Abstract: A time period for which an ineffective operation is performed during an excavation work is reduced. A work machine includes a vehicular body, a running wheel rotatably attached to the vehicular body, a work implement operable with respect to the vehicular body, an operation apparatus for operating the running wheel and the work implement, and a controller that controls an operation by the work machine. The controller determines that an ineffective operation in which the work implement does not work is being performed during the excavation work based on an operation command value output from the operation apparatus and outputs a time period for which the ineffective operation is being performed.

Abstract: A method for automatically controlling a display system for a work vehicle having a first implement supported at a first end of a chassis, a second implement supported at a second end of the chassis, and a chair that is selectively movable between a first position oriented toward the first end of the work vehicle and a second position oriented toward the second end of the work vehicle. The method may include receiving an input indicative of a position of the chair and an input indicative of an operating state of the work vehicle. Additionally, the method may include controlling a display device to display image data from an imaging device associated with a first portion of a worksite or a second portion of the worksite based at least in part on the position of the chair and the operating state of the work vehicle.

Abstract: The present disclosure relates generally to autonomous machines (AMs) and more particularly to techniques for intelligently planning, managing and performing various tasks using AMs. A control system (referred to as a fleet management system or FMS) is disclosed for managing a set of resources at a site, which may include AMs. The FMS is configured to control and manage the AMs at the site such that tasks are performed autonomously by the AMs. An AM may directly communicate with another AM located on the site to complete a task without requiring to be in constant communication with the FMS during the performance of the task. The FMS is configured to use various optimization techniques to allocate resources (e.g., AMs) for performing tasks at the site. The resource allocation is performed so as to maximize the use of available AMs while ensuring that the tasks get performed in a timely manner.

Abstract: A method of area coverage planning with replenishment planning includes receiving information of a boundary of the work area, location information of one or more refill stations, and information of a current amount of the material left in the autonomous vehicle, laying a plurality of tracks within the boundary of the work area so as to minimize a total distance of the plurality of tracks, generating a coverage trajectory, and based on (i) the coverage trajectory, (ii) the location information of the one or more refill stations, (iii) the current amount of the material left in the autonomous vehicle, and (iv) a nominal full amount and a nominal consumption rate of the material by the autonomous vehicle, determining one or more logistic points along the coverage trajectory at which a remaining amount of the material reaches a threshold, for each logistic point, generating a replenishment trajectory.

Abstract: One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural characteristic values at different geographic locations of a field. An in-situ sensor on the agricultural work machine senses an agricultural characteristic as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural characteristic at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural characteristic sensed by the in-situ sensor. The predictive map can be output and used in automated machine control.

Abstract: One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural characteristic values at different geographic locations of a field. An in-situ sensor on the agricultural work machine senses an agricultural characteristic as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural characteristic at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural characteristic sensed by the in-situ sensor. The predictive map can be output and used in automated machine control.

Abstract: A working vehicle includes a steering handle, a vehicle body to travel by manual steering via the steering handle or automatic steering for the steering handle based on a scheduled traveling line, a setting switch to switch between valid and invalid, a setting mode to set at least the automatic steering before the automatic steering is started, and a display including a driving display portion to display driving information of the vehicle body during traveling. When the setting mode is switched to be valid, the display changes a displaying state of the driving display portion to another different displaying state different from the displaying state where the setting mode is invalid.

Abstract: A vegetative health mapping system which creates two- or three-dimensional maps and associates moisture content, soil density, ambient light, surface temperature, and/or additional indications of vegetative health with the map. Moisture content is inferred using radar return signals of near-field and/or far-field radar. By tuning various parameters of the one or more radar (e.g. frequency, focus, power), additional data may be associated with the map from subterranean features (such as rocks, soil density, sprinklers, etc.). Additional sensors (camera(s), lidar, IMU, GPS, etc.) may be fused with radar returns to generate maps having associated moisture content, surface temperature, ambient light levels, additional indications of vegetative health (as may be determined by machine learned algorithms), etc. Such vegetative health maps may be provided to a user who, in turn, may indicate additional areas for the vegetative health device to scan or otherwise used to recommend and/or perform treatments.

