About

Nonoy Bandillo is an Assistant Professor in the Department of Crop and Soil Sciences at NC State University, located in Williams Hall. His research focuses on identifying and characterizing genes in small grains to improve food security and human health. He advances breeding tools for genetic innovation and develops elite cultivars tailored for North Carolina and surrounding states. His lab's work aims to enhance crop performance through genetic and genomic approaches, contributing to sustainable agriculture and crop improvement. In addition to his research, Professor Bandillo teaches courses such as Quantitative Genetics in Plant Breeding. He serves as an Associate Editor for The Plant Genome, reflecting his active engagement in the scientific community. His contributions include analyzing genetic diversity, salinity tolerance, and trait prediction in crops like soybean, dry pea, winter wheat, lentil, and field pea, utilizing advanced genomic, transcriptomic, and remote sensing technologies.

Research topics

• Biology
• Chromatography
• Food science
• Chemistry
• Biochemistry
• Biotechnology
• Evolutionary biology
• Chemical engineering
• Botany
• Agronomy
• Genetics
• Organic chemistry

Selected publications

• Genetic diversity analysis of North Dakota public soybean breeding program cultivars

  Scientific Reports · 2026-01-22

  articleOpen access

  Soybean [Glycine max (L.) Merr.] is a critical crop globally, valued for its protein and oil content. However, historical bottlenecks have constrained genetic diversity in soybean, particularly in high-latitude regions such as North Dakota, where environmental conditions necessitate maturity group (MG) 00 and 0 cultivars. This genetic diversity study examines the North Dakota State University (NDSU) soybean breeding program using pedigree, coefficient of parentage (CP), and SNP-based analyses. Pedigree tracing of 40 NDSU cultivars revealed a genetic base derived from 49 founders. CP analysis confirmed these findings, emphasizing dependence on limited germplasm, with the top ten founders accounting for over 70% of the genetic background and Mandarin (Ottawa) alone contributing 24%. SNP-based dendrograms and genetic relationship structures demonstrate the relationships among cultivars and founders. Notably, the specialty food grade natto cultivars formed a distinct cluster unrelated to commodity soybean. Population structure analyses emphasized the reliance on specific ancestral germplasm for breeding. This study underscores the need to diversify breeding materials to prevent genetic gain plateaus in MG 00 and 0 soybeans, thereby enhancing yield potential and adaptability in high-latitude regions.

  PublisherOA PDFDOI

• Enhancing yield and protein content estimation in dry peas through multispectral data integration and ensemble learning model

  The Plant Phenome Journal · 2025-08-15

  articleOpen access

  Abstract Accurately predicting yield and protein content in dry peas ( Pisum sativum L.) is essential for improving agricultural productivity, sustainability, and nutritional outcomes. Traditional methods for estimating these traits are labor‐intensive and limited in scope, while remote sensing technologies and machine learning offer scalable, nondestructive alternatives. This study addresses the challenge of integrating multispectral data and advanced machine learning models, specifically stacked meta‐models, to enhance prediction accuracy for yield and protein content in dry peas. Data were collected from 860 genotypes across two North Dakota locations over three growing seasons using uncrewed aerial system‐mounted multispectral sensors. The results revealed significant variability in yield and protein content due to location and year, with the meta‐model outperforming individual machine learning models for both traits. The meta‐model achieved a root mean squared error (RMSE) of 396.28 kg ha −1 and an coefficient of determination ( R 2 ) of 0.77 for yield, demonstrating strong predictive performance. However, protein content predictions were moderate, with an RMSE of 1.28% and an R 2 of 0.54, highlighting limitations in the correlation between spectral features and protein synthesis. Growth stage analysis emphasized the critical importance of the maturity stages to predict the yield and protein content in dry peas. These findings support the potential of integrating multispectral data and meta‐modeling for accurate agricultural predictions. Future research should focus on incorporating additional data sources, refining feature engineering techniques, and tailoring models to specific growth stages to further improve predictive accuracy. This study provides a foundation for advancing precision agriculture practices in pulse crops.

