US 2026/0245362 A1Published application

Method and system to estimate severity and causality for plant anomalies in a controlled environment

AssigneeTata Consultancy Services Limited

InventorsSwagatam BOSE CHOUDHURY, Sanat SARANGI, Dineshkumar Jang Bahadur SINGH, Srinivasu PAPPULA

Life of this patent

Estimating the term…

Loading patent…

Abstract

The embodiments of the present disclosure address unresolved problems of precise and scalable anomaly detection, root cause analysis, anomaly severity estimation, and trend analysis for plants within controlled environments. Embodiments herein provide a method and system for estimating severity and causality for plant development anomalies in plants in a controlled environment. The system uses RGB image based analysis to identify subtle, similar looking growth anomalies and timely corrective actions. System estimates anomaly severity by analyzing real-time data and dynamically generated synthetic baseline plant data for non-linear severity growth for plant anomalies. The system performs root cause analysis with prioritized rankings, severity zone mapping, severity trend estimation, and tailored role-specific insights to enable effective decision-making and targeted interventions in plant farming environments. Finally, the system identifies and ranks potential root causes of plant-specific stress symptoms along with providing a final zone, bench and rack health index and overall health status.

Claims20

Dependent claims

A processor-implemented method comprising:

receiving, via an Input/Output (I/O) interface, a plurality of images of one or more plants in a controlled environment as input;
pre-processing, via the one or more hardware processors, the received plurality of images using a predefined deep learning technique to perform data homogenization and structural isolation followed by a pseudo-spectral signal extraction and waveform transformation to identify deviations indicative of phenotypic anomalies;
analyzing, via one or more hardware processors, the pre-processed plurality of images using an anomaly detector to identify one or more anomalies in each of the one or more plants, wherein the identified one or more anomalies in each of the one or more plants are consumed by an Anomaly Layering Detection Index (ALDI) generator module to provide an index based on localization and layering of the one or more anomalies in each of the one or more plants;
estimating, via the one or more hardware processors, severity of each of the one or more anomalies in the one or more plants from values of the index using an anomaly severity estimator, wherein a severity percentage is estimated using a predefined synthetic severity generation module;
combining, via the one or more hardware processors, the estimated severity for each of the one or more anomalies using an integrated severity score generator to get a final severity score for the one or more identified one or more anomalies, wherein an overall severity percentage is determined for a bench;
analyzing, via the one or more hardware processors, the identified one or more anomalies and the overall severity percentage to determine a potential root cause and a possibility ranking of causal factors via a predefined Root Cause Analysis and Ranking (RCAR) module;
calculating, via the one or more hardware processors, a Zone Health Index (ZHI), Bench Health Index (BHI), Rack Health Index (RHI), and a severity trend to analyze progress of the severities over time using a predefined deep learning model, wherein temporal and environmental features are combined for predicting the severity trend for each of the one or more plants in the controlled environment;
and
generating, via the one or more hardware processors, a persona based comprehensive recommendation of final health index (FHI) based on the calculated ZHI, BHI, RHI, and a severity trend for improving plant health using a predefined large language model (LLM) based advisor module.

6 more elements

A system comprising:

a memory storing instructions;
one or more Input/Output (I/O) interfaces;
and
one or more hardware processors coupled to the memory via the one or more I/O interfaces, wherein the one or more hardware processors are configured by the instructions to:
receive, via an Input/Output (I/O) interface, a plurality of images of one or more plants in a controlled environment as input;
pre-process the received plurality of images using a predefined deep learning technique to perform data homogenization and structural isolation followed by a pseudo-spectral signal extraction and waveform transformation to identify deviations indicative of phenotypic anomalies;
analyze the pre-processed plurality of images using an anomaly detector to identify one or more anomalies in each of the one or more plants, wherein the identified one or more anomalies in each of the one or more plants are consumed by an Anomaly Layering Detection Index (ALDI) generator module to provide an index based on localization and layering of the one or more anomalies in each of the one or more plants;
estimate severity of each of the one or more anomalies in the one or more plants from values of the index using an anomaly severity estimator, wherein a severity percentage is estimated using a predefined synthetic severity generation module;
combine the estimated severity for each of the one or more anomalies using an integrated severity score generation to get a final severity score for the one or more identified one or more anomalies, wherein an overall severity percentage is determined for a bench;
analyze the identified one or more anomalies and the overall severity percentage to determine a potential root cause and a possibility ranking of causal factors via a predefined Root Cause Analysis and Ranking (RCAR) module;
calculate a Zone Health Index (ZHI), Bench Health Index (BHI), Rack Health Index (RHI), and a severity trend to analyze progress of the severities over time using a predefined deep learning model, wherein temporal and environmental features are combined for predicting the severity trend for each of the one or more plants in the controlled environment;
generate a persona based comprehensive recommendation of final health index (FHI) based on the calculated ZHI, BHI, RHI, and a severity trend for improving plant health using a predefined large language model (LLM) based advisor module.

9 more elements

One or non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause:

receiving via an Input/Output (I/O) interface, a plurality of images of one or more plants in a controlled environment as input;
pre-processing the received plurality of images using a predefined deep learning technique to perform data homogenization and structural isolation followed by a pseudo-spectral signal extraction and waveform transformation to identify deviations indicative of phenotypic anomalies;
analyzing the pre-processed plurality of images using an anomaly detector to identify one or more anomalies in each of the one or more plants, wherein the identified one or more anomalies in each of the one or more plants are consumed by an Anomaly Layering Detection Index (ALDI) generator module to provide an index based on localization and layering of the one or more anomalies in each of the one or more plants;
estimating severity of each of the one or more anomalies in the one or more plants from values of the index using an anomaly severity estimator, wherein a severity percentage is estimated using a predefined synthetic severity generation module;
combining the estimated severity for each of the one or more anomalies using an integrated severity score generation to get a final severity score for the one or more identified one or more anomalies, wherein an overall severity percentage is determined for a bench;
analyzing the identified one or more anomalies and the overall severity percentage to determine a potential root cause and a possibility ranking of causal factors via a predefined Root Cause Analysis and Ranking (RCAR) module;
calculating a Zone Health Index (ZHI), Bench Health Index (BHI), Rack Health Index (RHI), and a severity trend to analyze progress of the severities over time using a predefined deep learning model, wherein temporal and environmental features are combined for predicting the severity trend for each of the one or more plants in the controlled environment;
generating a persona based comprehensive recommendation of final health index (FHI) based on the calculated ZHI, BHI, RHI, and a severity trend for improving plant health using a predefined large language model (LLM) based advisor module.

5 more elements

Dependencies are inferred from the claim text.