Orchard Flowering Map for Targeted Chemical Thinning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for managing fruit tree orchards lack an efficient way to estimate and map the flowering rates of individual trees, leading to homogeneous chemical thinning treatments and costly manual thinning processes, which can result in suboptimal fruit production and resource wastage.

Innovation Solution

A decision support method and system that processes digital images of fruit trees to detect and count flowering objects, determine bloom levels, and generate a map of flowering levels, allowing for targeted thinning chemical application based on each tree's flowering level.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If homogeneous chemical thinning treatment is applied to the entire orchard, then the treatment process is simple and fast, but it results in suboptimal fruit production and cannot account for heterogeneous flowering rates among trees

Engineering Contradiction:
Improvefruit productionVSAvoidtreatment process complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The orchard is divided into individual tree units, each assessed separately for flowering rate. The continuous canopy is segmented into discrete tree zones, allowing differential treatment application based on each tree's specific flowering level rather than treating the entire orchard uniformly.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The thinning treatment is customized for each tree based on its local flowering characteristics. Trees with high flowering rates receive different treatment intensities compared to trees with low flowering rates, optimizing fruit production for each local condition rather than applying a uniform approach.

Inventive Principle:
Principle #3Local quality

2Productivity

If manual thinning is performed tree by tree to optimize production, then fruit production is optimized, but the process becomes very expensive and time-consuming

Engineering Contradiction:
Improvefruit production optimizationVSAvoidthinning process time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

Manual visual assessment and manual thinning operations are replaced with an automated optical system using cameras and image processing algorithms. The system automatically detects, counts, and assesses flowering on each tree, then guides chemical thinning application, eliminating the need for time-consuming manual inspection and thinning operations.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service thinning by providing automated flowering assessment and treatment guidance that allows operators to efficiently apply thinning chemicals without requiring expert manual evaluation of each tree's flowering status, significantly reducing the time and skill required for the process.

Inventive Principle:
Principle #25Self-service

3Reliability

If chemical inputs are increased to encourage flowering in trees with insufficient blooms, then flowering is improved, but resource wastage increases and environmental impact worsens

Engineering Contradiction:
Improveflowering reliabilityVSAvoidchemical input wastage
Core Design Contradiction:
ReliabilityVSLoss of substance

Solution Approach 1:

Chemical inputs are applied selectively to specific trees or zones based on their assessed flowering needs rather than blanket application across the entire orchard. The system identifies which trees require flowering encouragement and directs chemical inputs only to those locations, optimizing reliability while minimizing waste.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system provides real-time feedback on flowering status for each tree, enabling dynamic adjustment of chemical input application. By monitoring actual flowering levels and comparing them to target levels, the system determines the precise amount and location of chemical inputs needed, preventing over-application and resource wastage.

Inventive Principle:
Principle #23Feedback

4Reliability

If arborists underestimate flowering rates to ensure enough fruit per tree, then fruit quantity per tree is protected, but overall production yield is reduced

Engineering Contradiction:
Improvefruit quantity per treeVSAvoidoverall production yield
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The subjective judgment process is replaced with objective automated image analysis that accurately counts and assesses flowering on each tree. This eliminates the systematic underestimation bias that occurs when arborists manually assess flowering, providing reliable data for optimizing both per-tree and overall production outcomes.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system provides accurate feedback on actual flowering levels for each tree, enabling precise thinning decisions that optimize both fruit quantity per tree and overall production. By eliminating estimation errors, the feedback loop allows for scientifically optimal treatment decisions that maximize total yield while maintaining quality standards.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3828826B1Method and system to assist with decision-making for managing an agricultural plot
Publication Date: 2025.01.01 AGRICONNECT
  • EP3828826B1 patent drawingFigure 1~2
  • EP3828826B1 patent drawingFigure 3
  • EP3828826B1 patent drawingFigure 4

AI summary

The present invention relates to a decision support method for managing a fruit orchard, the method comprising: - receiving (10) a plurality of digital images acquired in color along the rows of the orchard, each image representing a respective fruit tree in the orchard, - processing (20-70) the plurality of acquired images, said processing phase comprising, for each current image of the plurality of images, the following steps: ∘ detection of objects of interest in each current image, ∘ counting the number of objects of interest detected in each current image, ∘ determining a flowering level for each current image as a function of the number of objects of interest counted for said current image, - post-processing the plurality of processed images, said post-processing phase comprising the following steps: ∘ merging the flowering levels of the fruit trees by zones along the rows of the orchard,• Generation of a map showing the flowering levels of the fruit trees in the orchard.