Methods and systems for crop pest management utilizing geospatial images and microclimate data

1. A system comprising a hardware processor and a non-transitory storage medium for storing program code, the program code executable by the hardware processor to execute a process for predicting a pest susceptibility, the program code when executed by the hardware processor causing the hardware processor to execute steps to:

receive geospatial image data of a crop field from one or more sensors, wherein the geospatial image data of the crop field is geocoded by longitude and latitude coordinates;

receive microclimate data of the crop field, wherein the microclimate data comprises locally variable environmental conditions in one or more portions of the crop field;

receive one or more crop field parameters, wherein the one or more crop field parameters comprise a degree of canopy closure of the crop field, and wherein the degree of canopy closure is estimated from the geospatial image data;

determine a crop vigor map for the crop field from the geospatial image data, wherein the crop vigor map comprises a crop vigor index on the one or more portions of the crop field, and wherein the crop vigor index is a numerical index based on a foliage volume, density, layout, or health status of the crop in the crop field; and

generate a pest susceptibility map utilizing a risk model based on the crop vigor map and the microclimate data, wherein the pest susceptibility map comprises a pest susceptibility index geocoded by latitude and longitude coordinates, wherein the pest susceptibility index is a measure of a susceptibility of a crop in the crop field to one or more crop pests, and wherein the one or more crop field parameters are used in combination with the crop vigor map in the risk model to predict the pest susceptibility.

2. The system of claim 1 , wherein the determining the crop vigor map for the crop field comprises calculating the crop vigor index from one or more crop vigor indicator equations using the geospatial image data as input.

3. The system of claim 1 , wherein the determining the crop vigor map for the crop field utilizes a first machine vision algorithm executable by the hardware processor.

4. The system of claim 3 , wherein the machine vision algorithm comprises one or more deep learning neural networks, and

wherein the deep learning neural networks are trained on ground truth data comprising geospatial image data of one or more sample crop fields and one or more crop vigor maps for the one or more sample crop fields.

5. The system of claim 1 , wherein the one or more crop field parameters are determined from the geospatial image data utilizing a machine vision algorithm executable by the hardware processor.

6. The system of claim 1 , wherein the one or more crop field parameters are machine data received from agricultural equipment.

7. The system of claim 1 , wherein the one or more crop field parameters comprise crop row spacing of the crop field, and wherein the crop row spacing is estimated from the geospatial image data using a third machine vision algorithm or received from machine data from one or more agricultural equipment.

8. The system of claim 1 , wherein the one or more crop field parameters comprise an irrigation status of the crop field, wherein the irrigation status is estimated using geospatial image data or received from machine data from one or more irrigation equipment.

9. The system of claim 1 , wherein the one or more crop field parameters comprise a crop stage of the crop field, and wherein the crop stage is determined from physical observation or one or more crop models.

10. The system of claim 1 , wherein the risk model is a machine learning algorithm executable by the hardware processor, and

wherein the machine learning algorithm is trained on ground truth data comprising one or more sample pest data points and one or more sample crop vigor maps for one or more sample crop fields.

11. The system of claim 10 , wherein the machine learning algorithm comprises one or more of a linear regressor, a nonlinear regressor, a random forest algorithm, and a neural network.

12. The system of claim 1 , wherein the crop pest is selected from the group consisting of crop diseases, insects, weeds, and plant pathogens.

13. The system of claim 1 , wherein the geospatial image data is selected from the group consisting of aerial imagery, satellite imagery, and unmanned aircraft system (UAS) imagery, and

wherein the one or more sensors are infrared cameras.

14. The system of claim 1 , wherein the one or more sensors are located on a machine selected from the group consisting of an unmanned aerial vehicle (UAV), an unmanned aircraft system (UAS), an aircraft, a satellite, and a field equipment.

15. The system of claim 1 , wherein the microclimate data comprises a microclimate map, and

wherein the microclimate map is generated from the group consisting of one or more in-field measurements, one or more aerial measurements, one or more satellite measurements, one or more drone measurements, and one or more microclimate models.

16. The system of claim 1 , further comprising program code to:

generate a treatment plan based on the pest susceptibility map,

wherein the treatment plan comprises an agricultural management technique, comprising application of one or more agricultural chemicals, to prevent outbreak or control propagation of one or more crop pests.

17. The system of claim 1 , further comprising program code to:

receive price information for a crop growing in the crop field, a cost information for one or more agricultural management techniques, and an anticipated efficacy for the one or more agricultural management techniques; and

generate an anticipated return on investment (ROI) based on the price and cost information and the anticipated efficacy.

18. A computer-implemented method for predicting a pest susceptibility, the computer-implemented method executable by a hardware processor, the method comprising:

receiving geospatial image data of a crop field from one or more sensors, wherein the geospatial image data of the crop field is geocoded by longitude and latitude coordinates;

receiving microclimate data of the crop field, wherein the microclimate data comprises locally variable environmental conditions in one or more portions of the crop field;

receiving one or more crop field parameters, wherein the one or more crop field parameters comprise a degree of canopy closure of the crop field, and wherein the degree of canopy closure is estimated from the geospatial image data;

determining a crop vigor map for the crop field from the geospatial image data, wherein the crop vigor map comprises a crop vigor index on the one or more portions of the crop field, and wherein the crop vigor index is a numerical index based on a foliage volume, density, layout, or health status of the crop in the crop field; and

generating a pest susceptibility map utilizing a risk model based on the crop vigor map and the microclimate data, wherein the pest susceptibility map comprises a pest susceptibility index geocoded by latitude and longitude coordinates, wherein the pest susceptibility index is a measure of a susceptibility of a crop in the crop field to one or more crop pests, and wherein the one or more crop field parameters are used in combination with the crop vigor map in the risk model to predict the pest susceptibility.