What question did this study set out to answer?

The aim is to develop a UAV-based framework that accurately classifies the physiological maturity of dry beans using integrated spectral data and machine learning.

February 26, 2026Open Access

An integrated UAV-based spectral-index fusion framework using machine learning classifiers to model physiological maturity in dry bean

Key Points

The aim is to develop a UAV-based framework that accurately classifies the physiological maturity of dry beans using integrated spectral data and machine learning.
Evaluated 63 spectral feature sets and 10 machine learning classifiers.
Utilized a Support Vector Classifier paired with a combined feature set for high accuracy.
Collected multispectral imagery over three growing seasons across multiple genotypes.
Applied stratified five-fold cross-validation and statistical ranking to assess model performance.
Achieved >70% test accuracy using the Support Vector Classifier with Band_All6 + MCARI.
Class-wise recall rates for early, medium, and late maturity were 63.2%, 71.4%, and 79.4%, respectively.
Hybrid feature sets integrating chlorophyll-sensitive indices consistently outperformed index-only or band-only sets.

Abstract

• UAV spectral-index fusion classifies dry bean’s three maturity classes. • Evaluates 63 spectral feature sets and 10 ML classifiers for non-linear maturity. • Support Vector Classifier with BandAll6 + MCARI achieves > 70% test accuracy. • Hybrid BandAll6 + MCARI feature outperform band-only or index-only maturity inputs. • Composite-Friedman ranking reveals SVC as most robust model across feature sets. Accurate and scalable prediction of physiological maturity (PM) in leguminous crops remains a key challenge due to indeterminate growth and canopy heterogeneity. Thus, causing difficulties for optimizing breeding decisions and field management. This study develops a novel UAV-based multispectral-index fusion framework for high-throughput maturity classification in dry bean. This is conducted by combining parametric and non-parametric machine learning (ML) classification models to capture non-linear maturity signatures. Multispectral imagery was collected over three growing seasons across multiple genotypes. Six spectral bands and five maturity-relevant vegetation indices capturing chlorophyll degradation, senescence, and canopy greenness were evaluated through 63 feature-set combinations and 10 parametric and non-parametric ML classifiers. Model performance was assessed using stratified five-fold cross-validation, composite z-score aggregation, and Friedman-Nemenyi statistical ranking to jointly evaluate accuracy and consistency. Among all the model-feature combinations, the Support Vector Classifier (SVC) paired with BandAll6 + MCARI feature-set achieved the highest test accuracy (>70%), with class-wise recall of 63. 2%, 71. 4% and 79. 4% for early, medium and late maturity, respectively. Hybrid feature-sets integrating chlorophyll-sensitive indices with spectral bands consistently outperformed index-only or band-only sets, confirming the synergistic effect of bands and engineered index coupling. This research establishes a statistically validated pipeline linking UAV multispectral data, vegetation spectral-index and machine learning classification to quantify PM variability in dry bean with potential for validation in other legume crops. The proposed framework offers a generalizable approach for non-destructive maturity prediction, enabling breeders to accelerate genotype selection and harvest scheduling under field-scale conditions.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper