公开(公告)号：US20230267385A1

公开(公告)日：2023-08-24

申请号：US17678440

申请日：2022-02-23

Applicant: Aquabyte, Inc.

Inventor： Bryton SHANG ,  Alok SAXENA

IPC: G06Q10/04 ,  G06N20/00

CPC classification number: G06Q10/04 ,  G06N20/00

Abstract: Computer-implemented techniques for forecasting growth of a set of aquatic organisms in an aquaculture environment using time-series models. The techniques can be used to predict the growth of a set of aquatic organisms in a fish farm enclosure in a period. In some variations, the techniques proceed by obtaining an evidentiary time series (e.g., daily biomass estimates produced by a biomass estimation system) and a set of one or more reference (covariant) time series (e.g., daily biomass estimates produced by a biological model of fish growth). The techniques construct a time-series model from the evidentiary time series and the set of reference time series. The techniques use the constructed time-series model to forecast the evidentiary time series. In some variations, the time-series model is a Bayesian structural time-series model or other state space model for time series data.

公开(公告)号：US20230267731A1

公开(公告)日：2023-08-24

申请号：US17678848

申请日：2022-02-23

Applicant: Aquabyte, Inc.

Inventor： Bryton SHANG ,  Alok SAXENA

IPC: G06V20/05 ,  G01N33/12 ,  G01S15/96 ,  G06V10/764 ,  G06T7/70

CPC classification number: G06V20/05 ,  G01N33/12 ,  G01S15/96 ,  G06T7/70 ,  G06V10/764 ,  G06T2207/10016 ,  G06T2207/30242 ,  G06V2201/07

Abstract: Computer-implemented techniques for multi-modal aquatic biomass estimation includes determining a fish mass measurement, a fish count, or a direct fish biomass estimate from a sample of one or more digital images or digital video captured by a digital camera immersed underwater in a fish farm enclosure. A technique further includes determining a plurality of fish densities for a plurality of water volumes within the fish farm enclosure based on analysis of signals received from a plurality of bias estimation sensors immersed underwater in the fish farm enclosure. The technique also includes computing a bias-adjusted fish mass measurement, fish count, or direct fish biomass estimate for the fish farm enclosure based on (i) the fish mass measurement, the fish count, or the direct fish biomass estimate determined from the sample of one or more digital images or digital video captured by the digital camera immersed underwater in the fish farm enclosure and (ii) the plurality of fish densities determined for the plurality of water volumes.