Abstract: Implementations are described herein for leveraging an agricultural knowledge graph to generate messages automatically. In various implementations, an agricultural event may trigger proactive performance of one or more of the following operations. Nodes of the agricultural knowledge graph may be identified as related to the agricultural event, including field node(s) representing subject agricultural field(s) to which the agricultural event is relevant and other node(s) connected to one or more of the field nodes by edge(s). Machine learning model(s) may be accessed based on the identified nodes and/or the edges that connect the identified nodes. Data relevant to the subject agricultural field(s) may be retrieved from data source(s) controlled by an agricultural entity and processed based on the machine learning model(s) to generate inference(s) about the subject agricultural field(s).

Abstract: Implementations are described herein for auditing performance of large-scale tasks. In various implementations, one or more ground-level vision sensors may capture a first set of one or more images that depict an agricultural plot prior to an agricultural task being performed in the agricultural plot, and a second set of one or more images that depict the agricultural plot subsequent to the agricultural task being performed in the agricultural plot. The first and second sets of images may be processed in situ using edge computing device(s) based on a machine learning model to generate respective pluralities of pre-task and post-task inferences about the agricultural plot. Performance of the agricultural task may include comparing the pre-task inferences to the post-task inferences to generate operational metric(s) about the performance of the agricultural task in the agricultural plot. The operational metric(s) may be presented at one or more output devices.

Abstract: Implementations relate to diagnosis of crop yield predictions and/or crop yields at the field- and pixel-level. In various implementations, a first temporal sequence of high-elevation digital images may be obtained that captures a geographic area over a given time interval through a crop cycle of a first type of crop. Ground truth operational data generated through the given time interval and that influences a final crop yield of the first geographic area after the crop cycle may also be obtained. Based on these data, a ground truth-based crop yield prediction may be generated for the first geographic area at the crop cycle's end. Recommended operational change(s) may be identified based on distinct hypothetical crop yield prediction(s) for the first geographic area. Each distinct hypothetical crop yield prediction may be generated based on hypothetical operational data that includes altered data point(s) of the ground truth operational data.

Abstract: Implementations set forth herein relate to using fiducial markings on one or more localized portions of an agricultural apparatus in order to generate local and regional data that can be correlated for planning and executing agricultural maintenance. An array of fiducial markings can be disposed onto plastic mulch that surrounds individual crops, in order that each fiducial marking of the array can operate as a signature for each individual crop. Crop data, such as health and yield, corresponding to a particular crop can then be stored in association with a corresponding fiducial marking, thereby allowing the certain data for the particular crop to be tracked and analyzed. Furthermore, autonomous agricultural devices can rely on the crop data, over other sources of data, such as GPS satellites, thereby allowing the autonomous agricultural devices to be more reliable.

Abstract: Implementations are described herein for predicting soil organic carbon (“SOC”) content for agricultural fields detected in digital imagery. In various implementations, one or more digital images depicting portion(s) of one or more agricultural fields may be processed. The one or more digital images may have been acquired by a vision sensor carried through the field(s) by a ground-based vehicle. Based on the processing, one or more agricultural inferences indicating agricultural practices or conditions predicted to affect SOC content may be determined. Based on the agricultural inferences, one or more predicted SOC measurements for the field(s) may be determined.

Abstract: Implementations are described herein for integrating phenotyping machine learning (ML) models with an agricultural knowledge graph (AKG) to facilitate streamlined and flexible phenotypic inferences. In various implementations, the AKG may be traversed based on input including image(s) of crops growing in an agricultural plot until a destination node is reached. The AKG may include a phenotypic taxonomy of nodes representing a taxonomic hierarchy of organisms, with the destination node corresponding to a level of the phenotypic taxonomy that is commensurate in scope with the input. The phenotypic taxonomy of nodes may provide access to a corresponding taxonomy of phenotyping ML models, each trained to generate phenotypic inference(s) at a specificity that corresponds to a level of the phenotypic taxonomy. The crop image(s) may be processed using the phenotyping ML model that is accessible via the destination node to generate phenotypic inference(s) about the agricultural plot.

Abstract: Implementations are described herein for training and applying machine learning models to digital images capturing plants, and to other data indicative of attributes of individual plants captured in the digital images, to recognize individual plants in distinction from other individual plants. In various implementations, a digital image that captures a first plant of a plurality of plants may be applied, along with additional data indicative of an additional attribute of the first plant observed when the digital image was taken, as input across a machine learning model to generate output. Based on the output, an association may be stored in memory, e.g., of a database, between the digital image that captures the first plant and one or more previously-captured digital images of the first plant.

