Enhancing genomic‐based forward prediction accuracy in wheat by integrating UAV‐derived hyperspectral and environmental data with machine learning under heat‐stressed environments

The Plant Genome, Год журнала: 2025, Номер 18(1)

Опубликована: Янв. 8, 2025

Abstract Integrating genomic, hyperspectral imaging (HSI), and environmental data enhances wheat yield predictions, with HSI providing detailed spectral insights for predicting complex grain (GY) traits. Incorporating single nucleotide polymorphic markers (SNPs) resulted in a substantial improvement predictive ability compared to the conventional genomic prediction models. Over course of several years, varied due diverse weather conditions. The most comprehensive parametric model tested, which included SNPs, HSI, covariates data, consistently achieved best results, closely followed by machine learning (ML) approaches when considering same omics data. For example, (M9), under forward cross‐validation scheme, predicted GY 2023 growing season using from 2021 2022 correlation between observed values 0.53. This demonstrated superior performance less models, emphasizing advantage integrating numerous sources their interactive effects. Furthermore, comparing top 25% lines versus corresponding highest GY, M9 returned coincide index (CI) 55% (i.e., both sets, were common), whereas performing ML (gradient boosting regression), CI was 46%. study highlights potential multi‐data source accelerate selection heat‐tolerant genotypes.

Язык: Английский

---

A survey of unmanned aerial vehicles and deep learning in precision agriculture

European Journal of Agronomy, Год журнала: 2024, Номер 164, С. 127477 - 127477

Опубликована: Дек. 17, 2024

Язык: Английский

---

Enhancing prediction accuracy of grain yield in wheat lines adapted to the southeastern United States through multivariate and multi‐environment genomic prediction models incorporating spectral and thermal information

The Plant Genome, Год журнала: 2024, Номер 18(1)

Опубликована: Ноя. 19, 2024

Abstract Enhancing predictive modeling accuracy in wheat ( Triticum aestivum ) breeding through the integration of high‐throughput phenotyping (HTP) data with genomic information is crucial for maximizing genetic gain. In this study, spanning four locations southeastern United States over 3 years, models to predict grain yield (GY) were investigated different cross‐validation approaches. The results demonstrate superiority multivariate comprehensive that incorporate both and HTP data, particularly accurately predicting GY across diverse years. These HTP‐incorporating achieve prediction accuracies ranging from 0.59 0.68, compared 0.40–0.54 genomic‐only when tested under scenarios years locations. exhibit superior generalization new environments highest trained on datasets. Predictive improves as multiple highlighting importance considering temporal dynamics study reveals outperformed methods lines percentage top 25% selected based was higher models, indicated by specificity, which proportion correctly identified top‐yielding matched observed performance sites Additionally, addresses untested other within same year at previously Findings show effectively extrapolate environments, their potential guiding strategies.

Язык: Английский

---

Advancing Crop Resilience Through High-Throughput Phenotyping for Crop Improvement in the Face of Climate Change

Plants, Год журнала: 2025, Номер 14(6), С. 907 - 907

Опубликована: Март 14, 2025

Climate change intensifies biotic and abiotic stresses, threatening global crop productivity. High-throughput phenotyping (HTP) technologies provide a non-destructive approach to monitor plant responses environmental offering new opportunities for both stress resilience breeding research. Innovations, such as hyperspectral imaging, unmanned aerial vehicles, machine learning, enhance our ability assess traits under various including drought, salinity, extreme temperatures, pest disease infestations. These tools facilitate the identification of stress-tolerant genotypes within large segregating populations, improving selection efficiency programs. HTP can also play vital role by accelerating genetic gain through precise trait evaluation hybridization enhancement. However, challenges data standardization, management, high costs equipment, complexity linking phenotypic observations improvements limit its broader application. Additionally, variability genotype-by-environment interactions complicate reliable selection. Despite these challenges, advancements in robotics, artificial intelligence, automation are precision scalability analyses. This review critically examines dual assessment tolerance performance, highlighting transformative potential existing limitations. By addressing key leveraging technological advancements, significantly research, discovery, parental selection, scheme optimization. While current methodologies still face constraints fully translating insights into practical applications, continuous innovation high-throughput holds promise revolutionizing ensuring sustainable agricultural production changing climate.

