Food Production Index Forecasting for Sustainable Food Systems in Türkiye: A Machine Learning-Based Approach

Creative Commons License

Balcı Torun F., Kayakuş M., Kabaş Ö., Moiceanu G., Gabriela M. M.

FOODS, cilt.15, sa.16, ss.1-25, 2026 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 15 Sayı: 16
  • Basım Tarihi: 2026
  • Doi Numarası: 10.3390/foods15162814
  • Dergi Adı: FOODS
  • Derginin Tarandığı İndeksler: Food Science & Technology Abstracts, Natural Science Collection (ProQuest), Scopus, Science Citation Index Expanded (SCI-EXPANDED), Directory of Open Access Journals
  • Sayfa Sayıları: ss.1-25
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Akdeniz Üniversitesi Adresli: Evet

Özet

Sustainable food systems are increasingly challenged by climate change, resource constraints, market volatility, and growing food demand, making accurate forecasting of food production essential for food security and long-term sustainability. Despite the growing use of machine learning in agricultural forecasting, studies directly modeling the Food Production Index (FPI) within a sustainable food systems framework remain limited, particularly in emerging economies. This study addresses this gap by forecasting Türkiye’s Food Production Index using agricultural, macroeconomic, and trade-related indicators covering the period 1962–2023. Seven predictive approaches, including Multiple Linear Regression (MLR), Bayesian Ridge Regression, Support Vector Regression (SVR), Random Forest, Gradient Boosting, Artificial Neural Networks (ANNs), and K-Nearest Neighbors (KNN), were comparatively evaluated using R2, RMSE, and MAE metrics. The results demonstrate that Bayesian Ridge Regression (R2 = 0.968) and MLR (R2 = 0.918) significantly outperform more complex machine learning algorithms, indicating that model–data compatibility is more critical than algorithmic complexity in long-term food production forecasting. The findings reveal that economic growth, agricultural inputs, and structural transformation processes play a decisive role in shaping food production dynamics. By integrating machine learning with sustainability-oriented food system analysis, this study provides a robust evidence base for supporting food security strategies, resource-efficient agricultural planning, and resilient food system governance. The proposed framework offers macro-level decision-support insights for policymakers engaged in long-term food system planning, strategic risk monitoring, and evidence-based policy evaluation.