Predictive weed map and material application machine control

Patent metadata

Field	Value
Publication number	US-12329148-B2
Application number	US-202217716350-A
Country	US
Kind code	B2
Filing date	Apr 8, 2022
Priority date	Feb 6, 2020
Publication date	Jun 17, 2025
Grant date	Jun 17, 2025

Abstract

A predictive map is obtained by an agricultural material application system. The predictive map maps predictive weed values at different geographic locations in a field. A geographic position sensor detects a geographic locations of an agricultural material application machine at the field. A control system generates a control signal to control the agricultural material application machine based on the geographic locations of the agricultural material application machine and the predictive map.

First claim

What is claimed is:

1. An agricultural material application system comprising:
a geographic position sensor configured to detect a geographic location of a mobile material application machine at a field and generates a sensor signal indicating the geographic location;
an in-situ sensor configured to detect a weed value corresponding to the geographic location; and
a control system configured to:
receive a vegetative index map that maps vegetative index values corresponding to different geographic locations in the field;
generate a predictive weed model indicative of a relationship between the vegetative index values and weed values based on the weed value detected by the in-situ sensor corresponding to the geographic location and a vegetative index value in the vegetative index map corresponding to the geographic location, the predictive weed model being configured to receive a vegetative index value as a model input and generate a predictive weed value as a model output;
generate a functional predictive weed map of the field that maps predictive weed values to the different geographic locations in the field based on the vegetative index values in the vegetative index map and based on the predictive weed model; and
control an actuator of the mobile material application machine at the field based on the sensor signal indicating the geographic location and the functional predictive weed map.

2. The agricultural material application system of claim 1 , wherein the weed value is indicative of one or more of weed presence, weed type, weed size, and weed intensity.

3. The agricultural material application system of claim 1 , wherein the vegetative index map comprises an optical map that maps, as the vegetative index values, optical characteristic values to the different geographic locations in the field;
wherein the predictive weed model models a relationship between the optical characteristic values and the weed values based on the weed value detected by the in-situ sensor corresponding to the geographic location and an optical characteristic value in the optical map at the geographic location to which the weed value corresponds, the predictive weed model being configured to receive an optical characteristic value as a model input and generate a predictive weed value as a model output; and
wherein the functional predictive weed map maps the predictive weed values to the different geographic locations in the field based on the optical characteristic values in the vegetative index map and based on the predictive weed model.

4. The agricultural material application system of claim 1 , wherein the control system is configured to:
receive an information map that maps values of a characteristic to the different geographic locations in the field;
wherein the predictive weed model is further indicative of a relationship between the values of the characteristic and weed values based on the weed value detected by the in-situ sensor corresponding to the geographic location and values of the characteristic in the information map corresponding to the geographic location; and
wherein the functional predictive weed map maps the predictive weed values to the different geographic locations in the field based further on the values of the characteristic in the information map and the predictive weed model.

5. The agricultural material application system of claim 4 , wherein the actuator comprises a material application actuator, and the control system is configured to control the material application actuator to increase an amount of material applied by the mobile material application machine based on the functional predictive weed map.

6. The agricultural material application system of claim 4 , wherein the actuator comprises a material application actuator, and the control system is configured to control the material application actuator to decrease an amount of material applied by the mobile material application machine based on the functional predictive weed map.

7. The agricultural material application system of claim 4 , wherein the actuator comprises a material application actuator, and the control system is configured to control the material application actuator to deactivate or activate a component of the mobile material application machine based on the functional predictive weed map.

8. A method of controlling a mobile agricultural material application machine, the method comprising:
detecting a geographic location of the mobile agricultural material application machine at a field;
obtaining in-situ sensor data indicative of a weed value corresponding to the geographic location;
receiving a vegetative index map that maps vegetative index values corresponding to different geographic locations in the field;
generating a predictive weed model indicative of a relationship between the vegetative index values and weed values based on the weed value corresponding to the geographic location and a vegetative index value in the vegetative index map corresponding to the geographic location;
generating a functional predictive weed map of the field that maps predictive weed values to the different geographic locations in the field based on the vegetative index values in the vegetative index map and based on the predictive weed model; and
controlling an actuator of the mobile agricultural material application machine at the field based on the geographic location of the mobile agricultural material application machine and the functional predictive weed map.

9. The method of claim 8 , wherein the actuator comprises a material application actuator.

10. The method of claim 9 , wherein controlling the material application actuator comprises controlling the material application actuator of the mobile agricultural material application machine to adjust a rate at which material is applied to the field based on the geographic location of the mobile agricultural material application machine and the functional predictive weed map.

11. The method of claim 9 , wherein controlling the material application actuator comprises controlling the material application actuator of the mobile agricultural material application machine to activate or deactivate a component of the mobile agricultural material application machine based on the geographic location of the mobile agricultural material application machine and the functional predictive weed map.

12. A mobile agricultural material application machine, comprising:
a geographic position sensor configured to detect a geographic location of the mobile agricultural material application machine at a field;
an in-situ sensor configured to detect a weed value corresponding to the geographic location; and
a control system configured to:
receive two or more information maps, each information map, of the two or more information maps, mapping values of a respective characteristic to different geographic locations in the field;
generate a predictive weed model indicative of a relationship between the values of the respective characteristics in the two or more information maps and weed values based on the weed value detected by the in-situ sensor corresponding to the geographic location and the values of the respective characteristics in the two or more information maps corresponding to the geographic location, the predictive weed model being configured to receive a value of each respective characteristic as a model input and generate a predictive weed value as a model output;
generate a functional predictive weed map of the field that maps predictive weed values to the different geographic locations in the field based on the values of the respective characteristics in

Assignees

• Deere & Co

Inventors

• Vandike Nathan R
• Palla Bhanu Kiran Reddy
• Pardina-Malbran Federico
• Hanson David A
• Agarwal Andrea M
• Anderson Noel W

Classifications

• A01C7/0445

  Seed ejectors · CPC title

• A01C7/0443

  Seed singulators · CPC title

• A01C7/046

  with perforated seeding discs · CPC title

• A01M9/0092

  Regulating or controlling systems (the delivery being related to the movement of a vehicle B05B9/06) · CPC title

• A01C7/105

  Seed sensors · CPC title