Abstract: A control system for an agricultural utility vehicle includes a distributor linkage for applying fertilizer, plant protection agents, or seed, the distributor linkage having a center part and two lateral extension arms. The center part is arranged so that it can be moved along a vertical axis to adjust the height of the distributor linkage. At least three sensors for determining the distance between the center part and a respective extension arm to the ground are assigned to the distributor linkage, and the system includes a data processing unit such that signals from the sensors are processed as actual values to generate an actuating signal for a hydraulic device is generated for adaptation to a target distance.

Abstract: A method of area coverage planning for an autonomous vehicle includes, at a computer system, receiving information of a boundary of a work area, and laying a plurality of tracks within the boundary of the work area. The plurality of tracks is spaced apart from each other by a spacing. Laying the plurality of tracks includes, based on the information of the boundary of the work area, performing a multivariate optimization to: (i) determine an optimal direction of the plurality of tracks, and (ii) an optimal offset for a first track from the boundary, so as to minimize a total distance of the plurality of tracks. The method further includes generating a trajectory that is traversable by the autonomous vehicle to traverse the plurality of tracks.

Abstract: The present disclosure describes computer systems and computer-implemented methods for use in an agricultural operation. Vehicle location information for at least one agricultural vehicle is received, and the vehicle location information is used to determine a vehicle path. Vehicle state information is received from the vehicle and is used to determine whether the vehicle is in a working or non-working state. The vehicle path is then rendered on a map display, with the map display visually distinguishing between sections of the vehicle path traversed while the vehicle is in the working state and sections of the vehicle path traversed while the vehicle is in the non-working state.

Abstract: The technology involves determining a minimum lateral gap distance between a vehicle configured for autonomous driving and one or more other objects in the vehicle's environment. The minimum lateral gap is used when determining whether to have a driver take over control of certain driving operations. This provides a measure of safety during disengagements or other change of control events. Determining the minimum lateral gap includes calculating a budgeted distance based on a cross-track error for a lateral position of the vehicle, an allowed actual gap distance to an object in the vehicle's environment, and a perception error associated with a location of the object in the vehicle's environment. This determination can be done for a set of possible operating speeds and steering rate limit combinations. The vehicle's control system may notify the driver to take control, for instance with audible, visual and/or haptic notifications.

Abstract: The present invention is for an autonomous aerial vehicle that enables near real-time computation of harvest yield data. Generally, the autonomous aerial vehicle receives combine harvest data from a harvesting vehicle, generates high-resolution yield data based on sensor suite that is on-board the autonomous vehicle, obtains edge compute data from an edge computing device at the edge of the network, and segments the received combine harvest data, the generated high-resolution yield data, and the obtained edge compute data. The aerial vehicle applies data normalization models to the segmented data and computes a normalized harvest yield for at least a portion a land tract. In this manner, the data delivery vehicles computes normalized data that otherwise can by noisy and unreliable.

Abstract: A working machine includes a controller configured to determine a first deceleration threshold corresponding to each of a first traveling pressure, a second traveling pressure, a third traveling pressure, and a fourth traveling pressure, to perform automatic deceleration to reduce rotation speeds of a left traveling motor and a right traveling motor, and to judge whether to perform the automatic deceleration based on the determined first deceleration threshold, the first traveling pressure, the second traveling pressure, the third traveling pressure, and the fourth traveling pressure.

Abstract: One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural characteristic values at different geographic locations of a field. An in-situ sensor on the agricultural work machine senses an agricultural characteristic as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural characteristic at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural characteristic sensed by the in-situ sensor. The predictive map can be output and used in automated machine control.

Abstract: A system and method are provided for determining the position and orientation of an implement on a work machine in a non-contact manner using machine vision. A 3D camera, which is mounted on the vehicle with a field of view that includes components on the implement (e.g., markers in some examples), determines a three-dimensional position in a local coordinate system of each of the components. A global positioning system in cooperation with an inertial measurement unit determines a three-dimensional position and orientation of the 3D camera in a global coordinate system. A computing system calculates a three-dimensional position in the global coordinate system for the components using the local three-dimensional positions of the components and the global three-dimensional position and orientation of the 3D camera. The position and orientation of the implement can then be calculated based on the calculated global three-dimensional positions of the components.