  PublisherOA PDFDOI

• Multispectral data and random forest model outperform deep learning in predicting lentil maturity using UAS imagery

  Journal of Agriculture and Food Research · 2025-07-25 · 2 citations

  articleOpen access

  Accurate prediction of lentil maturity is paramount in lentil breeding programs, influencing decisions on cultivar selection, disease management, and sustainable intensification of production. While previous research has emphasized combining spectral, structural, and textural metrics, this study aimed to streamline the maturity prediction process by investigating the independent predictive capabilities of narrow spectral bands. Additionally, our research evaluated various machine learning (random forest (RF), support vector machine (SVM), and eXtreme gradient boosting (XGBOOST)) and deep learning (U-shaped neural network (UNet) and pyramid scene parsing network (PSPN)) models, seeking optimal configurations tailored to distinctive RGB and multispectral datasets. Information was gathered across three distinct environments in North Dakota during the 2022 and 2023 cropping seasons. Maturity status was visually assessed at the plot level. RGB and multispectral aerial imagery datasets were acquired at different growth stages using two Uncrewed Aerial Systems (UASs): the DJI Matrice 300 and DJI Matrice 200. Image labelling and deep learning model training were conducted using the Image Analyst package in ArcGIS Pro 3.0.0, while the scikit-learn package in Python version 3.9.13 was used for training machine learning models. A hybrid approach involving the Monte Carlo technique and t-test was employed for hyperparameter tuning in both machine learning and deep learning models. The key findings of the study showed that (1) models trained on multispectral imagery consistently outperformed those using RGB, highlighting the advantage of spectral richness; (2) RF achieved the highest predictive performance, surpassing both other machine learning and deep learning models; (3) ensemble machine learning models (RF and XGBoost) demonstrated significantly lower computation times than deep learning models; and (4) the RF model trained on multispectral data maintained high accuracy (72–76 %) across different years and locations, underscoring its robustness and generalizability for maturity prediction. These results suggest that spectral-specific information, particularly from multispectral sensors, enhances predictive precision in high-throughput lentil phenotyping. • The multispectral data and Random Forest model yielded the highest accuracy and generalizability across diverse environments. • Ensemble machine learning models offer superior performance and efficiency over deep learning methods for maturity prediction. • Spectral features outperformed spatial resolution to estimate the maturity of Lentil.

  PublisherDOI

• Accurate plant height estimation in pulse crops through integration of LiDAR, multispectral information, and machine learning

  Remote Sensing Applications Society and Environment · 2025-01-01 · 3 citations

  article
  PublisherDOI

• Evaluating Sensor Fusion and Flight Parameters for Enhanced Plant Height Measurement in Dry Peas

  Sensors · 2025-04-12 · 2 citations

  articleOpen access

  Plant height is an important trait for evaluating plant lodging, drought, and stress. Standard measurement techniques are expensive, laborious, and error-prone. Although UAS-based sensors and digital aerial photogrammetry have been tested on plants with an erect growth habit, further study is needed in the application of these technologies to prostrate crops such as dry peas. This study has compared the performance of LiDAR, RGB, and multispectral sensors across different flight configurations (altitudes, speeds), and image overlaps over dry pea plots to identify the optimal setup for accurate plant height estimation. Data were assessed to determine the effect of sensor fusion on plant height accuracy using LiDAR's digital terrain model (DTM) as the base layer, and digital surface models (DSMs) generated from RGB and multispectral sensors. All sensors, particularly RGB, tended to underestimate plant height at higher flight altitudes. However, RMSE and MAE values showed no significant difference, indicating that higher flight altitudes can reduce data collection time and cost without sacrificing accuracy. Multispectral and LiDAR sensors were more sensitive to changes in flight speed than RGB sensors; However, RMSE and MAE values did not vary significantly across the tested speeds. Increased image overlap resulted in improved accuracy across all sensors. The Wilcoxon-Mann-Whitney test showed no significant difference between sensor fusion and individual sensors. Although LiDAR provided the highest accuracy of dry peas height estimation, it was not consistent across all canopy structures. Therefore, future research should focus on the integrating machine learning models with LiDAR to improve plant height estimation in dry peas.

