公开(公告)号：US20250156967A1

公开(公告)日：2025-05-15

申请号：US18940224

申请日：2024-11-07

Applicant: CLIMATE LLC

Inventor： Nathan BESTOR ,  Adrian CLARKE ,  Ryan COMPTON ,  Laura HESS ,  Chris HWANG ,  Shilpa SOOD ,  Joshua TOLLEFSON ,  Skylar TRIGUEIRO ,  Maria WOJAKOWSKI

IPC: G06Q50/02 ,  G06Q10/0635

Abstract: Systems and methods are provided for use in applying treatments to crops in fields. One example computer-implemented method includes determining a growth stage vector indicative of a growth stage of a crop in a field, using a GRU-based phenology model, based on a planting date of the crop and weather data for the field. The method also includes determining a disease risk for the crop in the field based on a disease risk model and the growth stage vector, determining a residual protection of the field for a prior treatment of the field, and determining whether application of the treatment is recommended for the field based on the disease risk and the determined residual protection. The method then includes, in response to determining that application of the treatment is recommended, identifying application intervals for the treatment based on the weather data for the application intervals.

公开(公告)号：US20240242121A1

公开(公告)日：2024-07-18

申请号：US18410962

申请日：2024-01-11

Applicant: CLIMATE LLC

Inventor： Juan Lopez ARRIAZA ,  Kelsey BLACKSTONE ,  Laura HESS ,  Hunter MERRILL ,  Maria WOJAKOWSKI

IPC: G06N20/00 ,  G06N5/022 ,  G06N7/01

CPC classification number: G06N20/00 ,  G06N5/022 ,  G06N7/01

Abstract: Systems and methods for predicting likelihoods of multiple crop disease types for target plots. An example computer-implemented method includes receiving a request for a crop disease prediction related to treatment of a target plot for one or more crop diseases and accessing a multiple disease joint model consistent with location data included in the request. The computer-implemented method also includes determining, via the multiple disease joint model, first and second disease likelihood output based on at least the location data, where the first and second disease likelihood outputs are each associated with a different one of the multiple disease types, and generating a treatment recommendation based on the first and second disease likelihood outputs. The computer-implemented method then includes directing application of at least one treatment to the target plot, based on the treatment recommendation output.