Method and system for performing data analysis for plant phenotyping

A data acquisition and evaluation system for performing data analysis for plant phenotyping of one or more single plants in each of a plurality of distributed fields, comprising:

• a hyperspectral imaging sensor for simultaneously capturing spectral data associated with the one or more single plants in each of the plurality of distributed fields;
• an image sensor for simultaneously capturing image data associated with the one or more single plants in each of the plurality of distributed fields, wherein the image sensor is a color sensor for selective detection and evaluation of a visible spectral range;
• an inertial measurement unit comprising acceleration sensors and rotational speed sensors for simultaneously capturing high-resolution georeference data associated with the one or more single plants in each of the plurality of distributed fields, the high-resolution georeference data comprising georeferenced coordinates;
• and
• a control unit, which is remote from the hyperspectral imaging sensor, the image sensor, and the inertial measurement unit, and adapted to:
• spatialize the image data to generate georeferenced image data and a high-resolution digital surface model, wherein spatializing the image data comprises assigning spatial coordinates to the image data and spatially correcting the image data, whereby spatial information is assigned to individual image pixels, wherein the high-resolution digital surface model includes height information comprising an orientation of growth of a plant, a direction of growth of the plant, a direction of growth of leaves of the plant, a height of the plant, or combinations thereof, wherein generating the high-resolution digital surface model comprises:
• obtaining recordings of multiple individual picture elements by capturing the image data;
• combining the recorded multiple individual picture elements in a three-dimensional image;
• generating one or more visual indications of diseased leaves, healthy leaves, soil, or combinations thereof from the spectral data by comparing the spectral data to referenced spectral data from a spectral database;
• spatialize the spectral data;
• generate georeferenced spectral data from the spatialized spectral data using the high-resolution digital surface model;
• overlay the one or more visual indications, the georeferenced image data, and georeferenced spectral data with field plan information to generate a high-resolution analysis data set, wherein the overlaying of the georeferenced image data and the georeferenced spectral data with the field plan information comprises an assignment of field piece information according to the georeferenced coordinates;
• and
• localize the one or more single plants in a range of 10 cm around one or more real positions of the one or more single plants in each of the plurality of distributed fields.

A method for selecting a plant, said method comprising:

• a) growing a plant population;
• b) simultaneously capturing spectral data associated with one or more single plants in each of a plurality of distributed fields via a hyperspectral imaging sensor;
• c) simultaneously capturing image data associated with the one or more single plants in each of the plurality of distributed fields via an image sensor, wherein the image sensor is a color sensor for selective detection and evaluation of a visible spectral range;
• d) simultaneously capturing high-resolution georeference data associated with the one or more single plants in each of the plurality of distributed fields via an inertial measurement unit comprising accelerate sensors and rotational speed sensors, the high-resolution georeference data comprising georeference coordinates;
• e) transmitting the captured spectral data, image data, and high-resolution georeference data to one or more remote servers;
• f) generating, via the one or more remote servers, one or more visual indications of diseased leaves, healthy leaves, soil, or combinations thereof from the spectral data by comparing the spectral data to referenced spectral data from a spectral database;
• g) spatializing, via the one or more remote servers, the image data to generate georeferenced image data and a high-resolution digital surface model, wherein spatializing the image data comprises assigning spatial coordinates to the image data and spatially correcting the image data, wherein spatial information is assigned to individual image pixels, wherein the high-resolution digital surface model includes height information comprising an orientation of growth of a plant, a direction of growth of the plant, a direction of growth of the leaves of the plant, a height of the plant, or combinations thereof, wherein generating the high-resolution digital surface model comprises:
• obtaining multiple recordings of an individual picture element by capturing the image data;
• and
• combining the recorded multiple individual picture elements in a three-dimensional image;
• h) spatializing, via the one or more remote servers, the spectral data;
• i) generating, via the one or more remote servers, georeferenced spectral data from the spatialized spectral data using the high-resolution digital surface model;
• j) overlaying, via the one or more remote servers, the one or more visual indications, the georeferenced image data, and the georeferenced spectral data with field plan information to generate a high-resolution analysis data set by using a merging algorithm, wherein the overlaying of the georeferenced image data and the georeferenced spectral data with the field plan information comprises an assignment of field piece information according to the georeference coordinates;
• k) localizing, via the one or more remote servers, the one or more single plants in a range of 10 cm around one or more real positions of the one or more single plants in each of the plurality of distributed fields;
• and
• l) selecting a plant from the plant population having a desired phenotype.

