From Pixels to Phenotypes: Quest of Machine Vision for Drought Tolerance Traits in Plants

Drought stress poses a significant threat to global agricultural productivity and food security. Understanding how plants adapt to drought conditions is crucial for developing drought-resistant crop varieties. Plants have been gifted with adaptation capacity to cope with situations arising from water deficit. Their capacity to acclimate is featured by adaptive changes in plants. The capacity to capture changes in shoot architecture has now been enhanced by the advent of non-invasive phenotyping techniques involving various imaging systems in plant phenomics platforms. These platforms thrive on the assumption that the plant responses reflected in terms of changes in the structure of the plant that can offer ample scope to employ machine vision for differentiating the responses of plants to soil-moisture deficit. Further, it is assumed that the detectable genetic variation in morphological traits responding to soil moisture deficit can provide hints about a plant’s tolerance to stress and can be exploited to improve crop productivity in drought-prone areas. Genomic interventions utilizing high throughput phenotyping, make the selection of drought-tolerant genotypes easier. In recent years, machine vision has emerged as a powerful tool to study and quantify plant responses to drought stress. This article reviews the current state of knowledge on drought-adaptive responses in plants and explores the potential of genomic-assisted breeding tools coupled with high-throughput phenotyping platforms and machine vision to accelerate the elucidation of genotypic differences in adaptive traits. We also highlighted its role in deciphering the complex interplay of genotypic variations in drought-adaptive traits and harnessing artificial intelligence (AI) for machine vision data processing for the transformative potential in enhancing our understanding of plant responses to drought and expediting the development of climate-resilient crop varieties.