To enhance the efficiency of automatic cherry tomato harvesting in precision agriculture, an improved YOLOv8n algorithm was proposed for fast and accurate recognition in natural environments. The improvements are as follows: first, the ADown down-sampling module replaces part of the original network backbone’s standard convolution, enabling the model to capture higher-level image features for more accurate target detection, while also reducing model complexity by cutting the number of parameters. Secondly, the model’s neck adopts a Slim-Neck (GSConv+VoV-GSCSP) instead of traditional convolution with C2f. It replaces this combination with the more efficient CSConv and swaps the C2f module for VoV-GSCSP. Finally, the model also introduces the EMA attention mechanism, implemented at the P5 layer, which enhances the feature representation capability, enabling the network to extract detailed target features more accurately. This study trained the object-detection algorithm on a self-built cherry tomato dataset before and after improvement and compared it with early deep learning models and YOLO series algorithms. The experimental results show that the improved model increases accuracy by 3.18%, recall by 1.43%, the F1 score by 2.30%, mAP50 by 1.57%, and mAP50-95 by 1.37%. Additionally, the number of parameters is reduced to 2.52 M, and the model size is reduced to 5.08 MB, which outperforms other related models compared to the previous version. The experiment demonstrates the technology’s broad potential for embedded systems and mobile devices. The improved model offers efficient, accurate support for automated cherry tomato harvesting.

High-throughput measurements of phenotypic parameters in plants generate substantial data, significantly improving agricultural production optimization and breeding efficiency. However, these measurements face several challenges, including environmental variability, sample heterogeneity, and complex data processing. This study presents a method applicable to stem and leaf segmentation and parameter extraction during the tomato seedling stage, utilizing three-dimensional point clouds. Focusing on tomato seedlings, data was captured using a depth camera to create point cloud models. The RANSAC, region-growing, and greedy projection triangulation algorithms were employed to extract phenotypic parameters such as plant height, stem thickness, leaf area, and leaf inclination angle. The results showed strong correlations, with coefficients of determination for manually measured parameters versus extracted 3D point cloud parameters being 0.920, 0.725, 0.905, and 0.917, respectively. The root-mean-square errors were 0.643, 0.168, 1.921, and 4.513, with absolute percentage errors of 3.804%, 5.052%, 5.509%, and 7.332%. These findings highlight a robust relationship between manual measurements and the extracted parameters, establishing a technical foundation for high-throughput automated phenotypic parameter extraction in tomato seedlings.

Artificial supplemental lighting represents a crucial agricultural technique for enhancing plant growth and development, with researchers continuously investigating the effectiveness of various light sources in horticultural applications. Laser technology, characterized by its monochromatic nature, high coherence, and elevated energy density, presents a promising light source whose potential applications and underlying mechanisms in plant supplemental lighting remain to be thoroughly explored. To investigate the effects of different red-to-blue light ratios in laser supplemental lighting on rice (Oryza sativa L. cv. Jijing129) seedlings, we conducted a seedling-stage lighting experiment on the rice cultivar Jijing129 in a greenhouse using an LGI-660/450 dual-wavelength semiconductor laser system. The experimental design included a natural light control (AL) and three laser treatment groups, with red: blue (R:B) ratios and corresponding photon flux densities as follows: BL (50:50; 150:150 μmol m⁻² s⁻¹), CL (60:40; 180:120 μmol m⁻² s⁻¹), and DL (75:25; 225:75 μmol m⁻² s⁻¹). We systematically analyzed short-term morphological, physiological, and gene expression changes to elucidate the potential mechanisms underlying yield enhancement under different laser spectra. The results indicated that, compared to AL, all laser treatments (BL, CL, and DL) significantly increased root fresh weight, dry weight, and nitrogen content in seedlings. Furthermore, the final yield was significantly improved in all laser-treated groups, with the CL treatment exhibiting the highest yield. Transcriptome sequencing identified 10,497, 10,441, 10,700, and 10,757 expressed genes in the AL, BL, CL, and DL groups, respectively. Comparative analysis revealed 101, 1645, and 2247 differentially expressed genes (DEGs) in the BL/AL, CL/AL, and DL/AL comparisons, respectively. Gene Ontology (GO) enrichment analysis showed that these DEGs were significantly enriched in pathways such as metabolic processes, nitrogen metabolism, and protein amino acid phosphorylation. Notably, genes involved in the regulation of nitrogen compound metabolism were significantly upregulated in the CL and DL treatments. Further analysis of nitrogen metabolism and photosynthesis pathways revealed that laser irradiation induced the upregulation of specific genes. Interestingly, although physiological assays showed no significant changes in CAT, SOD, and POD activities, the expression of their corresponding genes was upregulated by laser treatment, suggesting these genes play a regulatory role during the supplemental lighting process. Therefore, our results indicated that laser supplemental lighting during the rice seedling stage increased the nitrogen content in plants and modulated the expression of related genes, and these changes might have been associated with the subsequent increase in rice yield. This study lays a foundation for understanding the molecular mechanisms of laser supplemental lighting and provides empirical support for the application of laser technology as an effective light source in agriculture.

This study evaluated the effects of red and blue laser irradiation on the development and reproduction of the Asian corn borer (Ostrinia furnacalis (Guenée)) under controlled laboratory conditions, aiming to explore its potential for non-chemical pest control. Larvae were exposed to laser light at different wavelengths and intensities, and key biological parameters—including egg hatching, larval duration, pupation, adult emergence, and oviposition—were assessed. Red laser light slightly delayed egg hatching but had minimal effects on subsequent developmental stages. In contrast, blue laser irradiation significantly prolonged the larval period and reduced pupation rates. Combined red–blue treatments produced similar inhibitory effects to blue light alone, suggesting that blue wavelengths were the primary factor driving developmental delays. These findings demonstrate that blue and red–blue laser irradiation can effectively interfere with the life cycle of O. furnacalis, offering a promising approach for sustainable, light-based pest management strategies.

Laser-driven photocatalysis provides a wavelength-tunable approach for antibiotic removal, but its performance depends on complex interactions among catalyst properties, irradiation parameters, and operating conditions. This study developed an interpretable machine learning-guided framework integrating entropy weight-based evaluation, predictive modeling, and SHAP analysis to investigate the apparent removal efficiency of tetracycline hydrochloride (TCH) over ZnO/Cu_1.35O and ZnO/Cu_1.35O/g-C₃N₄ composites under red, blue, and mixed laser irradiation. At an initial TCH concentration of 20 mg L⁻¹, entropy weight analysis identified 0.02 g ZnO/Cu_1.35O under red laser irradiation at 50 μmol m⁻² s⁻¹ as the highest-scoring scheme (0.73). At 30 mg L⁻¹, ZCG-3 under mixed red/blue laser irradiation at 200 μmol m⁻² s⁻¹ achieved the highest score (0.90). Among five machine learning models, CCO-XGBoost exhibited the best average predictive performance under five-fold group-based cross-validation, with a mean R² of 0.92 ± 0.06 and a mean RMSE of 8.27 ± 2.79%. SHAP analysis identified reaction time, laser intensity, and initial TCH concentration as the most influential predictive features, reflecting model-based associations rather than physicochemical causality. These findings provide a data-driven framework for treatment-scheme evaluation and UV-Vis-derived apparent TCH removal prediction within the investigated experimental domain.