According to the FAO, wheat, corn, and rice are staple crops that support global food security, providing 50% of the world’s dietary energy. The ability to predict accurately these key food crop agricultural commodity prices is important in stabilizing markets, supporting policymaking, and informing stakeholders’ decisions. To this aim, machine learning (ML), ensemble learning (EL), deep learning (DL), and time series methods (TS) have been increasingly used for forecasting due to the rapid development of computational power and data availability. This study presents a systematic literature review (SLR) of peer-reviewed original research articles focused on forecasting the prices of wheat, corn, and rice using machine learning (ML), deep learning (DL), ensemble learning (EL), and time series techniques. The results of the study help uncover suitable forecasting methods, such as hybrid deep learning models that consistently outperform traditional methods, and they identify important limitations in model interpretability and the use of region-specific datasets, highlighting the need for explainable and generalizable forecasting solutions. This systematic review adheres to the PRISMA 2020 reporting guidelines.

This study examines governance strategies that facilitate sustainable regional circular bioeconomy development, culminating in a typology which enables the classification of regional government good practices supporting circular bioeconomy deployment in diverse regions within Europe. Data on regional circular bioeconomy governance models were collected through desk research and a survey, resulting in a compilation of 61 circular bioeconomy governance models. From this compilation, 20 case studies were identified and further explored to develop a typology of regional circular bioeconomy governance strategies in the EU-27. Findings reveal a strong regional commitment to expanding bioeconomies; however, managing conflicting sustainability goals remains a challenge. This paper provides a comprehensive overview of successful governance models and practices, offering valuable insights for policymakers to support the co-development and replication of effective circular bioeconomy strategies across diverse European regions.

The rapid growth of agricultural data necessitates the development of storage systems that are scalable and efficient in storing, retrieving and analyzing very large datasets. The traditional relational database management systems (RDBMSs) struggle to keep up with large-scale analytical queries due to the volume and complexity inherent in those data. This study presents the design and implementation of a scalable data warehouse (DWH) system for agricultural big data. The proposed solution efficiently integrates data and optimizes data ingestion, transformation, and query performance, leveraging a distributed architecture based on HDFS, Apache Hive, and Apache Spark, deployed on dockerized Ubuntu Linux environments. This paper highlights the reasons why a DWH is irreplaceable for big data processing, without disputing the strengths of traditional databases in transactional use cases. By detailing the architectural choices and implementation strategy, this study provides a practical framework for deploying robust DWH solutions that are useful in supporting agricultural research, market predictions and policy decision-making.

This paper presents the results of a survey conducted electronically in the years 2020-2022 within the framework of the AGRICORE Horizon project. It concerned the Agri-Environment-Climate Measure M10 within the Rural Development Programme 2014-2020 and aimed to quantify the impact of its effects...

Accurate forecasting of carbon credit prices is increasingly vital for the effective functioning of forest carbon markets, which play a growing role in global climate mitigation strategies. Against this backdrop, the present study conducts a systematic literature review to evaluate the state of carbon price forecasting methodologies, with particular emphasis on their applicability to forest-based carbon credits. The review highlights the predominance of machine learning (ML) and hybrid modeling approaches, which demonstrate enhanced predictive capabilities relative to conventional econometric techniques, particularly in capturing nonlinear dynamics and integrating heterogeneous data sources. However, their predictive power is limited by data scarcity, market opacity, and regulatory volatility. These issues are particularly severe in voluntary forest credit markets. The review identifies a critical research gap. Few studies explicitly model the behavior of forest credit prices. The findings suggest that future research should prioritize the development of policy-sensitive, scenario-based models that incorporate ecological, economic, and regulatory dimensions. While the majority of studies concentrate on compliance carbon markets, the methodological insights and forecasting approaches reviewed are highly relevant for the evolving forest carbon sector, nature-based mitigation strategies, and climate solutions. It also offers guidance for creating more transparent and robust forecasting tools in the forest carbon sector.

Accurately forecasting agricultural commodity prices is a complex and persistent problem for producers, traders, and policymakers. In this study we examine how artificial intelligence can be combined with large-scale global news data to refine daily corn price forecasts. A Long Short-Term Memory (LSTM) neural network was trained on Chicago corn futures between 2021 and 2024 to capture price dynamics, while agriculture-related news features were derived from the Global Database of Events, Language, and Tone (GDELT). Rather than sentiment polarity, the analysis shows that attention-based indicators, such as article volume, rolling intensity measures, and persistence of elevated coverage, carry stronger predictive information. These features are incorporated through a Ridge regression residual correction applied to the LSTM predictions, forming a lightweight two-stage hybrid model. While absolute forecast accuracy remains comparable to the price-only baseline (RMSE ≈ 9 ¢/bu; MAE ≈ 5.8 ¢/bu; R² ≈ 0.99), the hybrid framework improves directional accuracy by approximately 2.4 percentage points, with gains concentrated during periods of moderate news intensity. Feature attribution results indicate that media attention intensity and persistence dominate sentiment-tone variables, which receive zero weight under regularization. Overall, the proposed framework offers a transparent, computationally efficient, and reproducible approach for integrating open global news data into short-term agricultural price forecasting.