Precision Sowing Density Control via Zone Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current precision agriculture methods lack a comprehensive and reliable process for optimizing sowing density across agricultural plots, failing to adequately consider multiple environmental and soil factors, which limits their effectiveness in maximizing yield and resource efficiency.
Innovation Solution
A method that collects and processes georeferenced data on geophysical, topographic, yield, and biomass indicators to classify management zones and calculate a Dimensionless Productivity Index, using an ecophysiological model to determine optimal sowing densities for each zone, ensuring precise and adaptive input delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single average seeding density is applied across the entire plot, then the management process is simple and quick, but the yield optimization potential is lost due to ignoring intra-plot variability
Solution Approach 1:
The agricultural plot is divided into multiple management zones based on intra-plot variability in soil properties, topography, and historical yield data. Each zone is assigned a specific seeding density recommendation, transforming a single uniform management approach into multiple targeted zones that can be independently managed to optimize overall yield.
Solution Approach 2:
Different seeding densities are assigned to different zones within the plot based on their specific local conditions. High-productivity zones receive higher seeding densities while low-productivity zones receive lower densities, ensuring that each area receives the appropriate input level for its productivity potential rather than applying a uniform approach.
2Productivity
If high seeding density is applied to maximize yield in favorable areas, then productivity increases, but input costs and resource consumption increase
Solution Approach 1:
The system applies different seeding densities to different zones based on their productivity potential. Favorable areas with high productivity potential receive higher seeding densities to maximize yield, while less favorable areas receive lower densities, thereby optimizing the trade-off between input consumption and yield generation across the entire plot.
Solution Approach 2:
The seeding density parameter is varied spatially across the plot according to zone characteristics. By changing this key agronomic parameter from a uniform value to a spatially variable one, the system optimizes both yield and input efficiency by matching input levels to local productivity potential.
3Quantity of substance
If low seeding density is applied in unfavorable areas to reduce input costs, then resource efficiency improves, but yield potential is not fully realized
Solution Approach 1:
The system identifies unfavorable areas through multi-parameter analysis and assigns appropriately reduced seeding densities to these zones. This ensures that input efficiency is optimized in areas where resources are limited, while still capturing the available yield potential without over-applying inputs that would be wasted.
4Measurement precision
If multiple parameters are considered for zone classification, then the precision of seeding density recommendations improves, but the data processing complexity increases
Solution Approach 1:
The system segments the plot into management zones using multiple parameters including soil properties, topography, and historical yield data. This multi-parameter segmentation approach improves the precision of seeding density recommendations by capturing the complexity of intra-plot variability, with the benefit that modern computational systems can handle this processing efficiently.
Solution Approach 2:
The multi-parameter classification system serves multiple functions: it identifies productivity zones, guides seeding density recommendations, and can be applied to other precision agriculture decisions. By creating a comprehensive zone classification that captures essential variability, the system provides a universal framework that improves precision across multiple agronomic decisions.
Data Source
Figure 1~2
Figure 3A~3B
Figure 4A~4B
AI summary
The invention relates to an improved digital agriculture method, intended for increasing the yield of an agricultural plot (P) in relation to a variety of a specific plant species by improving the sowing density. The method essentially comprises the steps of: - a) collecting data relating to P; - b) treating/transforming this data such that they are grouped in relation to P; - c) breaking down P, for the groups obtained in step b), into different management areas (Zg) and classifying these (x) different areas (Zg) into (i) different classes Ck ((i=positive integer)) via an automated statistical classification method; - e) determining a Dimensionless Productivity Index (DPI) for each of the classes Ck; - f) assigning a fixed Yield Potential to P (PYP); - g) calculating, from the DPI obtained in step e) and the PYP obtained in step f), the Yield Potential (YP) of the species in question, for the areas (Zg); - h) determining a Sowing Density (SD) for the variety of the plant species in question and for each of the classes Ck, on the basis of a relationship SD = f (YP), f having constants obtained on the basis of growth simulations produced from an ecophysiological model; - i) generating at least one map of P on which the SD are plotted for the areas (Zg); - j) carrying out the sowing on P on the basis of said map.