An agricultural implement has implement settings for soil engaging tools that are controlled based on measured temporal and long-term soil properties in a field. A controller receives data from various soil and optical sensors and provides decision support for adjusting the implement settings. The soil sensors include a square or modified square electrical array that includes two independent, isolated disk coulters running side-by-side followed by two independent, isolated soil engaging runners. One runner has an optical sensor for organic matter, and the other runner has a temperature and moisture sensor. Above-ground optical sensors can be used to measure soil and plant material ahead of and behind the soil engaging tool. The controller can provide real time alerts to an operator that adjustments to the implement settings are needed, or the adjustments can be made automatically based on operator set thresholds, factory settings, or historical individual or global grower adjustments.

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.

A computing system includes a processor and a non-transitory, computer-readable media including instructions that, when executed by the one or more processors, cause the computing system to access an initial machine data set; label the machine data set; process the labeled machine data set; and modify one or more parameters of the machine-learned model. A method includes accessing an initial machine data set; labeling the machine data set; processing the labeled machine data set; and modifying one or more parameters of the machine-learned model. A computing system for predicting a variety profile index includes a processor; and a non-transitory, computer-readable media including a trained machine-learned model; and instructions that, when executed by the one or more processors, cause the computing system to process a second machine data set to generate one or more predicted variety profile index values; and provide the one or more predicted variety profile index values.

Computer systems and methods of spatially-indexing agricultural content involve inputting agricultural content comprising spatial data and spatially-indexing the agricultural content by: identifying from the spatial data a set of geospatial boundaries for the agricultural content, indexing the agricultural content to the identified geospatial boundaries, cross-referencing the indexed agricultural data with a plurality of sets of geospatial boundaries for a plurality of fields, and indexing the agricultural content to one or more of the plurality of fields when the cross-referencing identifies an overlap between the geospatial boundaries of the indexed agricultural data and one or more of the geospatial boundaries of the plurality of fields.

A method of controlling a mobile agricultural machine that includes performing an agricultural operation during a given pass in a field using a first set of machine settings, obtaining in situ data representing the agricultural operation during the given pass, generating a performance metric based on the in situ data, identifying a second set of machine settings based on the performance metric, and outputting a control instruction that controls the mobile agricultural machine during a subsequent pass in the field based on the second set of machine settings.

A method including adjusting a changeable component of a seed planting machine when switching from a first variety of seed to a second variety of seed during planting, wherein the adjusting is based on a location of the planting machine.

A computer system and computer-implemented techniques for determining and presenting improved seeding rate recommendations for planting seeds in a field are provided. In an embodiment, a computer-implemented method includes receiving digital data representing planting parameters including seed type information and planting row width, and retrieving a set of seeding models based upon the planting parameters, where each of the seeding models includes a regression model defining a relationship between plant yield and seeding rate on a specific field. The method also includes generating an empirical mixture model as a composite distribution of the set of seeding models, generating a seeding rate distribution for the planting parameters based upon the empirical mixture model, and calculating a seeding rate recommendation based on the seed rate distribution. The method then also includes planting plant seeds in the specific field consistent with the seeding rate recommendation.

An agricultural machine includes a seeding system having a seed transport mechanism configured to transport a seed along a transport route, a seed sensor configured to sense presence of the seed at a first location along the transport route, and a motor configured to drive movement of the seed transport mechanism to transport the seed from the first location to a second location in which the seed is released from the seed transport mechanism. A processing system is configured to track a position of the seed along the transport route based on an indication of the sensed presence of the seed at the first location and detected movement of the seed transport mechanism, and generate a motor operating parameter based on the tracked position of the seed and a target parameter for releasing the seed. The motor of the seeding system is operated based on the motor operating parameter.

A sensor network for measuring and processing agricultural sensor measurements having multi-depth sensors, field monitors, and/or field data collection systems. The multi-depth sensor having a GPS; sets of physical sensors located at different depths; a processing structure sampling measurements from the physical sensors; and storing the measurements. The field monitor for use with a mobile platform having: a housing; a camera; a LiDAR sensor; a processing structure capturing point data and image data; generating above-ground field data; and determining crop data. The field data collection system having a stationary field monitor and one or more mobile field monitors capturing above-ground data. The stationary field monitor and the mobile field monitors having an associated GPS. The multi-depth sensors capture below-ground data and communicating the below-ground data to the stationary field monitor. A GPU processes the above-ground data and the GPS data to generate a point cloud data set.

A soil imaging system having a work layer sensor disposed on an agricultural implement to generate an electromagnetic field through a soil area of interest as the agricultural implement traverses a field. A monitor in communication with the work layer sensor is adapted to generate a work layer image of the soil layer of interest based on the generated electromagnetic field. The work layer sensor may also generate a reference image by generating an electromagnetic field through undisturbed soil. The monitor may compare at least one characteristic of the reference image with at least one characteristic of the work layer image to generate a characterized image of the work layer of interest. The monitor may display operator feedback and may effect operational control of the agricultural implement based on the characterized image.