Fernanda Ferreira Verdelho

Ms. Fernanda Ferreira Verdelho

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
30 May 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FVFernanda Ferreira Verdelho
Fernanda Ferreira Verdelho
CBCesar Beneti
Cesar Beneti
LPLuis G. Pavam
Luis G. Pavam
LCLeonardo Calvetti
Leonardo Calvetti
LOLuiz Eduardo Oliveira
Luiz Eduardo Oliveira
MAMarco Antonio Zanata Alves
Marco Antonio Zanata Alves
In addressing the challenges of quantitative precipitation estimation (QPE) using weather radar, the importance of enhancing the rainfall estimates for applications such as flash flood forecasting and hydropower generation management is recognized. This study employed dual-polarization weather radar data to refine the traditional Z–R relationship, which often needs higher accuracy in areas with complex meteorological phenomena. Utilizing tree-based machine learning algorithms, such as random forest and gradient boosting, this research analyzed polarimetric variables to capture the intricate patterns within the Z–R relationship. The results highlight machine learning’s potential to improve the precision of precipitation estimation, especially under challenging weather conditions. Integrating meteorological insights with advanced machine learning techniques is a remarkable achievement toward a more precise and adaptable precipitation estimation method.

1 December 2018
Verified
Book Chapter
Closed access
UFUniversidade Estadual Paulista “Júlio de Mesquita Filho”
Universidade Estadual Paulista “Júlio de Mesquita Filho”
FVFernanda Ferreira Verdelho
Fernanda Ferreira Verdelho
VBVictor Barbério
Victor Barbério
GPGeórgia Jorge Pellegrina
Geórgia Jorge Pellegrina

20 January 2025
Verified
Conference Paper
Open access
CBCesar Beneti
Cesar Beneti
LPLuis Pavam
Luis Pavam
LOLuiz Oliveira
Luiz Oliveira
MAMarco Alves
Marco Alves
LCLeonardo Calvetti
Leonardo Calvetti
FVFernanda Ferreira Verdelho
Fernanda Ferreira Verdelho
Uninterrupted access to electricity is a fundamental feature of civilization. In its absence, an all-embracing cessation of activities occurs, ranging from essential services to more frivolous activities. The maintenance of the energy supply is critical for society's day-to-day functions. The Brazilian state of Paraná (PR) is home to the world's second-largest hydropower plant, Itaipu, which, in conjunction with other power plants in the state, provides almost one-third of the power energy production in Brazil. The transmission lines that pervade PR are essential to Brazil's power distribution system, for hydropower generation is typically made far away from the regions that most demand it, being transported by transmission lines in an interconnected power grid. This type of asset mainly depends on the forecast of Cloud-to-Ground (CG) lightning, as it is one of the leading weather-related causes of power outages. Lightning and wind gusts are the two leading weather-related causes of disruptions, representing at least 23% of the known causes of energy disruption, as declared by the local power distribution company. Our study of lightning incidence and power outages from 2017-2021 indicates a correlation of 0.98 between these events, denoting that more outages must be lightning-related. Reliable CG lightning forecasts are crucial for proactive hazard mitigation. This work expounds on developing a Machine Learning (ML) model for CG lightning forecasting for PR. Our ML model predicts the occurrence or lack of CG lightning near power company assets in PR, defining a binary classification task. The model makes its predictions based on the past spatio-temporal conditions of lightning occurrences, requiring only past lightning data to forecast lightning. We chose to use a stream ML method, i.e., the model is continuously trained as new data arrives. Using a stream ML, we intend to harness the machine's capacity to continuously learn the patterns of lightning occurrence and power outages in real-time -- thus constructing an ever-updating model capable of adapting to transient weather conditions. Given its rapid training time and aptitude for classification tasks, the chosen algorithm was a Very Fast Decision Tree. The stream ML classifier outperforms a classic static ML model by 30% regarding the ROC AUC metric (stream: 71.80%, static: 40.85%) and 50% considering the Micro-f1 score (stream: 91.05%, static: 40.91%). These results arise from the highly dynamic nature of lightning, defining an ideal phenomenon for prediction based on a constantly updated stream of data. An automatic system for CG lightning forecasting for power company assets is helpful for risk management and operational planning. Future steps include increasing the lead time from ten min. to up to one hour, allowing for more time to prepare and anticipate hazards, preventing power outages, and optimizing personnel allocation.

15 May 2023
Verified
Conference Paper
Open access
CBCesar Beneti
Cesar Beneti
LCLeonardo Calvetti
Leonardo Calvetti
FVFernanda Ferreira Verdelho
Fernanda Ferreira Verdelho
RJRodrigo Rocha Júnior
Rodrigo Rocha Júnior
JJJeova Silva Junior
Jeova Silva Junior
VCVinicius Cebalhos
Vinicius Cebalhos
Quantitative estimation of precipitation (QPE) of high resolution, accurate and in real-time, increases the potential of weather radars for many applications, such as flash flood forecasting and hydropower production and distribution management. Using polarimetric variables from dual-polarization weather radars has already shown significant improvements in quantitative precipitation estimation in many countries with diverse weather. In Brazil, in the past ten years, we have seen an increase in dual-polarization weather radar coverage, mostly S-Band and some X-Band, concentrated in the southern parts of the country, an area prone to severe weather with high precipitation and lightning due to mesoscale convective systems. This region's significant economic activity is agriculture and energy production, accounting for more than 33% of the hydro energy generation used in the country. Therefore, the improvement of precipitation estimation is a necessary goal. However, the use of weather radar's QPE depends on calibration, good fit with rain gauges and distrometers, good data filtering, target’s distance from the radar, orography (i.e., relative to the topography), and signal propagation, as well as other factors. A multi-sensor integration approach of remotely sensed precipitation estimation using weather satellites and weather radar with rain gauges improves the accuracy of hydrological models compared to a model using only rain gauge data. A quantitative precipitation estimation algorithm called SIPREC (System for Integrated PRECipitation) has been used operationally for more than 15 years, combining data from different sources, such as weather radar, rain gauge, and satellite. Precipitation estimates are obtained through an automated precipitation classification scheme based on reflectivity structures. This approach aggregates data from rain gauges by interpolation while maintaining the spatial distribution of the radar or satellite measurement. Statistical results indicate that the method can reduce radar and satellite data errors. This method is an essential advantage in an operational environment since it does not require frequent processing to update the weights as in other known schemes. However, this approach does not solve problems such as uncertainties related to Z-R estimation, spatial variability, and the one-hour temporal resolution. To improve the SIPREC algorithm, we used machine learning classification and regression methods to address the problem of precipitation estimation using dual polarization variables and rain gauge. An enhanced satellite precipitation estimation using GOES-16 data also replaced the previous dataset, and a new quality control algorithm for the network of weather radars was also applied to the dataset. A performance evaluation study shows improvements in precipitation estimation, primarily when used in real-time in an operational environment. This paper presents the results of this evaluation, with applications in severe weather events with high precipitation in the area.