A method for selecting plant individuals in a breeding program, said method comprising:

• a) growing a plant population of training individuals;
• b) simultaneously capturing spectral data associated with one or more single plants in each of a plurality of distributed fields via a hyperspectral imaging sensor;
• c) simultaneously capturing image data associated with the one or more single plants in each of the plurality of distributed fields via an image sensor, wherein the image sensor is a color sensor for selective detection and evaluation of a visible spectral range;
• d) simultaneously capturing high-resolution georeference data associated with the one or more single plants in each of the plurality of distributed fields via an inertial measurement unit comprising accelerate sensors and rotational speed sensors, the high-resolution georeference data comprising georeference coordinates;
• e) transmitting the captured spectral data, image data, and high-resolution georeference data to one or more remote servers;
• f) spatializing, via the one or more remote servers, the image data to generate georeferenced image data and a high-resolution digital surface model, wherein spatializing the image data comprises assigning spatial coordinates to the image data and spatially correcting the image data, wherein spatial information is assigned to individual image pixels, wherein the high-resolution digital surface model includes height information comprising an orientation of growth of a plant, a direction of growth of the plant, a direction of growth of the leaves of the plant, a height of the plant, or combinations thereof, wherein generating the high-resolution digital surface model comprises:
• obtaining multiple recordings of an individual picture element by capturing the image data;
• and
• combining the recorded multiple individual picture elements in a three-dimensional image;
• g) generating, via the one or more remote servers, one or more visual indications of diseased leaves, healthy leaves, soil, or combinations thereof from the spectral data by comparing the spectral data to referenced spectral data from a spectral database;
• h) spatializing, via the one or more remote servers, the spectral data;
• i) generating, via the one or more remote servers, georeferenced spectral data from the spatialized spectral data using the high-resolution digital surface model;
• j) overlaying, via the one or more remote servers, the one or more visual indications, the georeferenced image data, and the georeferenced spectral data with field plan information to generate a high-resolution analysis data set by using a merging algorithm, wherein the overlaying of the georeferenced image data and the georeferenced spectral data with the field plan information comprises an assignment of field piece information according to the georeference coordinates;
• k) localizing, via the one or more remote servers, the one or more single plants in a range of 10 cm around one or more real positions of the one or more single plants in each of the plurality of distributed fields;
• and
• l) generating a phenotype training data set;
• m) associating the phenotype training data set with a genotype training data set comprising genetic information across a genome of each training individual;
• n) genotyping a population of breeding individuals;
• and
• o) selecting breeding pairs from the population of breeding individuals based on plant genotypes using the associated training data set to select breeding pairs likely or able to generate offspring with one or more desired traits.

A method for selecting an inbred plant, the method comprising:

• a) quantitatively assessing a distribution of two or more traits in a population of inbred plants, wherein assessing the distribution of at least one trait is performed on bases of a high-resolution analysis data set generated by:
• simultaneously capturing spectral data associated with one or more single plants in each of a plurality of distributed fields via a hyperspectral imaging sensor;
• simultaneously capturing image data associated with the one or more single plants in each of the plurality of distributed fields via an image sensor, wherein the image sensor is a color sensor for selective detection and evaluation of a visible spectral range;
• simultaneously capturing high-resolution georeference data associated with the one or more single plants in each of the plurality of distributed fields via an inertial measurement unit comprising acceleration sensors and rotational speed sensors, the high-resolution georeference data comprising georeferenced coordinates;
• transmitting the captured spectral data, image data, and high-resolution georeference data to one or more remote servers;
• spatializing, via the one or more remote servers, the image data to generate georeferenced image data and a high-resolution digital surface model, wherein spatializing the image data comprises assigning spatial coordinates to the image data and spatially correcting the image data such that spatial information is assigned to individual image pixels, wherein the high-resolution digital surface model includes height information comprising an orientation of growth of a plant, a direction of growth of the plant, a direction of growth of the leaves of the plant, a height of the plant, or combinations thereof, wherein generating the high-resolution digital surface model comprises:
• obtaining multiple recordings of an individual picture element by capturing the image data;
• and
• combining the multiple recorded picture elements in a three-dimensional image;
• generating, via the one or more remote servers, one or more visual indications of diseased leaves, healthy leaves, soil, or combinations thereof from the spectral data by comparing the spectral data to referenced spectra data from a spectral database;
• spatializing, via the one or more remote servers, the spectral data;
• generating, via the one or more remote servers, georeferenced spectral data from the spatialized spectral data using the high-resolution digital surface model;
• and
• overlaying, via the one or more remote servers, the one or more visual indications, the georeferenced image data, and the georeferenced spectral data with field plan information to generate the high-resolution analysis data set by using a merging algorithm, wherein the overlaying of the georeferenced image data and the georeferenced spectral data with the field plan information comprises an assignment of field piece information according to the georeferenced coordinates;
• localizing, via the one or more remote servers, the one or more single plants in a range of 10 cm around one or more real positions of the one or more single plants in each of the plurality of distributed fields;
• b) constructing a relationship matrix for each inbred plant parent for the two or more traits of interest;
• c) applying the relationship matrix in a multivariate mixed model analysis for the population of inbred plants;
• d) obtaining a predicted value for said inbred plant;
• and
• e) selecting one or more inbred plants based on the predicted value.