Optimizing Harvest Planning in Perishable Agricultural Production: A Data-Driven Approach Leveraging Weather Conditions and Clustering Analysis


Samasti M., KÜÇÜKDENİZ T.

Food and Energy Security, cilt.14, sa.3, 2025 (SCI-Expanded, Scopus) identifier identifier

  • Yayın Türü: Makale / Derleme
  • Cilt numarası: 14 Sayı: 3
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1002/fes3.70107
  • Dergi Adı: Food and Energy Security
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Agricultural & Environmental Science Database, Applied Science & Technology Source, CAB Abstracts, Food Science & Technology Abstracts, Greenfile, Veterinary Science Database, Directory of Open Access Journals
  • Anahtar Kelimeler: harvest planning, logistics cost minimization, perishable agricultural products, weather-dependent operational planning
  • İstanbul Üniversitesi-Cerrahpaşa Adresli: Evet

Özet

In the rapidly evolving and competitive sector of agricultural production, optimizing operational efficiencies is crucial for the sustainability of enterprises. This study introduces a novel approach to enhance the profitability and sustainability of perishable food production enterprises by optimizing harvest planning and logistics activities, which are significantly influenced by weather conditions. Using the weighted fuzzy c-means (WFCM) method, a two-stage solution approach was developed to improve the decision-making process in both short- and long-term operational planning. In the first stage, clustering analysis was conducted to determine optimal facility locations and assign fields to these facilities, thereby facilitating the efficient processing of perishable food products. Following this, an integer linear programming model was developed to optimize the harvest plan, considering the variable weather-related costs and maximizing the total operating profit. This innovative approach not only considers the economic value of the product, which fluctuates over time, but also integrates weather precipitation data to dynamically adjust the harvesting plan, thereby minimizing costs and maximizing revenues. The model was rigorously tested using real data from 16 sugar factories in Türkiye and their corresponding sugar beet fields. The results demonstrated a substantial potential increase in operating profit by 27.47% compared with the current scenario. Furthermore, the model promises to reduce economic losses associated with improper storage and stacking and to stabilize seasonal fluctuations in vehicle supply and freight prices by distributing vehicle demand over a longer period. This study adds a significant layer to the existing literature, offering a comprehensive solution that addresses the complex interplay of various factors in agricultural production and setting the stage for more resilient and sustainable operations in the perishable food sector.