Abstract: A milling machine may include a frame supported by a traction device, a milling drum for milling a surface and supported on the frame, and a conveyor for receiving milled material from the milling drum and conveying the milled material upward to a release point. The milling machine may include a sensor configured for monitoring loading of a truck by the milling machine and a controller in communication with the sensor to coordinate with the sensor and recognize when the truck is full.

Abstract: A compaction mitigation system for a work area and a method of mitigating compaction in a work area may include determining a compaction map of the work area having compaction data associated with a plurality of reference points, passing a work tool through the work area at the plurality of reference points, and adjusting the work tool at the plurality of reference points based on the compaction data.

Abstract: A row unit downforce system including: a downforce actuator in operational communication with the row unit and constructed and arranged to apply supplemental downforce to the row unit and opening disks; a monitoring system comprising at least one furrow depth sensor constructed and arranged to generate furrow depth values; and a control system module, wherein the control system module is constructed and arranged to generate actuator command signals in response to the furrow depth values.

Abstract: Systems and methods for determining a swing angle of a swing boom of a vehicle are provided. Sensor data is received from sensors disposed on a swing boom and a body of a vehicle. It is determined whether the swing boom is static or moving relative to the body based on the sensor data. In response to determining that the swing boom is static, the received sensor data is corrected based on an observed swing angle and an estimated swing angle is calculated based on the corrected sensor data. In response to determining that the swing boom is moving, the estimated swing angle is calculated based on the received sensor data. The estimated swing angle is output.

Abstract: A shovel includes a lower traveling body, an upper turning body turnably mounted on the lower traveling body, a cab mounted on the upper turning body, an attachment attached to the upper turning body, a hardware processor, and a display device. The hardware processor is configured to move the end attachment of the attachment relative to an intended work surface with the ground being pressed with a predetermined force by the working part of the end attachment, in response to a predetermined operation input related to the attachment. The display device is configured to display information on an irregularity of the ground.

Abstract: mechanical arm type measuring robot device and an application method, and relates to the technical field of intelligent coal mine mining. The mechanical arm type measuring robot device comprises an automatic leveling total station, a protection mechanism, a pitch adjusting mechanism, a yaw adjusting mechanism, a vertical rotating mechanism, a controller, a mounting base and a mobile terminal. Based on a preset pitch angle and a preset yaw angle, the measuring robot starts from an initial position, and performs extension and retraction actions in a plurality of degrees of freedom in the pitch adjusting mechanism and the yaw adjusting mechanism to move the total station to a preset working position.

Abstract: An excavator includes a rotatable house and a bucket operably coupled to the rotatable house. The excavator also includes one or more swing sensors configured to provide at least one rotation sensor signal indicative of rotation of the rotatable house and one or more controllers coupled to the sensor. The one or more controllers being configured to implement inertia determination logic that determines the inertia of a portion of the excavator and control signal generator logic that generates a control signal to control the excavator, based on the inertia of the portion of the excavator.

Abstract: A machine system includes a first wireless transceiver, a plurality of second wireless transceivers, and a processing circuit. The first wireless transceiver is configured to couple to a portion or a component of a lift assembly of a machine. The first wireless transceiver is configured to transmit a first wireless signal. The plurality of second wireless transceivers are configured to couple to a base of the machine. The plurality of second wireless transceivers are configured to detect the first wireless signal and transmit a plurality of second wireless signals in response to detecting the first wireless signal. The first wireless transceiver is configured to detect the plurality of second wireless signals. The processing circuit is communicably coupled to the first wireless transceiver. The processing circuit is configured to determine a position of the portion or the component of the lift assembly based on information acquired from the first wireless transceiver.

Abstract: Embodiments describe a method for moisturizing soil at an open construction site. The method includes determining current site characteristics of the open construction site; storing the current site characteristics in memory; determining a target volume of water for achieving a target soil moisture level based on the current site characteristics of the open construction site; calculating a target water application rate to achieve the target soil moisture level across the open construction site; determining a planned path across the open construction site; and guiding a water truck along the planned path while dispensing the target volume of water at the target application rate to achieve the target moisture level in the soil at the open construction site.

