In this study, we explored the application of Deep Learning techniques for the classification of coconut plantations from images collected by a Remotely Piloted Aircraft (RPA). A Convolutional Neural Network was used to create a model that classifies images into two categories: coconut and non-coconut. The model achieved an accuracy of 88%, concluding that Deep Learning techniques are viable tools for the identification of plants in large areas, with the potential to improve the management of agricultural crops.
Luiz Henrique Dias Ramos, Maria Eliana da Silva Holanda, João Pedro dos Santos Verçosa, Gustavo Antonio Ruffeil Alves, Arthur Costa Falcão Tavares, Fabricio Almeida Araujo, Gilberto Nerino de Souza Junior, Marcus de Barros Braga
REVISTA OBSERVATORIO DE LA ECONOMIA LATINOAMERICANA Curitiba, v.21, n.12, p. 25917-25937. 2023.
Modeling time series has been a particularly challenging aspect due to the need for constant
adjustments in a rapidly changing environment, data uncertainty, dependencies between
variables, volatile fluctuations, and the need to identify ideal hyperparameters. The present
study presents a Framework capable of making projections from time series related to
cases and deaths by COVID-19 in the Amazonian state of Para´, in Brazil. For the first time,
deep learning models such as TCN, TRANSFORMER, TFT, N-BEATS, and N-HiTS were
assessed for this purpose. The ARIMA statistical model was also used in post-processing
for residual adjustment and short-term smoothing of the generated forecasts. The Framework generates probabilistic forecasts, with multivariate support, considering the following
variables: daily cases per day of the first symptom, cases published daily, the occurrence of
deaths, deaths published daily, and percentage of daily vaccination. The generated predictions are statistically evaluated by determining the best model for 7-day moving average
projections using evaluating metrics such as MSE, RMSE, MAPE, sMAPE, r
2
, Coefficient of
Variation, and residual analysis. As a result, the generated projections showed an average
error of 5.4% for Cases Publication, 8.0% for Cases Symptoms, 11.12% for Deaths Publication, and 4.6% for Deaths Occurrence, with the N-HiTS and N-BEATS models obtaining better results. In general terms, the use of deep learning models to predict cases and deaths
from COVID-19 has proven to be a valuable practice for analyzing the spread of the virus,
which allows health managers to better understand and respond to this kind of pandemic
outbreak.
Gilberto Nerino de Souza Junior, Alícia Graziella Balbino Mendes, Joaquim dos Santos Costa, Mikeias dos Santos Oliveira, Paulo Victor Cunha Lima, Vitor Nunes de Moraes, David Costa Correia Silva, Jonas Elias Castro da Rocha, Marcel do Nascimento Botelho, Fabricio Almeida Araujo, Rafael da Silva Fernandes, Daniel Leal Souza, Marcus de Barros Braga
Livestock in the territory of Pará offers planning challenges for both the
state and the private sector, with consequences of herd expansion impacting
economic and socio-environmental variables. This article presents a study on
livestock projections in terms of production and pasture coverage area using ARIMA
(AutoRegressive Integrated Moving Average) modeling through the hierarchical
approach. A short-term time series data analysis framework was developed, covering
data referring to the state of Pará between the years 1985 to 2021, with projections
until 2026. The results indicate an increase of 19% in the number of cattle and 1.5%
in pasture areas in the state of Pará, revealing an increase in productivity in the
Marabá region, as well as stabilization in the Redenção region.
Mikeias S. Oliveira, Rafael S. Fernandes, Marcio R. S. Melo, Daniel L. Souza, David C. C. Silva, Gilberto Nerino de Souza Junior, Marcus de Barros Braga
2023: ANAIS DO XIV WORKSHOP DE COMPUTAÇÃO APLICADA À GESTÃO DO MEIO AMBIENTE E RECURSOS NATURAIS
Weed infestation is an essential factor in sugarcane productivity loss. The use of remote sensing data in
conjunction with Artificial Intelligence (AI) techniques, can lead the cultivation of sugarcane to a new level in
terms of weed control. For this purpose, an algorithm based on Convolutional Neural Networks (CNN) was
developed to detect, quantify, and map weeds in sugarcane areas located in the state of Alagoas, Brazil.
Images of the PlanetScope satellite were subdivided, separated, trained in different scenarios, classified and
georeferenced, producing a map with weed information included. Scenario one of the CNN training and test
presented overall accuracy (0,983), and it was used to produce the final mapping of forest areas, sugarcane,
and weed infestation. The quantitative analysis of the area (ha) infested by weed indicated a high probability
of a negative impact on sugarcane productivity. It is recommended that the adequacy of CNN’s algorithm for
Remotely Piloted Aircraft (RPA) images be carried out, aiming at the differentiation between weed species,
as well as its application in the detection in areas with different culture crops.
João Pedro do Santos Verçosa, Flávio Henrique dos Santos Silva, Fabricio Almeida Araujo, Regla Toujaguez la Rosa Massahud, Francisco Rafael da Silva Pereira, Henrique Ravi Rocha de Carvalho Almeida, Marcus de Barros Braga, Arthur Costa Falcão Tavares
International Journal for Innovation Education and Research. Vol. 10. N. 11 (2022). pg. 210.