Abstract: Implementations set forth herein relate to utilizing S2 cell values to characterize arbitrary portions of land parcels and storing the S2 cell values in association with a non-fungible token (NFT) that is stored on a blockchain network, or other peer-to-peer (P2P) network. The S2 cell values can be generated by iteratively using bounding shapes that are selected to extend over at least a portion of a respective parcel of land, and each bounding shape can be represented by one or more single dimensional values. When a generated bounding shape extends outside of a boundary of a parcel of land, subcells of the bounding shape can be generated to define further bounding shapes. A land NFT for the list of cell values for the bounding shapes can be stored at a blockchain address for an authenticated owner of the parcel of land.

Abstract: Implementations are disclosed for automatic commissioning, configuring, calibrating, and/or coordinating sensor-equipped modular edge computing devices that are mountable on agricultural vehicles. In various implementations, neighbor modular edge computing device(s) that are mounted on a vehicle nearest a given modular edge computing device may be detected based on sensor signal(s) generated by contactless sensor(s) of the given modular edge computing device. Based on the detected neighbor modular edge computing device(s), an ordinal position of the given modular edge computing device may be determined relative to a plurality of modular edge computing devices mounted on the agricultural vehicle. Based on the sensor signal(s), distance(s) to the neighbor modular edge computing device(s) may be determined. Extrinsic parameters of the given modular edge computing device may be determined based on the ordinal position of the given modular edge computing device and the distance(s).

Abstract: Implementations are described herein for training and applying machine learning models to digital images capturing plants, and to other data indicative of attributes of individual plants captured in the digital images, to recognize individual plants in distinction from other individual plants. In various implementations, a digital image that captures a first plant of a plurality of plants may be applied, along with additional data indicative of an additional attribute of the first plant observed when the digital image was taken, as input across a machine learning model to generate output. Based on the output, an association may be stored in memory, e.g., of a database, between the digital image that captures the first plant and one or more previously-captured digital images of the first plant.

Abstract: Implementations are directed to generating a stream of agricultural annotations with respect to area(s) of interest of an agricultural field, and providing the stream of agricultural annotations for presentation to the user in an augmented reality manner with respect to the area(s) of interest. In some implementations, a stream of vision data may be received at a first computing device of the user and from a second computing device of the user. Further, the first computing device may process the stream of vision data to generate the stream of agricultural annotations. Moreover, the first computing device may transmit the stream of agricultural annotations to the second computing device to cause the stream of agricultural annotations to be provided for presentation to the user. In other implementations, the first computing device may be omitted, and the second computing device may be utilized to generate the stream of agricultural annotations.

Abstract: Implementations are disclosed for automatic commissioning, configuring, calibrating, and/or coordinating sensor-equipped modular edge computing devices that are mountable on agricultural vehicles. In various implementations, neighbor modular edge computing device(s) that are mounted on a vehicle nearest a given modular edge computing device may be detected based on sensor signal(s) generated by contactless sensor(s) of the given modular edge computing device. Based on the detected neighbor modular edge computing device(s), an ordinal position of the given modular edge computing device may be determined relative to a plurality of modular edge computing devices mounted on the agricultural vehicle. Based on the sensor signal(s), distance(s) to the neighbor modular edge computing device(s) may be determined. Extrinsic parameters of the given modular edge computing device may be determined based on the ordinal position of the given modular edge computing device and the distance(s).

Abstract: Implementations relate to detecting/replacing transient obstructions from high-elevation digital images. A digital image of a geographic area includes pixels that align spatially with respective geographic units of the geographic area. Analysis of the digital image may uncover obscured pixel(s) that align spatially with geographic unit(s) of the geographic area that are obscured by transient obstruction(s). Domain fingerprint(s) of the obscured geographic unit(s) may be determined across pixels of a corpus of digital images that align spatially with the one or more obscured geographic units. Unobscured pixel(s) of the same/different digital image may be identified that align spatially with unobscured geographic unit(s) of the geographic area. The unobscured geographic unit(s) also may have domain fingerprint(s) that match the domain fingerprint(s) of the obscured geographic unit(s).

