Zandi Abdolrahim, Hosseinirad Seyedali, Kashani Zadeh Hossein, Tavakolian Kouhyar, Cho Byoung-Kwan, Vasefi Fartash, Kim Moon S, Tavakolian Pantea
Biomedical Engineering Department, College of Engineering and Mines, University of North Dakota, Grand Forks, ND, United States.
SafetySpect Inc., Grand Forks, ND, United States.
Front Plant Sci. 2025 Apr 30;16:1545025. doi: 10.3389/fpls.2025.1545025. eCollection 2025.
Detecting plant stress is a critical challenge in agriculture, where early intervention is essential to enhance crop resilience and maximize yield. Conventional single-mode approaches often fail to capture the complex interplay of plant health stressors.
This review integrates findings from recent advancements in Multi-Mode Analytics (MMA), which employs spectral imaging, image-based phenotyping, and adaptive computational techniques. It integrates machine learning, data fusion, and hyperspectral technologies to improve analytical accuracy and efficiency.
MMA approaches have shown substantial improvements in the accuracy and reliability of early interventions. They outperform traditional methods by effectively capturing complex interactions among various abiotic stressors. Recent research highlights the benefits of MMA in enhancing predictive capabilities, which facilitates the development of timely and effective intervention strategies to boost agricultural productivity.
The advantages of MMA over conventional single-mode techniques are significant, particularly in the detection and management of plant stress in challenging environments. Integrating advanced analytical methods supports precision agriculture by enabling proactive responses to stress conditions. These innovations are pivotal for enhancing food security in terrestrial and space agriculture, ensuring sustainability and resilience in food production systems.
在农业领域，检测植物胁迫是一项关键挑战，早期干预对于增强作物恢复力和实现产量最大化至关重要。传统的单模式方法往往无法捕捉植物健康胁迫因素之间的复杂相互作用。
本综述整合了多模式分析（MMA）近期进展的研究结果，多模式分析采用光谱成像、基于图像的表型分析和自适应计算技术。它整合了机器学习、数据融合和高光谱技术，以提高分析的准确性和效率。
多模式分析方法在早期干预的准确性和可靠性方面有显著提高。它们通过有效捕捉各种非生物胁迫因素之间的复杂相互作用，优于传统方法。近期研究突出了多模式分析在增强预测能力方面的优势，这有助于制定及时有效的干预策略，以提高农业生产力。
多模式分析相对于传统单模式技术的优势显著，特别是在具有挑战性环境中的植物胁迫检测和管理方面。整合先进的分析方法通过对胁迫条件做出积极响应来支持精准农业。这些创新对于加强陆地和太空农业的粮食安全、确保粮食生产系统的可持续性和恢复力至关重要。
