Andréa Leda Ramos de Oliveira

Purpose: This study aims to improve the accuracy of agricultural freight cost forecasting by developing and evaluating machine learning models tailored for road transport in grain supply chains. This study addresses the need for robust predictive tools to support cost-efficient logistics decisions in regions that are heavily reliant on road transportation. Design/methodology/approach: Two machine learning techniques were tested: multilayer perceptron (MLP), a type of artificial neural network, and support vector regression (SVR), a supervised learning model for continuous predictions. Both models were trained on a comprehensive dataset of soybean and corn freight records collected in Brazil from 2012 to 2022. To improve the predictive accuracy, the dataset was segmented into short-distance (≤600 km) and long-distance (>600 km) routes. The methodology also included a rigorous data preprocessing phase to address missing values, inconsistencies, and dataset integration issues. Findings: Both models yielded satisfactory forecasting outcomes, with the SVR model demonstrating slight superiority over the MLP model across both distance categories. The use of two specialized models, one for each distance range, resulted in higher accuracy than that of a single general model. The findings also reveal that freight prices behave differently depending on the transport distance, reflecting distinct logistics cost dynamics. These results confirm the potential of machine learning models to support price-behavior forecasting and logistics planning. Research limitations/implications: This study is limited by its focus on MLP and SVR performance, without explicitly considering contextual factors such as geopolitical events, regulatory changes, weather conditions, or demand-side market fluctuations. It also does not assess the relative importance of each predictor. Social implications: Reliable forecasting of road freight prices in grain supply chains can reduce uncertainty for agribusiness actors and support more equitable negotiations among producers, traders, and carriers. By improving cost predictability, machine learning-based models enhance logistics planning and resource allocation, especially in regions facing infrastructure limitations. This contributes to more efficient supply chains, with potential downstream effects on food prices and rural development. Additionally, the findings inform public policy by highlighting the need for targeted infrastructure investments and support for digital innovation in logistics, fostering greater integration between technological advancement and agricultural distribution systems in large, road-dependent economies. Originality/value: This study advances the field of forecasting methodologies in agricultural logistics by illustrating the benefits of model specialization and meticulous data preparation. It offers one of the initial empirical applications of MLP and SVR techniques for forecasting road freight prices in Brazil's grain supply chains. The proposed framework delivers actionable insights for both public and private stakeholders, thereby enhancing the predictability of transportation costs and improving decision-making processes in the supply chain.

The expansion of Brazil’s agricultural frontier in Arco Norte has intensified environmental and socioeconomic concerns that may worsen under climate change. This study evaluates how climate-driven shifts in soybean suitability may reconfigure production patterns and affect logistical vulnerabilities. Three scenarios were modeled using the MaxEnt algorithm: a historical baseline (1970–2000) and two future projections (2041–2060) based on the CMIP6 climate pathways. The model integrated bioclimatic, physical, land-use and land-cover, and infrastructure variables. The results showed that soybean expansion was highly concentrated across all scenarios. Mato Grosso, Goiás, and Tocantins accounted for 82.7% to 85.5% of total projected expansion, while Bahia and Maranhão increased this share to more than 92% of total gains. Although consolidated areas absorbed most of the expansion, new frontiers still represented nearly 30% of the total gains. A logistical vulnerability index linked potential expansion areas to grain storage deficits and revealed critical conditions in the main soybean-producing municipalities of Mato Grosso. These findings indicate a growing mismatch between emerging production areas and existing logistics infrastructure, highlighting the need for coordinated investments in storage, intermodal transportation, and territorial planning.

The responsible consumption of food has provided experiences between producers and consumers who seek to reflect on the act of purchasing as a condition for transformation and minimization of social and environmental impacts in society. In view of this, the aim of the paper is to characterize the profile of Responsible Consumption Groups (GCR) for food, identify the real motivations of the actors and highlight the internal and external stimuli and obstacles that have affected these marketing channels. For this, bibliographical research and field research (online) were used through questionnaires with 34 GCR in eight states in Brazil, which represent 70% of the total groups identified at the time of the research. As a result, common patterns were identified between the groups, most of the time, they are classified as a singular network, with agroecological production practices and a more centralized location, due to the institutional support received. In addition, the main strengths (direct contact between consumers and producers, obtaining organic/agroecological foods that contribute to sustainability); opportunities (social experiences, such as exchanging knowledge and participating in collectives), as well as weaknesses (logistics, food waste, management and communication difficulties between group actors); and threats (a low external support).

