Recent Advances in Sustainable Agricultural Production: Insights into Artificial Intelligence Integration

Abstract

Sustainable agricultural production has emerged as a critical global priority in response to increasing food demand, climate variability, environmental degradation, and socio-economic instability within farming systems. Contemporary agricultural research increasingly emphasizes the integration of statistical modelling, artificial intelligence (AI), genetic improvement strategies, disease management frameworks, and economic assessment tools to enhance productivity while ensuring long-term ecological and economic sustainability. Recent advancements in time-series modelling, regression-based forecasting, bootstrap techniques, and meta-modelling approaches have strengthened crop yield prediction and production planning across diverse agro-climatic regions. Parallel developments in AI-driven precision agriculture, including machine learning (ML) algorithms and deep learning (DL) architectures, have improved predictive accuracy through the integration of environmental, morphological, and remote sensing datasets. Genetic variability assessment, marker-assisted screening, and stress tolerance studies have contributed to the development of resilient cultivars capable of sustaining productivity under biotic and abiotic stresses. Additionally, research on export forecasting, market infrastructure evaluation, geographically indicated (GI) products, and regional income convergence underscores the importance of economic viability within sustainable production systems. Rather than relying on isolated technological interventions, emerging evidence supports an integrated framework that combines predictive analytics, precision management, breeding innovations, and market-informed planning. This review synthesizes recent advances across these domains and highlights the necessity of interdisciplinary approaches for achieving resilient, resource-efficient, and economically viable agricultural systems.