Abstract: Implementations are disclosed for selectively operating edge-based sensors and/or computational resources under circumstances dictated by observation of targeted plant trait(s) to generate targeted agricultural inferences. In various implementations, triage data may be acquired at a first level of detail from a sensor of an edge computing node carried through an agricultural field. The triage data may be locally processed at the edge using machine learning model(s) to detect targeted plant trait(s) exhibited by plant(s) in the field. Based on the detected plant trait(s), a region of interest (ROI) may be established in the field. Targeted inference data may be acquired at a second, greater level of detail from the sensor while the sensor is carried through the ROI. The targeted inference data may be locally processed at the edge using one or more of the machine learning models to make a targeted inference about plants within the ROI.

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 crop yield prediction at the field- and pixel-level. In various implementations, a first temporal sequence of high-elevation digital images may be obtained that capture a first geographic area and are acquired over a first predetermined time interval while the first geographic area includes a particular crop. A first plurality of other data points may also be obtained that influence a ground truth crop yield of the first geographic area after the first predetermined time interval. The first plurality of other data points may be grouped into temporal chunks corresponding temporally with respective images of the first temporal sequence. The first temporal sequence and the temporal chunks of the first plurality of other data points may be applied, e.g., iteratively, as input across a machine learning model to estimate a crop yield of the first geographic area at the end of the first predetermined time interval.

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 tracking objects with changing appearances across temporally-disparate images. In various implementations, a first probability distribution over a plurality of classes may be determined for a first biological object depicted in a first image captured at a first point in time. The classes may represent stages of growth of biological objects. Additional probability distribution(s) over the plurality of classes may be determined for candidate biological object(s) depicted in a second image captured at a second point in time subsequent to the first point in time. The candidate biological object(s) may potentially match the first biological object depicted in the first image.

Abstract: Implementations are described herein for normalizing counts of plant-parts-of-interest detected in digital imagery to account for differences in spatial dimensions of plants, particularly plant heights. In various implementations, one or more digital images depicting a top of a first plant may be processed. The one or more digital images may have been acquired by a vision sensor carried over top of the first plant by a ground-based vehicle. Based on the processing: a distance of the vision sensor to the first plant may be estimated, and a count of visible plant-parts-of-interest that were captured within a field of view of the vision sensor may be determined. Based on the estimated distance, the count of visible plant-parts-of-interest may be normalized with another count of visible plant-parts-of-interest determined from one or more digital images capturing a second plant.

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 disclosed for facilitating visual programming of machine learning state machines. In various implementations, one or more graphical user interfaces (GUIs) may be rendered on one or more displays. Each GUI may include a working canvas on which a plurality of graphical elements corresponding to at least some of a plurality of available logical routines are manipulable to define a machine learning state machine. One or more of the available logical routines may include logical operations that process data using machine learning model(s). Two or more at least partially redundant logical routines that include overlapping logical operations may be identified, and overlapping logical operations of the two or more at least partially redundant logical routines may be merged into a consolidated logical routine. At least some of the logical operations that were previously downstream from the overlapping logical operations may be logically coupled with the consolidated logical routine.

Abstract: Implementations are described herein for edge-based real time crop yield predictions made using sampled subsets of robotically-acquired vision data. In various implementations, one or more robots may be deployed amongst a plurality of plants in an area such as a field. Using one or more vision sensors of the one or more robots, a superset of high resolution images may be acquired that depict the plurality of plants. A subset of multiple high resolution images may then be sampled from the superset of high resolution images. Data indicative of the subset of high resolution images may be applied as input across a machine learning model, with or without additional data, to generate output indicative of a real time crop yield prediction.

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: Techniques are disclosed that enable generating a unified data set by mapping a set of item description phrases, describing entries in a data set, to a set of canonical phrases. Various implementations include generating a similarity measure between each item description phrase and each canonical phrase by processing the corresponding item description phrase and the corresponding canonical phrase using a natural language processing model. Additional or alternative implementations include generating a bipartite graph based on the set of item description phrases, the set of canonical phrases, and the similarity measures. The mapping can be generated based on the bipartite graph.

Abstract: Techniques are described herein for using artificial intelligence to predict crop yields based on observational crop data. A method includes: obtaining a first digital image of at least one plant; segmenting the first digital image of the at least one plant to identify at least one seedpod in the first digital image; for each of the at least one seedpod in the first digital image: determining a color of the seedpod; determining a number of seeds in the seedpod; inferring, using one or more machine learning models, a moisture content of the seedpod based on the color of the seedpod; and estimating, based on the moisture content of the seedpod and the number of seeds in the seedpod, a weight of the seedpod; and predicting a crop yield based on the moisture content and the weight of each of the at least one seedpod.

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 directed to assigning corresponding semantic identifiers to a plurality of rows of an agricultural field, generating a local mapping of the agricultural field that includes the plurality of rows of the agricultural field, and subsequently utilizing the local mapping in performance of one or more agricultural operations. In some implementations, the local mapping can be generated based on overhead vision data that captures at least a portion of the agricultural field. In these implementations, the local mapping can be generated based on GPS data associated with the portion of the agricultural field captured in the overhead vision data. In other implementations, the local mapping can be generated based on driving data generated during an episode of locomotion of a vehicle through the agricultural field. In these implementations, the local mapping can be generated based on GPS data associated with the vehicle traversing through the agricultural field.

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 using machine learning to determine whether candidate crop fields are suitable for management by particular agricultural entities. In various implementations, a machine learning model may be applied to input data to generate output data. The input data may include a first plurality of data points corresponding to field-level agricultural management practices of an agricultural entity. The output data may be indicative of one or more predicted outcomes of the agricultural entity implementing the field-level agricultural management practices on one or more candidate crop fields not currently managed by the agricultural entity. Based on one or more of the predicted outcomes, one or more computing devices may be caused to provide a user associated with the agricultural entity with information about one or more of the candidate crop fields, and/or one or more parameter inputs of a graphical user interface may be prepopulated.

Abstract: Implementations relate to crop yield prediction at the field- and pixel-level. In various implementations, a first temporal sequence of high-elevation digital images may be obtained that capture a first geographic area and are acquired over a first predetermined time interval while the first geographic area includes a particular crop. A first plurality of other data points may also be obtained that influence a ground truth crop yield of the first geographic area after the first predetermined time interval. The first plurality of other data points may be grouped into temporal chunks corresponding temporally with respective images of the first temporal sequence. The first temporal sequence and the temporal chunks of the first plurality of other data points may be applied, e.g., iteratively, as input across a machine learning model to estimate a crop yield of the first geographic area at the end of the first predetermined time interval.