Cherry Yield Forecast: Harvest Prediction for Individual Sweet Cherry Trees

2025-03-26

AI Summary

Accurate early-yield prediction for individual sweet cherry trees remains challenging due to phenological complexity and fruit-scale variability. Method: We developed a digital twin framework to track three ‘Satin’ cherry trees across the full phenological cycle (dormancy to harvest), leveraging ground-truth yield data to systematically evaluate manual structural counting—specifically at initial flower cluster emergence and post-second fruit drop—on predictive performance. Linear regression models were trained and validated at empirically identified optimal timepoints balancing timeliness and robustness. Contribution/Results: Our approach achieves high-accuracy yield prediction (R² > 0.9) and, for the first time, identifies a fundamental failure mode of state-of-the-art image-based counting methods under conditions of small fruit size (<1 cm) and severe occlusion. Crucially, we establish a reliable phenological window for manual yield estimation—providing both a practical benchmark and essential guidance for developing next-generation automated fruit counting algorithms.

Technology Category

• Machine Learning: Ensemble Methods
• Intelligent Robots: State Estimation
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

This paper is part of a publication series from the For5G project that has the goal of creating digital twins of sweet cherry trees. At the beginning a brief overview of the revious work in this project is provided. Afterwards the focus shifts to a crucial problem in the fruit farming domain: the difficulty of making reliable yield predictions early in the season. Following three Satin sweet cherry trees along the year 2023 enabled the collection of accurate ground truth data about the development of cherries from dormancy until harvest. The methodology used to collect this data is presented, along with its valuation and visualization. The predictive power of counting objects at all relevant vegetative stages of the fruit development cycle in cherry trees with regards to yield predictions is investigated. It is found that all investigated fruit states are suitable for yield predictions based on linear regression. Conceptionally, there is a trade-off between earliness and external events with the potential to invalidate the prediction. Considering this, two optimal timepoints are suggested that are opening cluster stage before the start of the flowering and the early fruit stage right after the second fruit drop. However, both timepoints are challenging to solve with automated procedures based on image data. Counting developing cherries based on images is exceptionally difficult due to the small fruit size and their tendency to be occluded by leaves. It was not possible to obtain satisfying results relying on a state-of-the-art fruit-counting method. Counting the elements within a bursting bud is also challenging, even when using high resolution cameras. It is concluded that accurate yield prediction for sweet cherry trees is possible when objects are manually counted and that automated features extraction with similar accuracy remains an open problem yet to be solved.

Problem

• Predict sweet cherry tree yield early in season
• Assess fruit development stages for accurate forecasts
• Overcome automated counting challenges for small, occluded cherries

Innovation

• Digital twins for sweet cherry trees
• Linear regression for yield prediction
• Manual counting over automated methods