From Lab to Field: AI-Driven Phenotyping and Robotic Sensing for Crop Health and Smart Crop Management

Crops worldwide face intensifying threats from pathogens, pests, weeds, and abiotic stress, making timely, sustainable protection essential to food security. Increasingly, this protection depends on AI-driven phenotyping and sensing to detect and respond to crop conditions. However, the transition from controlled-environment studies to real-world field deployment remains the principal bottleneck: most solutions rely on cloud-connected, GPU-intensive pipelines that assume stable power, high-bandwidth connectivity, and controlled illumination — conditions atypical of agricultural fields, especially in smallholder and resource-constrained regions. This mismatch limits the real-world impact of crop phenotyping and phytoprotection research. Closing the well-documented “lab-to-field” gap calls for edge-native, computationally frugal, and hardware-aware AI that can safeguard crop health reliably and affordably where crops actually grow.This Research Topic curates a high-impact collection of studies that apply practical, field-deployable AI and robotic sensing to protect crops and monitor plant health under real field conditions. Its focus is agronomic and biological: detecting and managing crop diseases, pests, weeds, and stress earlier, more accurately, and more sustainably across diverse cropping systems. Alongside scientific novelty, we establish “implementation readiness” — computational efficiency, power awareness, latency, and operational robustness — as a first-class criterion, because a crop-protection tool matters only if it works in the field, including in smallholder and resource-constrained settings. By showcasing work that translates laboratory innovation into scalable, deployable solutions for defending crops against threats, this Research Topic catalyses research at the intersection of plant science, agronomy, agricultural engineering, and data science, keeping crop health and protection at its centre.We welcome Original Research, Methods, Reviews, and Perspectives in which a crop-protection or crop-health question is central and the AI/sensing approach is demonstrated under, or designed for, real field conditions. Topics of interest include, but are not limited to:· Edge-AI for on-device detection and diagnosis of crop diseases, pests, and weeds on resource-constrained field devices· Robotic and UAV/UGV platforms for targeted, sustainable plant protection and reduced chemical input· Cross-modal sensing (RGB, multispectral, hyperspectral, LiDAR, thermal) for early crop stress, disease, and trait phenotyping under natural conditions· Domain adaptation and generalization for robust crop monitoring across cultivars, crops, seasons, and fields with minimal labeled data· Benchmarking and reproducibility using field-collected crop datasets and standardized evaluation for phytoprotection tasks· Socio-technical and cost-benefit analysis of field crop-protection tools, including smallholder adoptionOut of ScopeTo keep the collection focused on deployable crop protection, the following fall outside its scope:· Purely cloud- or server-GPU-based approaches with no edge or field-deployment component· Laboratory-only or simulation-only studies with no field trial or hardware implementation· Model development trained solely on internet-scraped or public benchmark images, with no field-collected data or real-world validation· Pure breeding trials or genetic/marker-discovery studies without a sensing or AI component-------We welcome contributions from researchers across the field, and we are glad to support you as you prepare your submission. If you would like early feedback on whether your planned manuscript fits the scope of this Research Topic, please write to us at plantscience@frontiersin.org before submitting. A quick check at this stage helps confirm your work is a strong fit and can save you time later in the process.To take part, click “Participate in this topic” at the top right of this page, then confirm through the “Participate” link in the follow-up email. This lets us know to expect your contribution, keeps you informed of key deadlines, and gives you access to resources that guide you through submission. We would also be glad to talk with you about possible routes for support with the Article Processing Charge (APC).We look forward to your participation and to building a vibrant, cohesive Research Topic together. Topic editors: Zhenghong Yu, Suresh Gawande, Changcai Yang, Yanan Li Source: https://www.frontiersin.org/research-topics/83499/from-lab-to-field-ai-driven-phenotyping-and-robotic-sensing-for-crop-health-and-smart-crop-management