Abstract: A field planting system for planting seeds of at least two plant genotypes in a field includes a multi-variety planter operable to plant the seeds of the at least two plant genotypes in the field. The field planting system also includes a controller in operable communication with the multi-variety planter. The controller is configured to receive georeferenced field information for the field and plant information for the at least two plant genotypes, and generate a planting map for the field based on the georeferenced field information and the plant information, the planting map including a planting pattern for interplanting the seeds of the at least two plant genotypes. The controller is further configured to monitor a location of the multi-variety planter in the field, and control the multi-variety planter to plant the seeds of the at least two plant genotypes in the field according to the planting map.

Abstract: A system and method for adaptive calibration of a self-propelled work vehicle comprising a chassis and a blade front-mounted thereto for working a ground surface. First sensor signals correspond to a blade slope, and second sensor signals correspond to a chassis slope. During a first operating mode, a blade position is controlled relative to the chassis, based at least on a stored calibration value and a detected difference between the blade slope and a target slope of the ground surface, and a difference is also determined between the chassis slope and the target slope of the ground surface. During a second operating mode, the position of the blade is controlled relative to the chassis until the chassis slope corresponds to the target slope of the ground surface, and the stored calibration value is altered based on adjustments to the blade position during the second operating mode.

Abstract: A shovel includes a lower traveling body, an upper turning body turnably mounted on the lower traveling body, a cab mounted on the upper turning body, an attachment attached to the upper turning body, a hardware processor, and a display device. The hardware processor is configured to move the end attachment of the attachment relative to an intended work surface in response to a predetermined operation input related to the attachment. The display device is configured to display information on the hardness of the ground.

Abstract: A work implement's position is determined. Provided is a system including a work machine, the system comprising: a work machine body; a work implement attached to the work machine body; an imaging device that captures an image of the work implement; and a computer. The computer includes a trained position estimation model. The computer is programmed to obtain the image of the work implement captured by the imaging device and use the trained position estimation model to obtain a position of the work implement estimated from the captured image.

Abstract: A method of path planning for an autonomous vehicle to make a turn includes receiving a request for a turn of a vehicle from a current swath to a next swath in a work area. The work area has a headland at a periphery thereof, and the headland is characterized by a guidance line therethrough. The method further includes receiving information of the current swath, information of the next swath, and information of the guidance line, and determining a trajectory of the turn based on the information of the current swath, the information of the next swath, and the information of the guidance line. The trajectory includes one or more segments. At least a portion of a first segment of the one or more segments follows the guidance line in the headland. The method further includes, outputting the trajectory to a control system of the vehicle for executing the turn.

Abstract: A method for operating an implement assembly of a machine at a worksite is disclosed. The implement assembly is adapted to receive a load from a location, haul the load, and dump the load at a dump location. The method includes detecting, by a controller, a movement of the machine towards the location. Further, the method includes moving, by the controller, the implement assembly from a first state to a second state if at least one parameter associated with the machine relative to the location falls below a corresponding parameter threshold during the movement of the machine towards the location.

Abstract: Work machines, control systems for work machines, and methods of operating work machines are disclosed. A work machine includes a frame structure, a work implement, and a control system. The work implement is coupled to the frame structure and includes at least one ground engagement tool that is configured for movement in response to interaction with an underlying surface in use of the use work machine. The control system is coupled to the frame structure and includes a sensor mounted to the at least one ground engagement tool and a controller communicatively coupled to the sensor.

Abstract: A system controls a work machine that loads materials onto a conveyance vehicle. The system includes a controller. The controller performs a loading work by the work machine when the conveyance vehicle is stopped at a predetermined loading position. The controller acquires a loading amount onto the conveyance vehicle. The controller determines whether the loading work is finished based on the loading amount. The controller outputs a withdraw command to the conveyance vehicle to withdraw from the loading position upon determining that the loading work is finished. The controller determines whether the conveyance vehicle has withdrawn after outputting the withdraw command.

Abstract: A method for operating a driver assistance system for a motor vehicle driven in an at least partially automated manner includes learning a trajectory in a learning mode for driving the vehicle in a first automated manner along the trajectory. Subsequently, the vehicle is driven in the first automated manner along the learnt trajectory in an operating mode following the learning mode. While the vehicle is being driven along the trajectory in the operating mode, at least one transition from a private area to a public area is detected. Additional data, including current traffic data related to driving the vehicle in the public area, is acquired and provided for the driver assistance system. The motor vehicle is driven along the learnt trajectory in a second automated manner in the public area using the additional data.

