Physiological maturity of bananas is of vital importance in determination of their quality and marketability. This study assessed, with the use of a Vis/NIR hyperspectral imaging (400–1000 nm), the feasibility in differentiating six maturity levels (maturity level 2, 4, and 6 to 9) of green dwarf banana and characterizing their quality changes during maturation. Spectra were extracted from three zones (pedicel, middle and apex zone) of each banana finger, respectively. Based on spectra of each zone, maturity identification models with high accuracy (all over 91.53% in validation set) were established by partial least squares discrimination analysis (PLSDA) method with raw spectra. A further generic PLSDA model with an accuracy of 94.35% for validation was created by the three zones’ spectra pooled to omit the effect of spectra acquisition position. Additionally, a spectral interval was selected to simplify the generic PLSDA model, and an interval PLSDA model was built with an accuracy of 85.31% in the validation set. For characterizing some main quality parameters (soluble solid content, SSC; total acid content, TA; chlorophyll content and total chromatism, ΔE*) of banana, full-spectra partial least squares (PLS) models and interval PLS models were, respectively, developed to correlate those parameters with spectral data. In full-spectra PLS models, high coefficients of determination (R²) were 0.74 for SSC, 0.68 for TA, and fair of 0.42 as well as 0.44 for chlorophyll and ΔE*. The performance of interval PLS models was slightly inferior to that of the full-spectra PLS models. Results suggested that models for SSC and TA had an acceptable predictive ability (R² = 0.64 and 0.59); and models for chlorophyll and ΔE* (R² = 0.34 and 0.30) could just be used for sample screening. Visualization maps of those quality parameters were also created by applying the interval PLS models on each pixel of the hyperspectral image, the distribution of quality parameters in which were basically consistent with the actual measurement. This study proved that the hyperspectral imaging is a useful tool to assess the maturity level and quality of dwarf bananas.

Neural networks are widely used in fruit sorting and have achieved some success. However, due to the limitations of storage space and power consumption, the storage and computing of a neural network model on embedded devices remain a massive challenge. Aiming at realizing a lightweight mango sorting model, the feature-extraction characteristics of the shallow and deep networks of the SqueezeNet model were analyzed by a visualization method, and then eight lightweight models were constructed by removing redundant layers or modifying the convolution kernel. It was found that the model designated Model 4 performed well after training and testing. The class activation mapping method was used to explain the basis of the classification decision, and the model was compared with ten classical classification models. The results showed that the calculation performance of the model was significantly improved without reducing accuracy. The parameter storage requirement is 0.87 MB, and the calculation amount is 181 MFLOPS, while the average classification accuracy can still be maintained at 95.64%. This model has a high-cost performance and can be widely used in embedded devices.

A grading method of potted Anthurium based on machine vision is proposed. A detection system is designed to acquire color images and depth images of potted Anthurium, and the three-dimensional point-cloud image is reconstructed after registration. According to the testing requirements of potted Anthurium, the minimum enclosing rectangle method is used to measure the width of crowns and spathes. The bubble sequencing method is used to measure the plant height, and the clustering segmentation method is used to calculate the number of spathes. Online automatic grading software for potted Anthurium is developed. Compared with manual measurement, the average measurement accuracies of machine vision for crown width, plant height, spathe width, and spathe number are 98.4, 98.4, 98.8, and 86.7, respectively. The accuracy rate of grading is 85.86, which can meet the requirements of automatic grading of potted Anthurium.

Anoectochilus formosanus is a rare medicinal plant with anti-inflammatory, antioxidant, hepatoprotective, and immunomodulatory properties. Its morphological growth and accumulation of medicinal compounds are strongly influenced by environmental factors such as light intensity. To investigate the physiological and ecological responses of Anoectochilus formosanus to varying light intensities, we examined physiological, morphological, and growth parameters across different growth stages under five different light intensities. Correlation, plasticity, and principal component analysis (PCA) were performed. The results showed that high and low light intensities altered physiological and biochemical indicators at different stages. Leaf area, fresh weight, dry weight, stem thickness, and non-photochemical quenching (NPQ) increased with increasing light intensity, whereas chlorophyll fluorescence parameters (Fv, Fm, and Fv/Fm) and flavonoid content decreased, reflecting reduced light capture and consumption under high light intensities. The phenotypic plasticity index of the morphological traits (0.5), indicating a greater plasticity of the photosynthetic traits. Biomass indicators—leaf area ratio and relative growth rate—were strongly correlated, driving the response to light intensity. Growth and biomass allocation peaked at moderate light intensity (70 μmol·m⁻²·s⁻¹). These findings highlight the conservative strategy employed by A. formosanus for slow carbon use under low-light conditions, and the adventurous strategy employed for rapid carbon use under strong light, offering insights into efficient cultivation practices.

Porous microstructure is a common surface morphology that is widely used in antifouling, drag reduction, adsorption, and other applications. In this paper, the lattice gas automata (LGA) method was used to simulate the non-uniform electrochemical machining of porous structure at the mesoscopic level. In a cellular space, the metal and the electrolyte were separated into orderly grids, the migration of corrosive particles was determined by an electric field, and the influences of the concentration gradient and corrosion products were considered. It was found that different pore morphologies were formed due to the competition between dissolution and diffusion. When the voltage was low, diffusion was sufficient, and no deposit was formed at the bottom of the pore. The pore grew faster along the depth and attained a cylindrical shape with a large depth-to-diameter ratio. As the voltage increased, the dissolution rates in all directions were the same; therefore, the pore became approximately spherical. When the voltage continued to increase, corrosion products were not discharged in time due to the rapid dissolution rate. Consequently, a sedimentary layer was formed at the bottom of the pore and hindered further dissolution. In turn, a disc-shaped pore with secondary pores was formed. The obtained simulation results were verified by experimental findings. This study revealed the causes of different morphologies of pores, which has certain guiding significance for non-uniform electrochemical machining.

A biodegradable, lightweight substrate for facility-based stereoscopic planting was developed via a one-step polyurethane foaming process. The substrate was synthesized by incorporating a biomass mixture of bamboo charcoal and cassava flour into a polyurethane foam matrix. This study investigated the effects of varying the content ratios of polyether polyol, isocyanate, bamboo charcoal powder, and cassava flour on the structural and functional properties of the composite foam. Results indicated that the biomass blend significantly influenced the foam’s physicochemical properties, water retention capacity, hardness, and elasticity. Specifically, bamboo charcoal powder enhanced the porosity and degradation rate of the foam, whereas the swelling of cassava flour upon water absorption improved the matrix’s resilience and cohesion. A polyether polyol/isocyanate ratio of 4:1 yielded a substrate with superior physicochemical properties, water retention capacity, germination rate, seedling index, and plant dry weight. Subsequently, the optimal overall performance was achieved at a biomass/polyol–isocyanate ratio of 1:3. This optimal formulation exhibited a degradation rate of 6.24 ± 0.94%, porosity of 66.07 ± 1.10%, and water retention capacity of 86.03 ± 1.59%. Consequently, it also produced the highest seed germination rate (84 ± 5.16%), seedling index (12.49 ± 1.94), and mature plant dry weight (4.00 ± 0.51 g). Microscopic analysis confirmed that the biomass addition refined the substrate’s pore structure, leading to greater uniformity and stability of the internal pores. This enhancement reduced the foam’s susceptibility to collapse and improved its elasticity and cohesion, thereby making it more amenable to mechanized handling and planting operations.