlo simulation. The results demonstrate that the identified soft sensors are robust to uncertainties, corroborating the consistency of the proposed approach.

9 January 2024 in Heliyon
Verified
Journal Article
Open access
ECErbet Almeida Costa
Erbet Almeida Costa
CRCarine de Menezes Rebello
Carine de Menezes Rebello
VSVinicius Viena Santana
Vinicius Viena Santana
GRGaldir Damasceno Reges
Galdir Damasceno Reges
TSTiago de Oliveira Silva
Tiago de Oliveira Silva
LSLeizer Schnitman
Leizer Schnitman
This work proposes a new methodology to identify and validate deep learning models for artificial oil lift systems that use submersible electric pumps. The proposed methodology allows for obtaining the models and evaluating the prediction's uncertainty jointly and systematically. The methodology employs a nonlinear model to generate training and validation data and the Markov Chain Monte Carlo algorithm to assess the neural network's epistemic uncertainty. The nonlinear model was used to overcome the limitations of the need for big datasets for training deep learning models. However, the developed models are validated against experimental data after training and validation with synthetic data. The validation is also performed through the models' uncertainty assessment and experimental data. From the implementation point of view, the method was coded in Python with Tensorflow and Keras libraries used to build the neural Networks and find the hyperparameters. The results show that the proposed methodology obtained models representing both the nonlinear model's dynamic behavior and the experimental data. It provides a most probable value close to the experimental data, and the uncertainty of the generated deep learning models has the same order of magnitude as that of the nonlinear model. This uncertainty assessment shows that the built models were adequately validated. The proposed deep learning models can be applied in several applications requiring a reliable and computationally lighter model. Hence, the obtained AI dynamic models can be employed for digital twin construction, control, and optimization.

26 January 2022 in Journal of Petroleum Science and Engineering
Verified
Journal Article
Closed access
GRGaldir Damasceno Reges
Galdir Damasceno Reges
MFMarcio Fontana
Marcio Fontana
ECErbet Costa
Erbet Costa
ALAntonio Lima
Antonio Lima
MRMarcos Ribeiro
Marcos Ribeiro
LSLeizer Schnitman
Leizer Schnitman

1 July 2014 in Nanotechnology, Science and Applications
Verified
Journal Article
Open access
MFMarcio Fontana
Marcio Fontana
YLYian Liu
Yian Liu
MMMateus S Moura
Mateus S Moura
ACAdemir J Costa
Ademir J Costa
LALuiz Alberto Almeida
Luiz Alberto Almeida
MPMakarand Paranjape
Makarand Paranjape
Hysteresis modeling in ballistic carbon nanotube field-effect transistors Yian Liu,1 Mateus S Moura,2 Ademir J Costa,2,3 Luiz Alberto L de Almeida,4 Makarand Paranjape,1 Marcio Fontana21Department of Physics, Georgetown University, Washington, DC, USA; 2Department of Electrical Engineering, Federal University of Bahia, Salvador, Brazil; 3Federal Institute of Bahia, Santo Amaro, Brazil; 4Engineering, Modeling and Applied Social Sciences Center, Federal University of ABC, Santo André, Brazil Theoretical models are adapted to describe the hysteresis effects seen in the electrical characteristics of carbon nanotube field-effect transistors. The ballistic transport model describes the contributions of conduction energy sub-bands over carbon nanotube field-effect transistor drain current as a function of drain-source and gate-source voltages as well as other physical parameters of the device. The limiting-loop proximity model, originally developed to understand magnetic hysteresis, is also utilized in this work. The curves obtained from our developed model corroborate well with the experimentally derived hysteretic behavior of the transistors. Modeling the hysteresis behavior will enable designers to reliably use these effects in both analog and memory applications.Keywords: ballistic transport, nanoscale device, solid-state device

1 February 2008 in The 9th International Conference on Advanced Communication Technology
Verified
Conference Paper
Closed access
MFM. Fontana
M. Fontana
Fabiano CostaFabiano Costa
Fabiano Costa
USU. B. Sangiorgi
U. B. Sangiorgi
PBP. A. D. Bichara
P. A. D. Bichara
DGD. Guimaraes
D. Guimaraes
ALA. C. C. de Lima
A. C. C. de Lima
In this paper, we propose a computer aided design (CAD), so called HiperionCAD, which allows the design and optimization of optical communication networks. The tool has been developed by means of the model driven development (MDD) approach. A graphical modeling framework (GMF) has been employed to model the domain, automatic code generation and graphic edition of the object models. The HiperionCAD software allows the network visual design and the following computations: power budget, chromatic dispersion and polarization mode dispersion. Moreover, we propose an optimization procedure, which is provided as one of the HiperionCAD's tools, based on genetic algorithms (GA) so that each device comprising the optical network is set to optimize its power budget.

4 February 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
ECErbet Almeida Costa
Erbet Almeida Costa
OAOdilon Santana Luiz de Abreu
Odilon Santana Luiz de Abreu
GRGaldir Damasceno Reges
Galdir Damasceno Reges
TSTiago de Oliveira Silva
Tiago de Oliveira Silva
CRCarine Menezes Rebello
Carine Menezes Rebello
LSLeizer Schnitman
Leizer Schnitman
This study presents practical details and results from implementing model-based predictive controllers for artificial lift systems in oil production, which utilise electrical submersible pumps (ESPs). The proposed methodology integrates the existing instrumentation architecture with new control systems and techniques. This work implements two control strategies: a standard MPC and an MPC with input targets. Both were executed in real time, encapsulated in a C++ executable, and deployed within Petrobras's supervisory and control system. The results include an analysis of the instrumentation system, a discussion of operation under unmeasured disturbances and constraints, and a comparison of the controllers. The findings are extensive and indicate that both controllers stabilise the system, ensure constraint satisfaction, and appropriately compensate disturbances.