Abstract: A system for detecting the levelness of ground engaging tools of a tillage implement including an agricultural implement including a frame and ground engaging tools supported relative to the frame. The system includes a first sensor and a second sensor configured to capture data indicative of a material flow past one or more first ground engaging tools and second ground engaging tools, respectively. The system includes a controller configured to monitor data received from the first sensor and the second sensor and compare one or more first monitored values and one or more second monitored values associated with the material flow past the first ground engaging tool(s) and the second ground engaging tool(s), respectively. The controller is further configured to identify that at least a portion of the ground engaging tools are not level when the first monitored value(s) differs from the second monitored value(s) by a predetermined threshold value.

Abstract: A method and arrangement for storing and recalling of setting values of a vehicle (10) and/or implement (14) that can be used for agricultural purposes comprising the following steps: inputting of at least one setting value for an actuator (49) of the vehicle (10) and/or implement (14) by a user interface; transmitting of a command based on the setting value to a control unit (32, 34, 38, 48) standing in operational connection with the actuator (49); and storing of setting data based on the setting value in a memory (72) in order to recall the setting value on the user interface or another user interface as required, wherein the setting value is converted into setting data using meta data regarding technical properties of the vehicle (10) and/or implement (14), the setting data representing a physical measure of the adjustment of the vehicle (10) and/or implement (14) achieved by the actuator (49) based on the setting value, the measure calculated based on the meta data and the setting value, and the setting

Abstract: A method includes receiving raw machine data; determining topographic attributes and underlying environmental characteristics; encoding the respective topographic attributes and the underlying environmental characteristics in hexagrid data structures; and storing the hexagrid data structures in a memory. A computing system includes a processor; and a memory storing instructions that, when executed by the one or more processors, cause the computing system to: receive raw machine data; determine topographic attributes and underlying environmental characteristics; encode the respective topographic attributes and the underlying environmental characteristics in hexagrid data structures; and store the hexagrid data structures in the memory.

Abstract: A method of maintaining vehicle formation includes receiving a desired cross track offset distance and a desired along track offset distance between a lead vehicle and a follower vehicle; receiving a current position, a current yaw rate, and a current speed of the lead vehicle; determining a current turn radius of the lead vehicle based on the current yaw rate and the current speed of the lead vehicle; determining a projected turn radius of the follower vehicle based on the current turn radius of the lead vehicle, the desired cross track offset distance, and the desired along track offset distance; determining a commanded curvature and a next speed of the follower vehicle based on a current position of the follower vehicle and the projected turn radius of the follower vehicle; and outputting the next speed and the commanded curvature to a control system of the follower vehicle.

Abstract: A processor is configured to set a monitoring region including at least a part of a movable region of a work device outside a vehicle, and a detection device is configured to detect information on the vicinity of the vehicle. Here, the processor is configured to, when it is determined that an obstacle has entered the monitoring region or it is predicted that an obstacle will enter the monitoring region based on a detection result of the detection device and when a work mode is not an emergency mode, control the work device such that the work device switches the work mode to the emergency mode.

Abstract: A method includes obtaining, by the treatment system configured to implement a machine learning (ML) algorithm, one or more images of a region of an agricultural environment near the treatment system, wherein the one or more images are captured from the region of a real-world where agricultural target objects are expected to be present, determining one or more parameters for use with the ML algorithm, wherein at least one of the one or more parameters is based on one or more ML models related to identification of an agricultural object, determining a real-world target in the one or more images using the ML algorithm, wherein the ML algorithm is at least partly implemented using the one or more processors of the treatment system, and applying a treatment to the target by selectively activating the treatment mechanism based on a result of the determining the target.

Abstract: Machine data is obtained indicating a number of times that a control rule is triggered on a mobile machine, along with an indication as to whether the control operation corresponding to the control rule was implemented and a performance result of that implementation. Effectiveness analyzer logic identifies an effectiveness of the control rule and machine learning logic generates a rating for the rule, based on its effectiveness. A rule modification engine is automatically controlled to make any control rule modifications, and a synchronization engine updates the modified control rules with control rules on the mobile machine.

