Eduardo Costa de Carvalho

Dr. Eduardo Costa de Carvalho


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
20 September 2024 in Biodiversity Data Journal
Verified
Journal Article
Open access
PDF file
NMNubia Marques
Nubia Marques
CSCarla Danielle de Melo Soares
Carla Danielle de Melo Soares
DCDaniel de Melo Casali
Daniel de Melo Casali
EGErick Guimarães
Erick Guimarães
FFFernanda Fava
Fernanda Fava
VTValéria da Cunha Tavares
Valéria da Cunha Tavares
Biodiversity data, particularly species occurrence and abundance, are indispensable for testing empirical hypothesis in natural sciences. However, datasets built for research programmes do not often meet FAIR (findable, accessible, interoperable and reusable) principles, which raises questions about data quality, accuracy and availability. The 21st century has markedly been a new era for data science and analytics and every effort to aggregate, standardise, filter and share biodiversity data from multiple sources have become increasingly necessary. In this study, we propose a framework for refining and conforming secondary biodiversity data to FAIR standards to make them available for use such as macroecological modelling and other studies. We relied on a Darwin Core base model to standardise and further facilitate the curation and validation of data related including the occurrence and abundance of multiple taxa of a region that encompasses estuarine ecosystems in an ecotonal area bordering the easternmost Amazonia. We further discuss the significance of feeding standardised public data repositories to advance scientific progress and highlight their role in contributing to the biodiversity management and conservation.

25 April 2024 in European Journal of Applied Sciences
Verified
Journal Article
Open access
DFDouglas Ferreira
Douglas Ferreira
Ana Paula Paes Dos SantosAna Paula Paes Dos Santos
Ana Paula Paes Dos Santos
Claudia Priscila Wanzeler da CostaClaudia Priscila Wanzeler da Costa
Claudia Priscila Wanzeler da Costa
RENATA GONÇALVES TEDESCHIRENATA GONÇALVES TEDESCHI
RENATA GONÇALVES TEDESCHI
RJRENATO OLIVEIRA DA SILVA JUNIOR
RENATO OLIVEIRA DA SILVA JUNIOR
1A1350 Turismo Av. Protection System Of The Amazon
1350 Turismo Av. Protection System Of The Amazon
Mining is an important branch of the economy in Brazil. Particularly in the eastern Amazon, a large part of the mineral chain spans regions with heterogeneous landscapes characterized by ridges colonized by native rainforests and canga vegetation, where mining activities have developed, rolling hills with extensive pastures and croplands, and restricted urban areas. Regarding operational activities, the mining industry takes place in open-pit, railway and port settings, all of which are naturally exposed to the impacts of adverse weather conditions. This article addressed the importance of meteorological studies in minimizing and managing the rebounding of atmospheric processes in the mining chain from the mines to the ports. The main methods used in the analyzed studies included regional numerical models and statistical modeling adapted for the target area. The results presented herein refer to the development of climate projections focusing on precipitation extremes, seasonal precipitation forecasts, a short-term meteorological forecasting system, a lightning alert system for mining areas and the creation of a hydrometeorological monitoring network. Such results were presented to stakeholders, who can use information derived from scientific research, especially when planning their respective activities on different time scales, including annual, monthly, daily and hourly timescales, from the perspective of process optimization, human safety, community well-being, biodiversity conservation and water resource management.

23 April 2024 in ARPHA Preprints
Verified
Preprint
Open access
PDF file
NMNubia Marques
Nubia Marques
CSCarla Soares
Carla Soares
DCDaniel Casali
Daniel Casali
EGErick Guimarães
Erick Guimarães
FFFernanda Fava
Fernanda Fava
VTValeria Tavares
Valeria Tavares
Biodiversity data, particularly species occurrence and abundance, are indispensable for testing empirical hypothesis in natural sciences. However, datasets built for research programs do not often meet FAIR (findable, accessible, interoperable, and reusable) principles, which raises questions about data quality, accuracy, and availability. The 21st century has markedly been a new era for data science and analytics, and every effort to aggregate, standardize, filter, and share biodiversity data from multiple sources have become increasingly necessary. In this study, we propose a framework for refining and conform secondary biodiversity data to FAIR standards to make them available for valuable use such as macroecological modeling and other studies. We relied on a Darwin Core base model to standardize and further facilitate the curation and validation of data related including the occurrence and abundance of multiple taxa of a region that encompasses estuarine ecosystems in an ecotonal area bordering the easternmost Amazonia. We further discuss the significance of feeding standardized public data repositories to advance scientific progress and highlight their role in contributing to the biodiversity management and conservation.

