Accurately classifying the quality of apples is crucial for maximizing their commercial value. Deep learning techniques are being widely adopted for apple quality classification tasks, achieving impressive results. While existing research excels at classifying apple variety, size, shape, and defects, color and deformity analysis remain an under-explored area. Therefore, this study investigates the feasibility of utilizing convolutional neural networks (CNN) to classify the color and deformity of apples based on machine vision technology. Firstly, a custom-assembled machine vision system was constructed for collecting apple images. Then, image processing was performed to extract the largest fruit diameter from the 45 images taken for each apple, establishing an image dataset. Three classic CNN models (AlexNet, GoogLeNet, and VGG16) were employed with parameter optimization for a three-category classification task (non-deformed slice–red apple, non-deformed stripe–red apple, and deformed apple) based on apple features. VGG16 achieved the best results with an accuracy of 92.29%. AlexNet and GoogLeNet achieved 91.66% and 88.96% accuracy, respectively. Ablation experiments were performed on the VGG16 model, which found that each convolutional block contributed to the classification task. Finally, prediction using VGG16 was conducted with 150 apples and the prediction accuracy was 90.50%, which was comparable to or better than other existing models. This study provides insights into apple classification based on color and deformity using deep learning methods.

Organic pollutants, especially dyes, are seriously hazardous to the aquatic system and humans due to their toxicity, and carcinogenic or mutagenic properties. In this study, a biochar prepared from agricultural waste (pecan shells) via pyrolysis was applied to remove the dye pollutant Congo Red from wastewater to avoid a negative effect to the ecosystem. This study also investigated the effect of preparation conditions (temperature and heating rate) on the physicochemical properties and the adsorption performance of biochars. The physicochemical properties of the biochar were characterized using scanning electron microscopy, X-ray powder diffraction, Fourier transform infrared spectroscopy, and X-ray photoelectron spectroscopy. The adsorption performance of the biochar was evaluated for Congo Red removal. The results showed that biochar prepared at 800 °C with a heating rate of 20 °C/min (PSC-800-20) exhibited a higher specific surface area of 450.23 m²/g and a higher adsorption capacity for Congo Red (130.48 mg/g). Furthermore, adsorption experiments indicated that the pseudo-second-order and Langmuir models fitted well with the adsorption kinetics and isotherms of the biochar derived from pecan shells, respectively. Additionally, the PSC-800-20 biochar demonstrated a stable adsorption capacity over multiple cycles, suggesting its potential for regeneration and reuse in wastewater treatment applications. Therefore, the biochar derived from agricultural waste presents a promising and sustainable solution for the removal of toxic dye pollutants from wastewater.

Spatial-frequency domain imaging (SFDI) has been developed as an emerging modality for detecting early-stage bruises of fruits, such as apples, due to its unique advantage of a depth-resolved imaging feature. This paper presents theoretical and experimental analyses to determine the light penetration depth in apple tissues under spatially modulated illumination. Simulation and practical experiments were then carried out to explore the maximum light penetration depths in ‘Golden Delicious’ apples. Then, apple experiments for early-stage bruise detection using the estimated reduced scattering coefficient mapping were conducted to validate the results of light penetration depths. The results showed that the simulations produced comparable or a little larger light penetration depth in apple tissues (~2.2 mm) than the practical experiment (~1.8 mm or ~2.3 mm). Apple peel further decreased the light penetration depth due to the high absorption properties of pigment contents. Apple bruises located beneath the surface peel with the depth of about 0–1.2 mm could be effectively detected by the SFDI technique. This study, to our knowledge, made the first effort to investigate the light penetration depth in apple tissues by SFDI, which would provide useful information for enhanced detection of early-stage apple bruising by selecting the appropriate spatial frequency.

A series of bifunctional hierarchical HZSM-5 catalysts modified with Zn, Ga, Ni, Cr, or Ag were synthesized via impregnation, and their performance in the catalytic fast pyrolysis of walnut shells was systematically evaluated. The influence of the metal species and concentration of NaOH used for desilication (0.20–0.40 mol·L⁻¹) on the yield of light aromatics was assessed. Ga/HZSM-5 and Zn/HZSM-5 exhibited the most pronounced enhancement at 0.35 mol·L⁻¹, significantly outperforming the unmodified HZSM-5. Building on this finding, Zn-Ga bimetallic hierarchical catalysts were developed, and the effect of the Zn:Ga loading ratio (1%:2%, 1.5%:1.5%, 2%:1%) was investigated. The 1%Zn/2%Ga catalyst delivered the highest performance, achieving a total aromatic yield of 3.876 × 10⁴ a.u.·mg⁻¹, with 82% BTX (benzene, toluene, and xylenes) selectivity. The term “a.u.” stands for “arbitrary units,” typically derived from peak area counts obtained through GC-MS analysis. These values represent the relative signal intensity detected by the instrument, rather than absolute quantities of the substance. To more accurately characterize the aromatic hydrocarbon yield, these data are normalized to the yield of aromatic hydrocarbons per unit mass. These findings demonstrate that the combination of Zn-Ga modification and tailored mesoporosity can markedly enhance the production of high-value benzene, toluene, and xylene (BTX) aromatics from lignocellulosic biomass.