Predicting road freight prices is a challenging task influenced by multiple factors. Understanding which variables have the greatest impact is essential for building more accurate models, and consequently for enhancing the competitiveness of Brazilian soybeans in the global market. This study aims to evaluate the influence of different exogenous variables on soybean freight prices and to analyze how this influence varies across different distance ranges. To achieve this, a combination of machine learning techniques was applied to a comprehensive dataset containing information on freight costs, regional characteristics, production, fuel prices, storage, and commercialization. The results indicate that distance is the most significant variable in determining freight costs, directly reflecting operational expenses such as fuel consumption and labor costs. Additionally, macroeconomic factors such as the exchange rate and export volume play a crucial role, highlighting the global context of Brazil’s soybean exports. Stratified analysis by distance ranges reveals distinct patterns; short-distance freight is predominantly related to domestic markets, while medium- and long-distance freight are strongly linked to export logistics.

Freight price prediction is a complex problem with multiple determinants. Identifying the most important variables can be used to develop more accurate prediction models and increase the competitiveness of Brazilian soybeans. This study aims to assess the influence of various exogenous variables on the price of soybean road freight and how this influence varies across different distance ranges. A combination of machine learning techniques was employed to evaluate a dataset containing variables related to freight, region, production, fuel, storage, and commercialization. The results indicate that distance is the most significant variable in determining freight costs, aligning with operational expenses such as fuel and labor. Additionally, the exchange rate and export volume emerge as key factors, reflecting the macroeconomic context of Brazilian soybean exports. The stratified analysis highlights the differentiation between short, medium, and long-distance freights, showing that different variables influence the price. Short-distance transportation is mainly geared toward the domestic market, while longer distances are more related to export logistics.

Nas últimas safras a região Centro-oeste se consolidou como o maior produtor e exportador de soja. Apesar da importância significativa desta atividade para a economia nacional, ainda há pouco investimento público em infraestrutura para o escoamento de grãos. Neste sentido, programas como Programa de Parceria de Investimento (PPI) podem ser ferramentas para a promoção da melhoria na cadeia de suprimentos agrícolas para exportação. Isto posto, o objetivo desta pesquisa foi o desenvolvimento de um sistema de avaliação de desempenho para classificar os projetos de infraestrutura logística de exportação da soja no âmbito do PPI. Para tanto, foi utilizado o método de análise multicritério Análise Hierárquica de Processos (AHP), para avaliar os principais atributos de projetos logísticos e ranqueá-los considerando aspectos econômicos, operacionais e ambientais. Os resultados indicaram que a ferrovia Ferrogrão (EF-107) é mais prioritária, tendo em vista sua potencial promoção da intermodalidade na região Centro-Norte do país. Este projeto é o mais indicado para o deslocamento de commodities por longas distâncias, pois promovem menor custo logístico, economia de escala e menor impacto ambiental. Além disso, contribui para o estabelecimento de uma matriz de transporte mais equilibrada para a movimentação de cargas.

Entre 2006 e 2017, a área plantada com soja no Brasil cresceu 68%, contribuindo para o bom desempenho do PIB do Agronegócio, que aumentou 135% no mesmo período. Essa expansão, concentrada na região Centro-Norte, enfrenta desafios como a infraestrutura de transporte e obstáculos logísticos. Os portos do Arco Norte se apresentam como uma alternativa estratégica para o escoamento da produção, proporcionando menor congestionamento e maior proximidade com o mercado asiático. No entanto, a expansão do cultivo da soja levanta preocupações relacionadas ao desmatamento e à conservação ambiental, principalmente em áreas de floresta tropical. A pesquisa indica que, embora tenha impulsionado o PIB agropecuário e a renda das propriedades agrícolas, a riqueza gerada não é distribuída equitativamente, agravando a desigualdade social em municípios com grandes áreas de cultivo. A análise utilizou dados dos censos agropecuários e indicadores econômicos e sociais, aplicando técnicas de autocorrelação espacial para avaliar se há uma relação entre a expansão agrícola e o desenvolvimento socioeconômico. Apesar de a expansão da soja ter o potencial de promover o desenvolvimento econômico, ela também intensifica a desigualdade e gera impactos ambientais, reforçando a necessidade de políticas públicas que garantam um crescimento sustentável e justo.

The road system is the main mode used for the transportation of agricultural cargo, and in some cases, it is the only option for handling this type of product. This dependence means that the implementation of tools to support the management of logistical costs can reduce the financial impact with the transport felt by the economic agents operating in the soybean chain. This study contributed to a better understanding of the variables that make up the cost of road freight, generating a system of road freight prediction from a multiple linear regression model using the selection of variables Stepwise, Forward, and Backward elimination. This being said, this research intends to evaluate whether the behavior of soybean road freight is influenced by the variables that make up the productive, economic, and infrastructure dimensions in price formation. The regression models had an explanatory power of 87.20%. In the infrastructure dimension, the most impact variable in soybean road freight was the distance traveled; in the economic dimension, the variables of inflation and fuel price stood out; while in the productive dimension, the main contribution was the volume of production. A more assertive predictability of logistical costs and better understanding of the dynamics of freight price formation helps industry agents in planning and decision-making. Another contribution of this study is that it can be used as a practical tool for predicting soybean road freight on several transportation routes.