  PublisherOA PDFDOI

• Improving estimation of days to maturity in field pea using RGB aerial imagery and machine learning

  The Plant Phenome Journal · 2025-09-18 · 1 citations

  articleOpen accessSenior author

  Abstract Accurately estimating days to maturity (DTM) is essential for assessing local adaptation and yield potential in field pea ( Pisum sativum L.) breeding programs. However, traditional manual scoring of DTM is labor‐intensive and inefficient for large‐scale, multi‐environment trials. To address this challenge, we developed a high‐throughput, low‐cost phenotyping framework using uncrewed aerial systems (UASs) equipped with red‐green‐blue cameras, implemented within the North Dakota State University Pulse Crop Breeding Program. This study aimed to (1) compare aerial and manual phenotyping for DTM estimation, (2) identify the optimal assessment time point, and (3) detect significant loci associated with DTM in a panel of 300 genetically diverse pea accessions. Image‐derived vegetation indices (VIs) collected 71 days after planting exhibited strong correlations with manually assessed DTM. Notably, vegetation indices demonstrated higher heritability ( H 2 = 0.91) compared to traditional DTM scores ( H 2 = 0.84). eXtreme Gradient Boosting models identified the visible atmospherically resistant index (31%), modified green‐red vegetation index (17%), and redness index (13%) as the most predictive VIs. Genome‐wide association mapping using these indices revealed three significant single nucleotide polymorphisms on chromosomes 3 and 5—variants not detected using traditional maturity data—highlighting the potential enhanced detection power of image‐derived traits. This work demonstrates the utility of low‐cost UAS platforms for scalable, non‐destructive maturity estimation and illustrates their potential to uncover genetic components of economically important traits, offering new avenues for addressing missing heritability in legume breeding.

  PublisherDOI

• Genome‐wide association study of seed mineral nutrients in peas ( <i>Pisum sativum</i> L.)

  The Plant Genome · 2025-10-12 · 1 citations

  articleOpen access

  Pea (Pisum sativum L.) is an important crop with high nutritional value and agricultural benefits. This study aimed to identify genetic factors that influence the levels of mineral elements (B, Ca, Cu, Fe, K, Mg, Mn, Na, P, S, Zn, Co, Mo, Ni, and Se) in pea seeds. A panel of 482 genetically variable pea accessions was grown in field trials for 3 years (2019-2021) and the seed mineral nutrients were analyzed. Individual accessions in the panel were genotyped using genotyping-by-sequencing, resulting in 79,608 high-quality single nucleotide polymorphisms after filtering. A genome-wide association study identified 113 SNPs significantly associated with mineral nutrient concentrations, explaining between 0.4% and 64.3% of the observed variation. Candidate genes linked to these SNPs were found to be involved in processes such as nutrient transport, metal binding, and stress responses, all of which affect mineral accumulation in seeds. The study also showed that genetic factors and environmental conditions interact to shape pea mineral concentration. Overall, genotype had a stronger effect on most mineral traits, particularly Mn and Na, while environmental effects were more prominent for elements like S and P. These findings offer valuable genetic tools for breeding programs aimed at improving pea nutritional quality, which can help address food insecurity and reduce malnutrition globally.

