Predicting yellow mosaic disease severity in yardlong bean using visible imaging coupled with machine learning model

Abstract Accurate estimation of plant disease severity is pivotal for effective management and decision-making. Field experiments were conducted to understand the correlation and predict the yellow mosaic disease severity in yard-long beans using visible image indices. A total of 45 visible / Red Gr...

Full description

Saved in:
Bibliographic Details
Main Authors: Abhishek Kumar Dubey, Prakash Kumar Jha, Kumari Shubha, RN Singh, Manisha Tamta, Sonam Sah, Santosh Kumar, Sanjeev Kumar, Rakesh Kumar, Kirti Saurabh, Rajeev Kumar, Anup Das, P. V. V. Prasad, Arbind Kumar Choudhary
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-09176-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333297312694272
author Abhishek Kumar Dubey
Prakash Kumar Jha
Kumari Shubha
RN Singh
Manisha Tamta
Sonam Sah
Santosh Kumar
Sanjeev Kumar
Rakesh Kumar
Kirti Saurabh
Rajeev Kumar
Anup Das
P. V. V. Prasad
Arbind Kumar Choudhary
author_facet Abhishek Kumar Dubey
Prakash Kumar Jha
Kumari Shubha
RN Singh
Manisha Tamta
Sonam Sah
Santosh Kumar
Sanjeev Kumar
Rakesh Kumar
Kirti Saurabh
Rajeev Kumar
Anup Das
P. V. V. Prasad
Arbind Kumar Choudhary
author_sort Abhishek Kumar Dubey
collection DOAJ
description Abstract Accurate estimation of plant disease severity is pivotal for effective management and decision-making. Field experiments were conducted to understand the correlation and predict the yellow mosaic disease severity in yard-long beans using visible image indices. A total of 45 visible / Red Green Blue (RGB) indices were derived from the RGB images and correlated with disease severity, and also used as inputs for predicting disease severity using nine machine learning (ML) models. Out of 143 genotypes screened based on final disease severity 3, 18, 18, 17, 34 and 53 genotypes were grouped in immune, resistant, moderately resistant, moderately susceptible, susceptible and highly susceptible categories, respectively. Model performances was evaluated using R2, d-index, mean bias error, and normalized Root Mean Square Error (n-RMSE) metrics. Results revealed that 34 indices exhibited significant correlations (p < 0.01) with YMD severity, with 23 positively and 12 negatively correlated. Among these, Red Color Composite (RCC) and Excessive red (ExR) demonstrated the highest and equal positive correlations (0.87), while Green red difference (GRD) exhibited the largest negative correlation (-0.88) with disease severity. The ML models achieved commendable performance, attaining R2 and d-index values exceeding 0.92 and 0.98, respectively, in calibration, and 0.88 and 0.96 in validation, underscoring their effectiveness in predicting YMD severity using RGB images only. Random Forest (RF), Cubist, XGBoost (XGB), K-Nearest Neighbors (KNN), and Gradient Boosting Machine (GBM) emerged as the five top-performing models for predicting YMD severity using visible indices in yard-long beans. These findings hold practical implications for timely disease management strategies, expediting breeding programs, and aiding policy planners and farmers in making well-informed decisions.
format Article
id doaj-art-6a07701bba854ff5b5d8ffaf04ee08f7
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-6a07701bba854ff5b5d8ffaf04ee08f72025-08-20T03:45:55ZengNature PortfolioScientific Reports2045-23222025-07-0115111310.1038/s41598-025-09176-8Predicting yellow mosaic disease severity in yardlong bean using visible imaging coupled with machine learning modelAbhishek Kumar Dubey0Prakash Kumar Jha1Kumari Shubha2RN Singh3Manisha Tamta4Sonam Sah5Santosh Kumar6Sanjeev Kumar7Rakesh Kumar8Kirti Saurabh9Rajeev Kumar10Anup Das11P. V. V. Prasad12Arbind Kumar Choudhary13ICAR-Research Complex for Eastern RegionMississippi State UniversityICAR-Research Complex for Eastern RegionICAR-National Institute of Abiotic Stress ManagementICAR-Research Complex for Eastern RegionICAR-National Institute of Abiotic Stress ManagementICAR-Research Complex for Eastern RegionICAR-Research Complex for Eastern RegionICAR-Research Complex for Eastern RegionICAR-Research Complex for Eastern RegionICAR-Indian Institute of Sugarcane ResearchICAR-Research Complex for Eastern RegionKansas State UniversityICAR-Research Complex for Eastern RegionAbstract Accurate estimation of plant disease severity is pivotal for effective management and decision-making. Field experiments were conducted to understand the correlation and predict the yellow mosaic disease severity in yard-long beans using visible image indices. A total of 45 visible / Red Green Blue (RGB) indices were derived from the RGB images and correlated with disease severity, and also used as inputs for predicting disease severity using nine machine learning (ML) models. Out of 143 genotypes screened based on final disease severity 3, 18, 18, 17, 34 and 53 genotypes were grouped in immune, resistant, moderately resistant, moderately susceptible, susceptible and highly susceptible categories, respectively. Model performances was evaluated using R2, d-index, mean bias error, and normalized Root Mean Square Error (n-RMSE) metrics. Results revealed that 34 indices exhibited significant correlations (p < 0.01) with YMD severity, with 23 positively and 12 negatively correlated. Among these, Red Color Composite (RCC) and Excessive red (ExR) demonstrated the highest and equal positive correlations (0.87), while Green red difference (GRD) exhibited the largest negative correlation (-0.88) with disease severity. The ML models achieved commendable performance, attaining R2 and d-index values exceeding 0.92 and 0.98, respectively, in calibration, and 0.88 and 0.96 in validation, underscoring their effectiveness in predicting YMD severity using RGB images only. Random Forest (RF), Cubist, XGBoost (XGB), K-Nearest Neighbors (KNN), and Gradient Boosting Machine (GBM) emerged as the five top-performing models for predicting YMD severity using visible indices in yard-long beans. These findings hold practical implications for timely disease management strategies, expediting breeding programs, and aiding policy planners and farmers in making well-informed decisions.https://doi.org/10.1038/s41598-025-09176-8CowpeaCubistXGBsRPIRGB indicesCorrelation
spellingShingle Abhishek Kumar Dubey
Prakash Kumar Jha
Kumari Shubha
RN Singh
Manisha Tamta
Sonam Sah
Santosh Kumar
Sanjeev Kumar
Rakesh Kumar
Kirti Saurabh
Rajeev Kumar
Anup Das
P. V. V. Prasad
Arbind Kumar Choudhary
Predicting yellow mosaic disease severity in yardlong bean using visible imaging coupled with machine learning model
Scientific Reports
Cowpea
Cubist
XGB
sRPI
RGB indices
Correlation
title Predicting yellow mosaic disease severity in yardlong bean using visible imaging coupled with machine learning model
title_full Predicting yellow mosaic disease severity in yardlong bean using visible imaging coupled with machine learning model
title_fullStr Predicting yellow mosaic disease severity in yardlong bean using visible imaging coupled with machine learning model
title_full_unstemmed Predicting yellow mosaic disease severity in yardlong bean using visible imaging coupled with machine learning model
title_short Predicting yellow mosaic disease severity in yardlong bean using visible imaging coupled with machine learning model
title_sort predicting yellow mosaic disease severity in yardlong bean using visible imaging coupled with machine learning model
topic Cowpea
Cubist
XGB
sRPI
RGB indices
Correlation
url https://doi.org/10.1038/s41598-025-09176-8
work_keys_str_mv AT abhishekkumardubey predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT prakashkumarjha predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT kumarishubha predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT rnsingh predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT manishatamta predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT sonamsah predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT santoshkumar predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT sanjeevkumar predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT rakeshkumar predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT kirtisaurabh predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT rajeevkumar predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT anupdas predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT pvvprasad predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel
AT arbindkumarchoudhary predictingyellowmosaicdiseaseseverityinyardlongbeanusingvisibleimagingcoupledwithmachinelearningmodel