Background: Transportation demand forecasting is an essential activity for logistics operators and carriers. It leverages business operation decisions, infrastructure, management, and resource planning activities. Since 2015, there has been an increase in the use of deep learning models in this domain. However, there is a gap in works comparing traditional statistics and deep learning models for transportation demand forecasts. This work aimed to perform a case study of aggregated transportation demand forecasts in 54 distribution centers of a Brazilian carrier. Methods: A computational simulation and case study methods were applied, exploring the characteristics of the datasets through autoregressive integrated moving average (ARIMA) and its variations, in addition to a deep neural network, long short-term memory, known as LSTM. Eight scenarios were explored while considering different data preprocessing methods and evaluating how outliers, training and testing dataset splits during cross-validation, and the relevant hyperparameters of each model can affect the demand forecast. Results: The long short-term memory networks were observed to outperform the statistical methods in ninety-four percent of the dispatching units over the evaluated scenarios, while the autoregressive integrated moving average modeled the remaining five percent. Conclusions: This work found that forecasting transportation demands can address practical issues in supply chains, specially resource planning management.

RESUMO O combate à má alimentação em todas as suas formas, que também se expressa na epidemia da obesidade, é uma das prioridades da Agenda 2030 e dos Objetivos de Desenvolvimento Sustentável. Este artigo traz elementos sobre insegurança alimentar no Brasil, a partir de temas relativos ao crescimento populacional, mudanças climáticas, biodiversidade e sistemas alimentares tradicionais e regenerativos; trata também do papel dos movimentos sociais para a garantia do Direito Humano à Alimentação Adequada. O Grupo de Pesquisa em Nutrição e Pobreza, o Saúde Planetária Brasil, e o Centro de Inteligência Artificial (C4AI) - Eixo AgriBio, entendem que a retomada organizada e sistêmica das frentes apontadas neste artigo de posicionamento, pode constituir um caminho para a articulação entre pesquisa, serviço e políticas públicas na direção do combate à fome e às demais manifestações da má alimentação, enquanto problema complexo prioritário para a garantia do bem-estar social.

Citrus are the most produced fruits worldwide. It is expected that these crops will be severely affected by climate change. However, the literature lacks works that attempt to understand the influence of climate change on citrus. For this reason, a bibliometric analysis was conducted on climate change and citrus to investigate its development and current trends in this research domain. The main trends, keywords, and their relations were identified. The period from 1992 to 2022 was analyzed, resulting in 178 documents in the Scopus database. The most significant publishers’ countries were also the largest citrus producers in the world besides being G7 members. Three main research areas were identified: modeling, socio-political issues, and plant physiology. A tendency to change interest from modeling and risk analysis to physiology and stress studies was observed. Additionally, some of the most cited papers observed the positive impacts of climate change on certain citrus crops. Despite the multidisciplinary publications, two main gaps were identified: (i) the lack of investigations with combined stresses (abiotic and biotic) instead of isolated studies, and (ii) the lack of studies of predictive models for citrus production in different conditions and climate change scenarios. Finally, there was a tendency toward studying water use and irrigation alternatives due to water scarcity and management solutions to improve the production system’s resilience, considering the potential impacts of climate change.

Agrometeorological models are great tools for predicting yields and improving decision-making. High-quality climatic data are essential for using these models. However, most developing countries have low-quality data with low frequency and spatial coverage. In this case, two main options are available: gathering more data in situ, which is expensive, or using gridded data, obtained from several sources. The main objective here was to evaluate the quality of two gridded climatic databases for filling gaps of real weather stations in the context of developing agrometeorological models. Therefore, a comparative analysis of gridded database and INMET data (precipitation and air temperature) was conducted using an agrometeorological model for sweet orange yield estimation. Both gridded databases had high determination and concordance coefficients for maximum and minimum temperatures. However, higher errors and lower confidence coefficients were observed for precipitation data due to their high dispersion. BR-DWGD indicated more accurate results and correlations in all scenarios evaluated in relation to NasaPower, pointing out that BR-DWGD may be better at filling gaps and providing inputs to simulate attainable yield in the Brazilian citrus belt. Nevertheless, due to the BR-DWGD database’s geographical and temporal limitations, NasaPower is still an alternative in some cases. Additionally, when using NasaPower, it is recommended to use a measured precipitation source to improve prediction quality.

This paper explores the use of several state-of-the-art machine learning models for predicting the daily prices of corn and sugar in Brazil in relation to the use of traditional econometrics models. The following models were implemented and compared: ARIMA, SARIMA, support vector regression (SVR), AdaBoost, and long short-term memory networks (LSTM). It was observed that, even though the prices time series for both products differ considerably, the models that presented the best results were obtained by: SVR, an ensemble of the SVR and LSTM models, an ensemble of the AdaBoost and SVR models, and an ensemble of the AdaBoost and LSTM models. The econometrics models presented the worst results for both products for all metrics considered. All models presented better results for predicting corn prices in relation to the sugar prices, which can be related mainly to its lower variation during the training and test sets. The methodology used can be implemented for other products.

Mastitis, an important disease in dairy cows, causes significant losses in herd profitability. Accurate diagnosis is crucial for adequate control. Studies using artificial intelligence (AI) models to classify, identify, predict, and diagnose mastitis show promise in improving mastitis control. This bibliometric review aimed to evaluate AI and bovine mastitis terms in the most relevant Scopus-indexed papers from 2011 to 2021. Sixty-two documents were analyzed, revealing key terms, prominent researchers, relevant publications, main themes, and keyword clusters. “Mastitis” and “machine learning” were the most cited terms, with an increasing trend from 2018 to 2021. Other terms, such as “sensors” and “mastitis detection”, also emerged. The United States was the most cited country and presented the largest collaboration network. Publications on mastitis and AI models notably increased from 2016 to 2021, indicating growing interest. However, few studies utilized AI for bovine mastitis detection, primarily employing artificial neural network models. This suggests a clear potential for further research in this area.