Panda D, Mohanty S, Das S, Senapaty J, Sahoo D B, Mishra B, Baig M J, Behera L
ICAR-National Rice Research Institute, Cuttack, Odisha, India.
Photosynthetica. 2025 Jul 8;63(2):196-233. doi: 10.32615/ps.2025.012. eCollection 2025.
Ensuring global food security requires noninvasive techniques for optimizing resource use and monitoring crop health. Hyperspectral imaging (HSI) enables the precise analysis of plant physiology by capturing spectral data across narrow bands. This review explores HSI's role in agriculture, particularly its integration with unmanned aerial vehicles, AI-driven analytics, and machine learning. These advancements allow real-time monitoring of photosynthesis, chlorophyll fluorescence, and carbon assimilation, linking spectral data to plant health and agronomic decisions. Key indicators such as solar-induced fluorescence and vegetation indices enhance crop stress detection. This work compares HSI-derived metrics in differentiating nutrient deficiencies, drought, and disease. Despite its potential, challenges remain in data standardization and spectral interpretation. This review discusses solutions such as molecular phenotyping and predictive modeling, for AI-driven precision agriculture. Addressing these gaps, HSI is poised to revolutionize farming, improve climate resilience, and ensure food security.
确保全球粮食安全需要采用非侵入性技术来优化资源利用并监测作物健康状况。高光谱成像（HSI）通过捕获窄波段的光谱数据，能够对植物生理进行精确分析。本综述探讨了高光谱成像在农业中的作用，特别是其与无人机、人工智能驱动的分析以及机器学习的整合。这些进展使得能够实时监测光合作用、叶绿素荧光和碳同化，将光谱数据与植物健康状况及农艺决策联系起来。诸如太阳诱导荧光和植被指数等关键指标可增强作物胁迫检测能力。这项工作比较了高光谱成像得出的指标在区分养分缺乏、干旱和疾病方面的表现。尽管高光谱成像具有潜力，但在数据标准化和光谱解释方面仍存在挑战。本综述讨论了诸如分子表型分析和预测建模等解决方案，以推动人工智能驱动的精准农业发展。解决这些差距后，高光谱成像有望彻底改变农业，提高气候适应能力并确保粮食安全。