29 November 2024 in Sensors
Verified
Journal Article
Open access
PDF file
ECEduardo Costa de Carvalho
Eduardo Costa de Carvalho
BFBruno Ferreira
Bruno Ferreira
AGAna Claudia Gomes
Ana Claudia Gomes
CGCamilo Gonçalves
Camilo Gonçalves
GDGIOVANNI AUGUSTO FERREIRA DIAS
GIOVANNI AUGUSTO FERREIRA DIAS
GPGustavo Pessin
Gustavo Pessin
In every business, equipment requires repair services. Over time, equipment wears out; however, with well-conducted and guided maintenance, this degradation can be controlled, and failed equipment can be restored to operational status. Preventive maintenance allows this concept to be applied, given the great advantages for large companies in reusing equipment and machinery, always putting the worker’s health and safety first. Rail transport has several pieces of equipment that can be reused if they are in a regular and well-defined maintenance cycle. In this sense, this article sought to create a method using real data for identifying cracks in wagons. Through the use of computer vision algorithms to prepare the data, along with several machine learning classification algorithms to locate cracks in train cars, the classification used properly annotated images and obtained great results, with a best case 98.10% hit-rate when wagons had a crack problem.

25 September 2023
Verified
Conference Paper
Open access
PDF file
RRRafael de Lima Rocha
Rafael de Lima Rocha
EOEwerton Oliveira
Ewerton Oliveira
ECEduardo Costa de Carvalho
Eduardo Costa de Carvalho
RENATA GONÇALVES TEDESCHIRENATA GONÇALVES TEDESCHI
RENATA GONÇALVES TEDESCHI
Claudia Priscila Wanzeler da CostaClaudia Priscila Wanzeler da Costa
Claudia Priscila Wanzeler da Costa
RARonnie Alves
Ronnie Alves
Severe weather events pose a global threat, causing property damage and endangering lives. Weather-related disasters account for 50% of all natural and technological disasters. The development of accurate prediction systems are crucial for early warnings and mitigation. The present study evaluates the effectiveness of the U-Net model in weather radar-based precipitation nowcasting, considering reflectivity thresholds. Visual comparison and evaluation metrics are used to assess observed and predicted reflectivity. The 10 dBZ threshold achieved a prominent result, accurately predicting over 75% of values above the reflectivity threshold. Results contribute to improving severe weather prediction and decision-making.

29 September 2025
Verified
Conference Paper
Closed access
Helder Moreira ArrudaHelder Moreira Arruda
Helder Moreira Arruda
ADAnita Drumond
Anita Drumond
EOEwerton Oliveira
Ewerton Oliveira
JFJulio Freitas
Julio Freitas
RRRafael de Lima Rocha
Rafael de Lima Rocha
ECEduardo Costa de Carvalho
Eduardo Costa de Carvalho
Este estudo avalia a previsão de precipitação em 12 pontos de monitoramento no sudeste do Brasil, utilizando cinco modelos estatísticos (MLR, ARIMA, SARIMA, SARIMAX e VARMAX). A acurácia das previsões foi avaliada em dois momentos (M1 e M2), utilizando o RMSE. O modelo MLR apresentou o melhor desempenho no curto prazo (M1) em metade das localidades (50%), enquanto o SARIMAX foi superior em quatro delas (33%). No longo prazo (M2), o VARMAX superou os demais modelos em sete localidades (58%), evidenciando sua capacidade de capturar dinâmicas multivariadas. Os resultados destacam a importância dos modelos estatísticos para a previsão meteorológica local e o planejamento de infraestrutura.