EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

AI-driven time series analysis for predicting strawberry weekly yields integrating fruit monitoring and weather data for optimized harvest planning

Shiyu Liu, Yiannis Ampatzidis, Congliang Zhou, Won Suk Lee

Computers and Electronics in Agriculture · 2025-06 · 233 · 110212

DOI: 10.1016/j.compag.2025.110212 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers and Electronics in Agriculture, 2025-06. Verfasst von Shiyu Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: U.S. Department of Agriculture, National Institute of Food and Agriculture.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

• A wave-specific strawberry yield forecasting system was developed. • This AI-driven system forecasts strawberry yield for the upcoming week. • It combines weather data and machine vision fruit counts for yield prediction. • MLR and GBM excel in modeling yield for specific strawberry varieties. • This system can reduce labor and enhance resource planning for harvests. Strawberries, as an indeterminate crop, produce fruit multiple times per season, making fruit monitoring and wave-specific yield prediction essential for optimizing harvest planning. This study developed an AI-driven approach to predict next week’s yield using real-time plant image data collected by a machine vision system and environmental data. YOLOv8n was employed to count flowers, immature fruit, and mature fruit per plant, with manual counts used to evaluate the system’s accuracy. The YOLOv8n-based data, combined with weather features, were used to train several AI models for yield prediction. These models included traditional time series machine learning approaches, such as Multiple Linear Regression (MLR) with time lag features, Vector Autoregression (VAR), Gradient Boosting Machines (GBM), Random Forest, and deep learning time-series models, including Long Short-Term Memory (LSTM) and Temporal Convolutional Networks (TCN). Recursive Feature Elimination (RFE) was employed to identify the most relevant features. The performance of these models was evaluated across three strawberry varieties: Sensation, Brilliance, and Medallion. Results showed that MLR outperformed other models for Sensation and Brilliance, with R 2 values of 0.633 and 0.908, respectively. For Medallion, GBM achieved the best performance with an R 2 score of 0.848. LSTM, which outperformed TCN, achieved R 2 scores of 0.522 (Sensation), 0.839 (Brilliance), and 0.740 (Medallion). This AI-driven system automates yield forecasting, reducing labor costs and enabling more efficient harvest planning. The study highlights the potential of combining machine vision and predictive analytics for precise, scalable yield prediction, offering valuable insights for proactive farm management and supply chain optimization.

Förderung

  • U.S. Department of Agriculture
  • National Institute of Food and Agriculture

Zitieren

APA

Liu, S., Ampatzidis, Y., Zhou, C., & Lee, W. S. (2025). AI-driven time series analysis for predicting strawberry weekly yields integrating fruit monitoring and weather data for optimized harvest planning. Computers and Electronics in Agriculture, 233, 110212. https://doi.org/10.1016/j.compag.2025.110212

Vancouver

Liu S, Ampatzidis Y, Zhou C, Lee WS. AI-driven time series analysis for predicting strawberry weekly yields integrating fruit monitoring and weather data for optimized harvest planning. Computers and Electronics in Agriculture. 2025;233:110212. doi:10.1016/j.compag.2025.110212

BibTeX
@article{Liu2025,
  author = {Liu, Shiyu and Ampatzidis, Yiannis and Zhou, Congliang and Lee, Won Suk},
  title = {AI-driven time series analysis for predicting strawberry weekly yields integrating fruit monitoring and weather data for optimized harvest planning},
  journal = {Computers and Electronics in Agriculture},
  year = {2025},
  volume = {233},
  pages = {110212},
  doi = {10.1016/j.compag.2025.110212}
}
Kostenlos starten →