Multi-Sensor High-Throughput Phenotyping Dataset of Hydroponic Lettuce under Variable Fertigation Conditions]{Multi-Sensor High-Throughput Phenotyping Dataset of Hydroponic Lettuce under Variable Fertigation Conditions

A multimodal high-throughput phenotyping dataset of hydroponically grown looseleaf lettuce (Lactuca sativa L.) acquired in a semi-controlled glasshouse under variable fertigation conditions. The dataset provides repeated measurements from transplanting to harvest over a 42 days crop cycle, enabling analysis of temporal changes in lettuce growth and development. The experiment included 45 plants from two cultivars ("Grand Rapid" and "Lollo Rossa"), three nitrogen concentrations in the nutrient solution (6, 13, and 17 mmol.L-1), and two nutrient solution application rates corresponding to 50% and 75% of water loss between irrigations. The dataset comprises: (i) plot-level 3D pointclouds, 2D RGB (Red, Blue, Green) images, and environmental measurements, (ii) plant-level 3D pointclouds, 2D RGB images, and multispectral measurements, (iii) leaf-level multispectral measurements spanning 320 to 2150 nm, and (iv) reference measurements, including SPAD chlorophyll content, chlorophyll fluorescence, morphological traits, and treatment-level nutritional composition. Beyond raw sensor outputs, the deposited record includes metadata, processed data products, image annotations, and FAIR (Findable, Accessible, Interoperable, and Reusable) tabular records that support data linkage within an ontology-based structure. This dataset links multimodal and multiscale measurements with reference data over a complete crop cycle. By combining multimodal sensing with structured contextual and reference data, this dataset supports reproducible reuse in hydroponic crop phenotyping, trait estimation, and modeling of lettuce responses to variable fertigation conditions.