The timely and effective detection of forest fires is crucial for environmental and socio-economic protection. Existing deep learning models struggle to balance accuracy and a lightweight design. We introduce SWVR, a new lightweight deep learning algorithm. Utilizing the Reparameterization Vision Transformer (RepViT) and Simple Parameter-Free Attention Module (SimAM), SWVR efficiently extracts fire-related features with reduced computational complexity. It features a bi-directional fusion network combining top-down and bottom-up approaches, incorporates lightweight Ghost Shuffle Convolution (GSConv), and uses the Wise Intersection over Union (WIoU) loss function. SWVR achieves 79.6% accuracy in detecting forest fires, which is a 5.9% improvement over the baseline, and operates at 42.7 frames per second. It also reduces the model parameters by 11.8% and the computational cost by 36.5%. Our results demonstrate SWVR’s effectiveness in achieving high accuracy with fewer computational resources, offering practical value for forest fire detection.

The tea industry, as one of the most globally important agricultural products, is characterized by pests and diseases that pose a serious threat to yield and quality. These diseases and pests often present different scales and morphologies, and some pest and disease target sizes can be tiny and difficult to detect. To solve these problems, we propose TeaViTNet, a multi-scale attention-based tea pest and disease detection model that combines CNNs and Transformers. First, MobileViT is used as the feature extraction backbone network. MobileViT captures and analyzes the tiny pest and disease features in the image via a self-attention mechanism and global feature extraction. Second, the EMA-PANet network is introduced to optimize the model’s learning and attention to the Apolygus lucorum and leaf blight regions via an efficient multi-scale attention module with cross-space learning, which improves the model’s ability to understand multi-scale information. In addition, RFBNet is embedded in the module to further expand the perceptual range and effectively capture the information of tiny features in tea leaf images. Finally, the ODCSPLayer convolutional block is introduced, aiming to focus on acquiring richer gradient flow information. The experimental results show that the TeaViTNet model proposed in this paper has an average accuracy of 89.1%, which is a significant improvement over the baseline network MobileViT and is capable of accurately detecting Apolygus lucorum and leaf blight of different scales and complexities.

Tea cultivation holds significant economic value, yet the leaves of tea plants are frequently susceptible to various pest and disease infestations. Consequently, there is a critical need for research focused on precisely and efficiently detecting these threats to tea crops. The investigation of a model capable of effectively identifying pests and diseases in tea plants is often hindered by challenges, such as limited datasets of pest and disease samples and the small size of detection targets. To address these issues, this study has chosen TLB, a common pest and disease in tea plants, as the primary research subject. The approach involves the application of transfer learning in conjunction with data augmentation as a fundamental methodology. This technique entails transferring knowledge acquired from a comprehensive source data domain to the model, aiming to mitigate the constraints of limited sample sizes. Additionally, to tackle the challenge of detecting small targets, this study incorporates the decoupling detection head TSCODE and integrates the Triplet Attention mechanism into the E-ELAN structure within the backbone to enhance the model’s focus on the TLB’s small targets and optimize detection accuracy. Furthermore, the model’s loss function is optimized based on the Wasserstein distance measure to mitigate issues related to sensitivity in localizing small targets. Experimental results demonstrate that, in comparison to the conventional YOLOv7 tiny model, the proposed model exhibits superior performance on the TLB small sample dataset, with precision increasing by 6.5% to 92.2%, recall by 4.5% to 86.6%, and average precision by 5.8% to 91.5%. This research offers an effective solution for identifying tea pests and diseases, presenting a novel approach to developing a model for detecting such threats in tea cultivation.

Sweetness is one of the most important quality traits for fruit which directly affects consumers’ acceptance. The aim of this study was to detect and grade sweetness levels of intact peaches and nectarines by combining short-wave and long-wave Fourier-transform near-infrared spectroscopy (FT-NIRS). FT-NIR spectra of 720 samples (360 peaches and 360 nectarines) were collected using a system operated in range from 15,700 to 4000 cm⁻¹. Soluble solids contents (SSC) were measured as indicators and samples were individually grouped into three sweetness levels based on predetermined thresholds. Partial least squares regression (PLSR) and principal component regression (PCR) were compared, and results showed that PLSR models developed using raw full spectra performed best with correlation coefficient (R _p) of 0.7747 and 0.8473, and root mean square error (RMSEP) of 0.6915% and 0.7228% in prediction. Furthermore, effective wavelengths were individually selected using regression coefficients (RC) and competitive adaptive reweighted sampling (CARS) to simplify the PLSR models. Through comparison, RC-PLSR resulted in comparable performance with original models showing R _p = 0.7716 and 0.8157, and RMSEP = 0.6943% and 0.7945%. To grade different sweetness levels, two-dimensional correlation spectroscopy (2D-COS) was innovatively conducted, and autopeaks characterizing the differences among different groups were retained. Partial least square discriminant analysis (PLS-DA) classification models based on autopeaks achieved a total correct classification rate (CCR) of 66.7% and 86.6% for peaches and nectarines, respectively. The overall results indicated the combination of short-wave and long-wave FT-NIRS was potentially useful in detecting and grading sweetness for these fruit varieties.