The disclosure relates to a plant growth apparatus and related system to grow and maintain plants under controlled biotic conditions, for example to grow axenic (microbe-free) plants, gnotobiotic (defined microbiota) plants, and holoxenic (complex, or undefined microbiota) plants. This system allows aseptic bottom irrigation with water, soluble nutrients, chemicals, and/or microbiota. Plants can be inverted for dipping and/or vacuum infiltration. The system also allows for passive (gravity) drainage, thereby allowing for gas exchange and preventing root anoxia. A variety of plant growth substrates can be used within the plant growth apparatus as a plant growth medium. The plant growth apparatus, containing the growth substrate medium, can be completely flushed via the drainage port to remove potential toxic byproducts of the sterilization processes. The entire system is suitably constructed using autoclavable material.

Systems and Methods for Augmented-Human Field Inspection Tools for Automated Phenotyping Systems and Agronomy Tools. In one embodiment, a method for plant phenotyping, includes: acquiring a first set of observations about plants in a field by a trainer. The trainer carries a sensor configured to collect observations about the plant, and the first set of observations includes ground truth data. The method also includes processing the first set of observations about the plants by a trait extraction model to generate instructions for a trainee; and acquiring a second set of observations about the plants by a trainee while the trainee follows the instructions.

Systems and Methods for Augmented-Human Field Inspection Tools for Automated Phenotyping Systems and Agronomy Tools. In one embodiment, a method for plant phenotyping, includes: acquiring a first set of observations about plants in a field by a trainer. The trainer carries a sensor configured to collect observations about the plant, and the first set of observations includes ground truth data. The method also includes processing the first set of observations about the plants by a trait extraction model to generate instructions for a trainee; and acquiring a second set of observations about the plants by a trainee while the trainee follows the instructions.

A membrane for covering the cut end of a tree trunk to prevent the tree from creating a seal after it has been cut. The membrane is attachable to the cut end surface of the tree trunk and includes a hydrating layer comprising a hydrogel. The hydrogel, made up primarily of water, adheres to the cut end surface of the tree trunk to continue hydrating the tree, and prevents air from reaching the tree's exposed transport tissue. In some embodiments, the membrane includes a backing layer and a release layer on opposite sides of the hydrating layer.

A membrane for covering the cut end of a tree trunk to prevent the tree from creating a seal after it has been cut. The membrane is attachable to the cut end surface of the tree trunk and includes a hydrating layer comprising a hydrogel. The hydrogel, made up primarily of water, adheres to the cut end surface of the tree trunk to continue hydrating the tree, and prevents air from reaching the tree's exposed transport tissue. In some embodiments, the membrane includes a backing layer and a release layer on opposite sides of the hydrating layer.

Implementations include providing a baseline multi-dimensional model of a cultivar, determining an encoding based on the baseline multi-dimensional model, and a target multi-dimensional model, the encoding defining a string of symbols, and being based on an alphabet and a set of rules, providing an expected multi-dimensional model based on the encoding, and a modified set of rules, the modified set of rules being based on the set of rules, the expected multi-dimensional model representing the cultivar after a period of time, selecting a set of actions by determining multiple predicted multi-dimensional models for each set of actions in a plurality of sets of actions, and, for each predicted multi-dimensional model, providing a predicted yield that can be used to determine impact with respect an expected yield, the set of actions being selected based on a respective impact, and providing the set of actions as output for executing on the cultivar.

Implementations include providing a baseline multi-dimensional model of a cultivar, determining an encoding based on the baseline multi-dimensional model, and a target multi-dimensional model, the encoding defining a string of symbols, and being based on an alphabet and a set of rules, providing an expected multi-dimensional model based on the encoding, and a modified set of rules, the modified set of rules being based on the set of rules, the expected multi-dimensional model representing the cultivar after a period of time, selecting a set of actions by determining multiple predicted multi-dimensional models for each set of actions in a plurality of sets of actions, and, for each predicted multi-dimensional model, providing a predicted yield that can be used to determine impact with respect an expected yield, the set of actions being selected based on a respective impact, and providing the set of actions as output for executing on the cultivar.

Disclosed are methods of producing nutrient solutions having unique isotopic fingerprints; methods of producing traceable plants; and methods of identifying the source of a traceable plant that does not rely on expensive artificially separated isotopes. Plants grown with these nutrient solutions will have unique isotopic fingerprints that will be difficult or impossible to counterfeit.

Disclosed are methods of producing nutrient solutions having unique isotopic fingerprints; methods of producing traceable plants; and methods of identifying the source of a traceable plant that does not rely on expensive artificially separated isotopes. Plants grown with these nutrient solutions will have unique isotopic fingerprints that will be difficult or impossible to counterfeit.

In some embodiments, the system is programmed to build from multiple training sets multiple digital models, each for recognizing plant diseases having symptoms of similar sizes. Each digital model can be implemented with a deep learning architecture that classifies an image into one of several classes. For each training set, the system is thus programmed to collect images showing symptoms of one or more plant diseases having similar sizes. These images are then assigned to multiple disease classes. For a first one of the training sets used to build the first digital model, the system is programmed to also include images that correspond to a healthy condition and images of symptoms having other sizes. These images are then assigned to a no-disease class and a catch-all class. Given a new image from a user device, the system is programmed to then first apply the first digital model. For the portions of the new image that are classified into the catch-all class, the system is programmed to then apply another one of the digital models. The system is programmed to finally transmit classification data to the user device indicating how each portion of the new image is classified into a class corresponding to a plant disease or no plant disease.