[Dataset] Spatial Centroids and Network Representations of Stomata in Three Plant Species under Environmental Stress

This dataset corresponds to the data used in manuscript Machicao et al. (2026) "Pattern Recognition of Stomatal Distribution: A Network Automata Approach to Identify Plasticity under Environmental Stress", for submission. It contains: Microscopic Images: Original captures of stomatal distributions for three plant species. Expert-Validated Centroids: Spatial coordinates (x, y) of stomata, manually identified using GIMP to ensure high ground-truth accuracy. Stomatal Networks: Proximity graphs and distance matrices derived from the centroids. This data enables the characterization of phenotypic plasticity through spatial pattern recognition and network science. Stomata Dataset •Ctenanthe oppenheimiana: Plants, measuring 5 to 8 cm, were planted in standard Carolina substrate (Carolina soil, Brazil). Samples were acclimated in a controlled growth chamber (Eletrolab EL212/4G-RS) with continuous 55% relative humidity, a photon flux of 100μmol/m2 ×s, and temperature of 25◦C. Two light/dark photoperiods were tested: 24 hours (L24) and 4 hours (L4) per day for 60 days, resulting in 18 images per condition. •Tradescantia zebrina: Plants were acclimated in the same controlled growth chamber under identical conditions for 68 days. A third group was maintained under uncontrolled conditions in an external environment. A total of 6 images were obtained for each condition. This collection was previously described by Florindo et al. (2015). • Callisia repens: Three experimental groups were used. The first was sealed in a bottle with Carolina soil and subjected to a CO2 gas stream (1500 ppm for 6 hours/day over 30 days). The second group was treated similarly but without the CO2 flow. In both bottled groups, relative humidity was maintained between 85 and 90% during the daily 6-hours cycle. A third group was collected from a natural, uncontrolled environment in July 2015 (georeferenced at -22.007 S; -47.894 W). Five images were captured for each condition. Regarding imaging specifications, images were captured at different magnifications depending on the species. For Ctenanthe oppenheimiana, a 100x objective lens was used, resulting in a pixel scale of 0.347μm/px and a resolution of 2560 × 1920 pixels. For Tradescantia zebrina and Callisia repens, images were captured at 15x magnification, corresponding to 4.65935μm/px and 1388 × 1038 pixels. These specific optical scales were used for all subsequent spatial measurements and pixel-to-micron conversions. Stomata Network Dataset The files are in edgelist. For Ctenanthe oppenheimiana, we used 7 thresholds ranging from Tini = 140 to TQ = 260 μm. For Tradescantia zebrina and Callisia repens, the feature vector was expanded to 16 thresholds from Tini = 400 to TQ = 640 μm.