Next-Generation Crop Breeding: Harnessing Genomics, Phenomics and Machine Learning: A Review
Namita Singh *
Department of Genetics and Plant Breeding, College of Horticulture and Research Station Arjunda Balod, MGUVV- DURG, India.
Anup Aurojyoti Nayak
Department of Genetics and Plant Breeding, Palli Siksha Bhavana (Institute of Agriculture) Visva-Bharati, Sriniketan, West Bengal, India.
Mahiboobsa
Department of Genetics and Plant Breeding, College of Agricultural Sciences Iruvakki, KSNUAHS, Shivamogga, Karnataka, India.
Vikram Singh
Department of Biotechnology, Amrapali University, Haldwani, Uttarakhand, India.
Divya Patel
Department of Genetics and Plant Breeding, Raj Mohini Devi College of Agriculture and Research Station, Ambikapur (IGKV, Raipur Chhattisgarh), India.
Dilip Patidar
Department of Plantation, Spices, Medicinal and Aromatic Crops, Kerala Agricultural University, India.
Harsh Harilal Maru
Division of Genetics and Plant Breeding, Junagadh Agricultural University, India.
Budhayash Gautam
Section of Bioinformatics, College of Biotechnology, Sardar Vallabhbhai Patel University of Agriculture and Technology (SVPUAT), Meerut, U.P., India.
*Author to whom correspondence should be addressed.
Abstract
Global food security requires crop improvement strategies that can respond to population growth, climate variability and increasing constraints on agricultural resources. Conventional plant breeding has contributed substantially to crop productivity, yet long selection cycles and dependence on extensive field evaluation can limit the rate of genetic gain. This review synthesises advances in genomics, phenomics and machine learning for next-generation crop breeding, with emphasis on their combined contribution to selection accuracy and breeding efficiency. Key genomic approaches discussed include whole-genome sequencing, reference and pan-genome resources, genome-wide association studies, genomic selection and CRISPR-Cas-based genome editing. The review also examines high-throughput phenotyping platforms, including controlled-environment systems, ground-based robots, UAV-based remote sensing and root phenotyping tools. Machine learning approaches, ranging from random forest and support vector machines to convolutional neural networks, recurrent networks, transformers and explainable artificial intelligence, are considered in relation to genomic prediction, image analysis and breeding decision support. Multi-omics integration, data management, FAIR principles and an integrated genomics-phenomics-ML breeding pipeline are reviewed as enabling components for practical deployment. Crop-specific examples from wheat, rice, maize, soybean and legumes illustrate the potential and constraints of these technologies. The review further identifies key challenges, including phenotyping bottlenecks, genotype-environment interaction, data governance, model interpretability and regulatory uncertainty.
Keywords: Genomic selection, genome-wide association studies, high-throughput phenotyping, machine learning, deep learning, multi-omics integration, CRISPR-Cas systems, pan-genomics, digital breeding, crop improvement