Abstract: This application relates to a technical field of cargo transportation and provides a method for controlling an intelligent pallet. The method includes: acquiring current shelf location information and performing movement according to the current shelf location information; acquiring cargo information and retrieving preset path information; acquiring weight information of current cargo and retrieving inclination angle threshold information; acquiring actual inclination angle information, and modifying the preset path information to generate updating path information by comparing the actual inclination angle information with the inclination angle threshold information; associating the updating path information with the cargo information and the cargo weight information and replacing the preset path information with the updating path information; and performing movement according to the updating path information. This application has an effect of improving the efficiency of cargo transportation.

Abstract: A computer-implemented method of controlling a mobile agricultural machine includes receiving field map data representing a first agricultural operation performed on a field, receiving a location sensor signal indicative of a sensed geographic location of the mobile agricultural machine on the field, the mobile agricultural machine having a plurality of sections that are independently controllable to perform a second agricultural operation on the field that is different than the first agricultural operation, and generating a control signal to control the plurality of sections based on the field map data and the location sensor signal.

Abstract: A digital fence of a work area is generated and loaded into a machine control system that controls an off-road machine. The machine control system detects whether the off-road machine is within a threshold distance of the digital fence and automatically controls operating parameters of the off-road machine when the off-road machine is within a threshold distance of the digital fence.

Abstract: A priori georeferenced vegetative index data is obtained for a worksite, along with field data that is collected by a sensor on a work machine that is performing an operation at the worksite. A predictive model is generated, while the machine is performing the operation, based on the georeferenced vegetative index data and the field data. A model quality metric is generated for the predictive model and is used to determine whether the predictive model is a qualified predicative model. If so, a control system controls a subsystem of the work machine, using the qualified predictive model, and a position of the work machine, to perform the operation.

Abstract: The present disclosure relates to a remote control system for construction equipment, which includes a work apparatus operated according to operation information of a real joystick, that allows construction equipment to be remotely controlled using a mobile device, the remote control system including: a receiver, a virtual joystick interface, a haptic interface, and a transmitter.

Abstract: A work machine includes a work implement and a vehicle body including a first vehicle body portion, a mount attached to the first vehicle body portion, and a second vehicle body portion supported on the first vehicle body portion via the mount. A control system for the work machine includes a vehicle body positional sensor, a work implement positional sensor, and a controller. The vehicle body positional sensor is attached to the second vehicle body portion and outputs vehicle body position data indicative of a position of the second vehicle body portion. The work implement positional sensor is attached to the second vehicle body portion and outputs work implement position data indicative of a relative position of the work implement with respect to the second vehicle body portion. The controller calculates a position of the work implement based on the vehicle body position data and the work implement position data.

Abstract: The present disclosure relates to a method for real time monitoring of the current status of a construction site having one or more work machines, wherein a monitoring means installed at least one work machine monitors the environment of the work machine in real time and generates corresponding monitoring data, with the generated monitoring data being transmitted by the monitoring means to at least one processing unit for a real time evaluation of the current construction site status.

Abstract: Apparatuses, systems and methods associated with powered vehicles are disclosed herein. In examples, a system for controlling a vehicle may include sensors and a processor coupled to the sensors. The processor may identify one or more values received from the one or more sensors, wherein the one or more values are associated with one or more conditions of the vehicle and/or the vehicle's environment, and determine, based on the one or more values, a net resultant force vector of one or more forces acting on a center of mass of the vehicle. The processor may further determine a relationship between the net resultant force vector and a stability polygon that is superimposed at a base of the vehicle, and determine whether to limit one or more of a speed, rate of change, and/or travel amount for one or more of the operational systems controlled by the processor based on the relationship between the net resultant force vector and the stability polygon. Other examples may be described and/or claimed.

Abstract: A method for determining national crop yields during the growing season is provided. In an embodiment, a server computer system receives agricultural data records for a particular year that represent covariate data values related to plants at a specific geo-location at a specific time. The system aggregates the records to create geo-specific time series for a geo-location over a specified time. The system creates aggregated time series from a subset of the geo-specific time series. The system selects a representative feature from the aggregated time series and creates a covariate matrix for each specific geographic area in computer memory. The system determines a specific crop yield for a specific year using linear regression to calculate the specific crop yield from the covariate matrix. The system determines a forecasted crop yield for the specific year using a sum of the specific crop yields for the specific year, as adjusted.