Broccoli is a highly nutritious vegetable that is favored worldwide. Assessing and predicting the shelf life of broccoli holds considerable importance for effective resource optimization and management. The physicochemical parameters and spectral characteristics of broccoli are important indicators partially reflecting its shelf life. However, few studies have used spectral image information to predict and evaluate the shelf life of broccoli. In this study, multispectral imaging combined with multi-feature data fusion was used to predict and evaluate the shelf life of broccoli. Spectral data and textural features were extracted from multispectral images of broccoli and fused with the physicochemical parameters for analysis. Savitzky–Golay (SG) convolution smoothing and standard normal variate (SNV) and normalization (Norm) preprocessing methods were employed to preprocess the original spectral data and textural features, while a successive projection algorithm (SPA) was used to extract relevant feature bands. The physicochemical parameters for broccoli shelf life were predicted using three methods: support vector regression (SVR), random forest classification (RF), and 2D convolutional neural network (2D-CNN) models. Broccoli shelf life prediction models were evaluated using three classification methods: RF, 1D-CNN, and 2D-CNN. The results demonstrate that, among the models used for predicting and evaluating the shelf life of broccoli, the SPA+SG+RF classification model employing fused data Type C achieves the highest accuracy. Specifically, this method achieves accuracies of 88.98% and 88.64% for the training and validation sets, respectively. Multi-feature data fusion of spectral image information and physical and chemical parameters were combined with different machine learning methods to predict and evaluate the shelf life of broccoli.

For different broccoli materials, it used to be necessary to manually plant in a large area for the investigation of flower ball information, and this method is susceptible to subjective influence, which is not only time-consuming and laborious but may also cause some damage to the broccoli in the process of investigation. Therefore, the rapid and nondestructive monitoring of flower heads is key to acquiring high-throughput phenotypic information on broccoli crops. In this study, we used an unmanned aerial vehicle (UAV) to acquire hundreds of images of field-grown broccoli to evaluate their flower head development rate and sizes during growth. First, YOLOv5 and YOLOv8 were used to complete the position detection and counting statistics at the seedling and heading stages. Then, UNet, PSPNet, DeepLabv3+, and SC-DeepLabv3+ were used to segment the flower heads in the images. The improved SC-DeepLabv3+ model excelled in segmenting flower heads, showing Precision, reconciled mean F1-score, mean intersection over union, and mean pixel accuracy values of 93.66%, 95.24%, 91.47%, and 97.24%, respectively, which were 0.57, 1.12, 1.16, and 1.70 percentage points higher than the respective values achieved with the DeepLabv3+ model. Flower head sizes were predicted on the basis of the pixel value of individual flower heads and ground sampling distance, yielding predictions with an R² value of 0.67 and root-mean-squared error of 1.81 cm. Therefore, the development rate and sizes of broccoli flower heads during growth were successively estimated and calculated. Compared with the existing technology, it greatly improves work efficiency and can help to obtain timely information on crop growth in the field. Our methodology provides a convenient, fast, and reliable way for investigating field traits in broccoli breeding.

With the increasing variety of electric vehicles (EVs) joining virtual power plants (VPPs), VPP operators increasingly require precise and tailored models for schedulable EV energy. Based on a publicly available anonymous EV charging power dataset, EV users are clustered through a weighted K-means++ algorithm. Secondly, based on the results of clustering, we analyzed the daily traveling patterns of various types of EVs, including commuting EVs, electric light-duty trucks (ELDTs) and electric tractors (ETs), and then customized the all-day schedulable energy domain model (SEDM) for each category. Subsequently, an optimal bidding strategy for a VPP consisting of diversified-member EVs, air conditionings (ACs), energy storage (ES) and distributed energy resources (DERs) is constructed. By modifying the levels of participation in supplementation and absorption of DERs among VPP members, while integrating considerations such as user comfort, EV defying rate, and seasonal variability, diverse VPP operational frameworks are established. Finally, using the Gurobi solver, the optimal bidding strategies and profit results under different scenarios are derived. The results indicate that (1) increasing the VPP members’ participation in the supplementation and absorption of DERs will bring higher benefits to both the VPP and its members; (2) with the increased sensitivity of users to room temperature and range anxiety, the demand response capacity of AC clusters decreases, reducing EV clusters’ market participation and VPP profits; and (3) among various types of EVs, ELDTs and ETs have a larger battery energy adjustment range, which can fully supplement the output shortfalls of DERs. Therefore, these EVs prove to be a good supplement for the improvement of VPP’s schedule capability and profitability.