Язык: Английский

---

Metabolome selection for enhancing abiotic stress resilience: advances in phenomics, prospects and challenges for breeding applications

Plant Physiology Reports, Год журнала: 2025, Номер unknown

Опубликована: Май 26, 2025

Язык: Английский

---

Low density marker‐based effectiveness and efficiency of early‐generation genomic selection relative to phenotype‐based selection in dolichos bean (Lablab purpureus L. Sweet)

The Plant Genome, Год журнала: 2025, Номер 18(2)

Опубликована: Май 26, 2025

Abstract Genomic prediction has been demonstrated to be an efficient approach for the selection of candidates based on marker information in many crops. However, efforts understand efficiency genomic over phenotype‐based understudied crops such as dolichos bean ( Lablab purpureus L. Sweet) are limited. Our objectives were (i) explore effective density achieving high accuracy and (ii) assess effectiveness seed yield at early segregating generations bean. In this study, training population, which consisted F 5:6 recombinant inbreds, had a shared common parent with breeding 2 generation population. The populations genotyped newly synthesized simple sequence repeat‐based markers. was assessed by using varying number markers predictions 11 different models. Furthermore, comparing genetic gains progenies between genotypes selected predicted phenotypically genotypes. results indicate that low‐density evenly distributed throughout genome sufficient integration programs. proved two times more than phenotypic early‐generation beans. have significant impact adopting regular programs Dolichos beans low cost.

Язык: Английский

---

Artificial Intelligence-Assisted Breeding for Plant Disease Resistance

International Journal of Molecular Sciences, Год журнала: 2025, Номер 26(11), С. 5324 - 5324

Опубликована: Июнь 1, 2025

Harnessing state-of-the-art technologies to improve disease resistance is a critical objective in modern plant breeding. Artificial intelligence (AI), particularly deep learning and big model (large language large multi-modal model), has emerged as transformative tool enhance detection omics prediction science. This paper provides comprehensive review of AI-driven advancements detection, highlighting convolutional neural networks their linked methods through bibliometric analysis from recent research. We further discuss the groundbreaking potential models interpreting complex patterns via heterogeneous data. Additionally, we summarize how AI accelerates genomic phenomic selection by enabling high-throughput resistance-associated traits, explore AI’s role harmonizing multi-omics data predict disease-resistant phenotypes. Finally, propose some challenges future directions terms data, model, privacy facets. also provide our perspectives on integrating federated with for prediction. guide into breeding programs, facilitating translation computational advances crop

Язык: Английский

---

High Throughput Phenotyping Using Automated Imaging System Reveals the Relationship between Seed Yield and Agronomic Traits in Korean Rice Cultivars

Journal of Plant Physiology, Год журнала: 2025, Номер unknown, С. 154544 - 154544

Опубликована: Июнь 1, 2025

Язык: Английский

---

Univariate and multivariate genomic prediction for agronomic traits in durum wheat under two field conditions

PLoS ONE, Год журнала: 2024, Номер 19(11), С. e0310886 - e0310886

Опубликована: Ноя. 14, 2024

Genomic prediction (GP) has been evaluated in durum wheat breeding programs for several years, but accuracy (PA) remains insufficient some traits. Recently, multivariate (MV) analysis gained much attention due to its potential significantly improve PA. In this study, PA was agronomic traits using a univariate (UV) model wheat, subsequently, different genomic models were performed attempt increase The panel phenotyped 10 over two consecutive crop seasons and under field conditions: high nitrogen well-watered (HNW), low rainfed (LNR). Multivariate GP implemented cross-validation (CV) schemes: MV-CV1, testing the each target trait only markers, MV-CV2, additional phenotypic information. These MV-CVs applied analyses: modelling same both HNW LNR conditions, grain yield together with five most genetically correlated all higher than trait, except yellow index. Among traits, ranged from 0.34 (NDVI LNR) 0.74 (test weight HNW). LNR, MV-CV1 produced improvements up 12.45% compared model. By contrast, MV-CV2 increased 56.72% (thousand kernel LNR). scheme did not when it modelled whereas improved by ~18%. This study demonstrated that increases can be achieved conditions MV-CV2. addition, effectiveness of established

Язык: Английский

---

Using remotely sensed vegetation indices and multi-stream deep learning improves county-level corn yield predictions

European Journal of Agronomy, Год журнала: 2024, Номер 164, С. 127496 - 127496

Опубликована: Дек. 25, 2024

Язык: Английский

---