Abstract: Some implementations herein relate to a graphical user interface (GUI) that facilitates dynamically partitioning agricultural fields into clusters on an individual agricultural field-basis using agricultural features. A map of a geographic area containing a plurality of agricultural fields may be rendered as part of a GUI. The agricultural fields may be partitioned into a first set of clusters based on a first granularity value and agricultural features of individual agricultural fields. The individual agricultural fields may be visually annotated in the GUI to convey the first set of clusters of similar agricultural fields. Upon receipt of a second granularity value different from the first granularity value, the agricultural fields may be partitioned into a second set of clusters of similar agricultural fields. The map of the geographic area may be updated so that individual agricultural fields are visually annotated to convey the second set of clusters.

Abstract: Implementations are described herein for predicting soil organic carbon (“SOC”) content for agricultural fields detected in digital imagery. In various implementations, one or more digital images depicting portion(s) of one or more agricultural fields may be processed. The one or more digital images may have been acquired by a vision sensor carried through the field(s) by a ground-based vehicle. Based on the processing, one or more agricultural inferences indicating agricultural practices or conditions predicted to affect SOC content may be determined. Based on the agricultural inferences, one or more predicted SOC measurements for the field(s) may be determined.

Abstract: Implementations relate to detecting/replacing transient obstructions from high-elevation digital images, and/or to fusing data from high-elevation digital images having different spatial, temporal, and/or spectral resolutions. In various implementations, first and second temporal sequences of high-elevation digital images capturing a geographic area may be obtained. These temporal sequences may have different spatial, temporal, and/or spectral resolutions (or frequencies). A mapping may be generated of the pixels of the high-elevation digital images of the second temporal sequence to respective sub-pixels of the first temporal sequence. A point in time at which a synthetic high-elevation digital image of the geographic area may be selected. The synthetic high-elevation digital image may be generated for the point in time based on the mapping and other data described herein.

Abstract: Implementations are described herein for colorizing an X-ray image and predicting one or more phenotypic traits about a plant based on the colorized X-ray image. In various implementations, an X-ray image that depicts a plant with a canopy of the plant partially occluding a part-of-interest is obtained, where the part-of-interest is visible through the canopy in the X-ray image. The X-ray images is colorized to predict one or more phenotypic traits of the part-of-interest. The colorization includes processing the X-ray image based on a machine learning model to generate a colorized version of the X-ray image, and predicting the one or more phenotypic traits based on one or more visual features of the colorized version of the X-ray image.

Abstract: Implementations relate to diagnosis of crop yield predictions and/or crop yields at the field- and pixel-level. In various implementations, a first temporal sequence of high-elevation digital images may be obtained that captures a geographic area over a given time interval through a crop cycle of a first type of crop. Ground truth operational data generated through the given time interval and that influences a final crop yield of the first geographic area after the crop cycle may also be obtained. Based on these data, a ground truth-based crop yield prediction may be generated for the first geographic area at the crop cycle's end. Recommended operational change(s) may be identified based on distinct hypothetical crop yield prediction(s) for the first geographic area. Each distinct hypothetical crop yield prediction may be generated based on hypothetical operational data that includes altered data point(s) of the ground truth operational data.

Abstract: Implementations are disclosed for automatic commissioning, configuring, calibrating, and/or coordinating sensor-equipped modular edge computing devices that are mountable on agricultural vehicles. In various implementations, neighbor modular edge computing device(s) that are mounted on a vehicle nearest a given modular edge computing device may be detected based on sensor signal(s) generated by contactless sensor(s) of the given modular edge computing device. Based on the detected neighbor modular edge computing device(s), an ordinal position of the given modular edge computing device may be determined relative to a plurality of modular edge computing devices mounted on the agricultural vehicle. Based on the sensor signal(s), distance(s) to the neighbor modular edge computing device(s) may be determined. Extrinsic parameters of the given modular edge computing device may be determined based on the ordinal position of the given modular edge computing device and the distance(s).

Abstract: Implementations are disclosed for adaptively adjusting various parameters of equipment in unpredictable terrain, such as agricultural fields. In various implementations, edge computing device(s) may obtain a first image captured by vision sensor(s) transported across an agricultural field by a vehicle. The first image may depict plant(s) growing in the agricultural area. The edge computing device(s) may process the first image based on a machine learning model to generate agricultural inference(s) about the plant(s) growing in the agricultural area. The edge computing device(s) may determine a quality metric for the agricultural inference(s). While the vehicle continues to travel across the agricultural field, and based on the quality metric: the edge computing device(s) may trigger one or more hardware adjustments to one or more of the vision sensors, or one or more adjustments in an operation of the vehicle.