  PublisherDOI

• Optimizing integration techniques for UAS and satellite image data in precision agriculture — a review

  Frontiers in Remote Sensing · 2025-06-24 · 16 citations

  reviewOpen access

  The fusion of unmanned aerial system (UAS) and satellite imagery has emerged as a pivotal strategy in advancing precision agriculture. This review explores the significance of integrating high-resolution UAS and satellite imagery via pixel-based, feature-based, and decision-based fusion methods. The study investigates optimization techniques, spectral synergy, temporal strategies, and challenges in data fusion, presenting transformative insights such as enhanced biomass estimation through UAS-satellite synergy, improved nitrogen stress detection in maize, and refined crop type mapping using multi-temporal fusion. The combined spectral information from UAS and satellite sources confirms instrumental in crop monitoring and biomass estimation. Temporal optimization strategies consider factors such as crop phenology, spatial resolution, and budget constraints, offering effective and continuous monitoring solutions. The review systematically addresses challenges in spatial and temporal resolutions, radiometric calibration, data synchronization, and processing techniques, providing practical solutions. Integrated UAS and satellite data impact precision agriculture, contributing to improved resolution, monitoring capabilities, resource allocation, and crop performance evaluation. A comparative analysis underscores the superiority of combined data, particularly for specific crops and scenarios. Researchers exhibit a preference for pixel-based fusion methods, aligning fusion goals with specific needs. The findings contribute to the evolving landscape of precision agriculture, suggesting avenues for future research and reinforcing the field’s dynamism and relevance. Future works should delve into advanced fusion methodologies, incorporating machine learning algorithms, and conduct cross-crop application studies to broaden applicability and tailor insights for specific crops.

  PublisherOA PDFDOI

• Predicting lodging severity in dry peas using UAS-mounted RGB, LIDAR, and multispectral sensors

  Remote Sensing Applications Society and Environment · 2024-02-15 · 12 citations

  article
  PublisherDOI

• Identification of novel candidate genes for Ascochyta blight resistance in chickpea

  Scientific Reports · 2024-12-28 · 2 citations

  articleOpen accessSenior authorCorresponding

  Ascochyta blight, caused by the necrotrophic fungus Ascochyta rabiei, is a major threat to chickpea production worldwide. Resistance genes with broad-spectrum protection against virulent A. rabiei strains are required to secure chickpea yield in the US Northern Great Plains. Here, we performed a genome-wide association (GWA) study to discover novel sources of genetic variation for Ascochyta blight resistance using a worldwide germplasm collection of 219 chickpea lines. Ascochyta blight resistance was evaluated at 3, 9, 11, 13, and 14 days post-inoculation. Multiple GWA models revealed eight quantitative trait nucleotides (QTNs) across timepoints mapped to chromosomes 1, 3, 4, 6, and 7. Of these eight QTNs, only CM001767.1_28299946 on Chr 4 had previously been reported. QTN CM001766.1_36967269 on Chr 3 explained up to 33% of the variation in disease severity and was mapped to an exonic region of the pentatricopeptide repeat-containing protein At4g02750-like gene (LOC101506608). This QTN was confirmed across all models and timepoints. A total of 153 candidate genes, including genes with roles in pathogen recognition and signaling, cell wall biosynthesis, oxidative burst, and regulation of DNA transcription, were observed surrounding QTN-targeted regions. Further gene expression analysis on the QTNs identified in this study will provide insights into defense-related genes that can be further incorporated into breeding of new chickpea cultivars to minimize fungicide applications required for successful chickpea production in the US Northern Great Plains.

  PublisherOA PDFDOI

Frequent coauthors

• Edward S. Buckler

  Cornell University

  41 shared

• Hannah Worral

  North Dakota State University

  21 shared

• Lisa Piche

  North Dakota State University

  18 shared

• Sikiru Adeniyi Atanda

  North Dakota State University

  18 shared

• Mario Morales

  Dakota State University

  17 shared

• Paulo Flores

  Dakota State University

  15 shared

• Aaron J. Lorenz

  12 shared

• Ravi Valluru

  12 shared

Labs

• Crop and Soil SciencesPI

Education

• PhD Plant Breeding and Genetics, Department of Agronomy and Horticulture

  University of Nebraska-Lincoln

  2016