Best Researcher Award
Puranjit Singh — University of Delaware, United States
Puranjit Singh is a researcher in plant and soil sciences at the University of Delaware whose work combines computer vision, machine learning, deep learning, remote sensing, and precision agriculture. His research addresses automated plant and vegetation assessment, weed detection, crop phenotyping, and data-driven agricultural decision-making. His publicly documented research profile identifies six publications and emphasizes digital agriculture and computational approaches to agricultural problems. [1] [2]
Abstract
Puranjit Singh’s research is situated at the intersection of plant science, precision agriculture, computer vision, and artificial intelligence. His work includes semantic segmentation for weed detection, UAV-based vegetation assessment, smartphone-based blueberry detection and yield estimation, and computational approaches to plant phenotyping. These studies demonstrate the application of image-based and machine-learning methods to agricultural monitoring and decision support. [2] [3]
Keywords
Precision phenotyping; plant science; computer vision; deep learning; machine learning; remote sensing; semantic segmentation; UAV imaging; precision agriculture; weed detection; crop monitoring; digital agriculture.
Introduction
Precision agriculture increasingly uses imaging, machine learning, and remote sensing to measure plant traits and agricultural conditions. Singh’s research contributes to this direction by applying computational vision methods to vegetation classification, weed detection, and crop yield estimation. His work links plant science with scalable digital tools designed for objective agricultural monitoring and management. [2]
Research Profile
Singh’s research profile centers on digital agriculture, with particular emphasis on computer vision, deep learning, remote sensing, precision agriculture, and machine learning. His University of Delaware work is associated with plant and soil sciences and computational phenotyping. The research combines field imagery and artificial intelligence to characterize vegetation, crops, and weeds through automated analytical workflows. [1] [2]
Research Contributions
Singh has contributed to computer-vision methods for semantic segmentation, UAV-based vegetation assessment, and automated crop measurement. His research includes lightweight deep-learning approaches for real-time weed detection and smartphone-based blueberry detection and yield estimation. These contributions support more efficient image interpretation and demonstrate practical pathways for integrating artificial intelligence into precision agricultural systems. [2] [3]
Publications
The documented publication record includes journal articles, a conference paper, and a master’s thesis. Representative works address site-specific weed management, vegetation composition assessment, blueberry detection and yield estimation, and semantic segmentation. The record also includes collaborative research on real-time weed detection using lightweight convolutional neural networks and computer vision approaches for ecological and agricultural applications. [2]
Research Impact
The impact of Singh’s research is reflected in its practical focus on automated agricultural observation and decision support. His studies address scalable approaches to weed identification, vegetation assessment, and crop yield estimation, while collaborative work explores deployment of machine-learning models on resource-constrained devices. Such research supports the broader development of data-driven and technology-enabled plant production systems. [3]
Award Suitability
Singh’s research profile is relevant to recognition in plant science because it applies computational methods to measurable plant and vegetation characteristics. His documented work spans precision phenotyping, computer vision, remote sensing, and agricultural artificial intelligence. The combination of interdisciplinary methods and plant-focused applications provides a scholarly basis for consideration within an international plant science award framework. [1]
Conclusion
Puranjit Singh represents an interdisciplinary research profile connecting plant science with artificial intelligence and precision agriculture. His publications demonstrate applications of deep learning, semantic segmentation, remote sensing, and digital tools to agricultural and ecological assessment. Collectively, these contributions establish a research trajectory focused on computational approaches to plant phenotyping and agricultural monitoring. [3]
External Links
References
- Semantic Segmentation based deep learning approaches for weed detection
https://www.researchgate.net/publication/366288371_Semantic_Segmentation_based_deep_learning_approaches_for_weed_detection
- Computer Vision for Site-Specific Weed Management in Precision Agriculture: A Review
https://www.mdpi.com/2077-0472/15/21/2296
- Image-based Assessment of Vegetation Cover and Composition using U-Net-based Semantic Segmentation
https://elibrary.asabe.org/abstract.asp?aid=54094