Temperature is a critical factor influencing crop growth in controlled environment agriculture. Accurate regulation of air temperature within a greenhouse is essential for promoting optimal crop development and enhancing production efficiency. In this study, a Categorical Boosting model based on SMOTETomek mixed sampling method and improved Sparrow Search Algorithm (SMOTETomek-ISSA-CatBoost) was proposed to predict the categories of greenhouse temperature control modes. This study utilized historical temperature control mode data, which had been accumulated by cultivation experts through practical production and demonstrated effective in temperature management. To enhance the model’s performance and achieve real-time, precise temperature regulation in greenhouses, firstly, the SMOTETomek mixed sampling method was utilized to expand the original training set, effectively addressing the issue of data imbalance. Secondly, the Latin Hypercube Sampling (LHS) method, the Cauchy mutation perturbation operator, and a greedy rule were employed to refine the Sparrow Search Algorithm to enhance the global search capability. Ultimately, the improved Sparrow Search Algorithm was employed to optimize the hyper-parameters of CatBoost model to improve its predictive accuracy. Compared with SMOTETomek-CatBoost models optimized by Whale Optimization Algorithm (WOA), Fruit Fly Optimization Algorithm (FOA), Particle Swarm Optimization (PSO), and standard Sparrow Search Algorithm (SSA), the SMOTETomek-ISSA-CatBoost model demonstrated better prediction efficacy, with F1-score and AUC values reaching 0.8147 and 0.9629, respectively. The SMOTETomek-ISSA-CatBoost model exhibited the capability to predict the category of temperature control modes in a greenhouse accurately, thereby providing a decision-making foundation for intelligent management of greenhouse environments.

Hyperspectral remote sensing images can capture the continuous spectral curves of the ground surface, and then enable the delicate classification of crops, due to their diagnostic capability of high spectral data. The conventional algorithms of hyperspectral image classification are highly required to explore the spatial information and effective utilization of spectral images. It cannot be fully addressed on the "same object, different spectra; different objects, same spectra" problem, such as the Hughes phenomenon. The classification accuracy has been improved with the continuous development of deep learning-based classification on hyperspectral images. However, there are still several issues that need to be addressed: 1) Traditional convolution layers can be calculated by the equal weights for all pixels in the feature extraction, particularly without considering the spatial correlation and local similarity within the feature neighborhood. 2) Although the previous algorithms have separately captured the spatial and spectral features in the hyperspectral images, the extraction of high-dimensional features can often result in redundancy, which is lacking in effective feature selection. 3) Traditional algorithms of deep learning can often merge the temporal and spatial features using a single feature constraint method, especially for loss calculation. Comprehensive feedback is required on the classification from the spatial and spectral perspectives. The comprehensiveness of the fused features can remain to be examined during this time. In this study, a hyperspectral classification algorithm was proposed using a spatial-spectral dual-branch architecture and a dynamic feature selection strategy. The channel and spatial attention modules were introduced to extract and screen the spatial-spectral joint features. Moreover, the gated convolutional layers were used to calculate the correlation of extracted features, enabling dynamic feature selection in both the spatial and channel dimensions. A novel loss function was designed to constrain the classification, in terms of the spatial and spectral perspectives. The results indicate that: 1) The DBDS algorithm performed better in the time efficiency and accuracy, compared with the mainstream crop classification. On the JAAS dataset, the OA and Kappa of the improved algorithms were 99.35% and 99.2%, respectively, which were 4.91% and 6.12%, 6.82% and 8.53%, 2.12% and 2.63%, 2.04% and 2.54% higher than those of CDCNN, WCRN, DBDA, and DCNN, respectively. On the WHU-Hi-HanChuan dataset, the OA of 99.49% and the Kappa of 99.41% were 1.67% and 1.96%, 3.23% and 3.80%, 2.00% and 2.35%, 1.10% and 1.29% higher than those of CDCNN, WCRN, DBDA, and DCNN, respectively. On the WHU-Hi-Longkou dataset, the OA and Kappa were also improved, reaching 99.8% and 99.74%, respectively, which were 1.30% and 1.71%, 0.59% and 1.74%, 0.71% and 0.93%, 0.57% and 0.76% higher than those of CDCNN, WCRN, DBDA, and DCNN, respectively. 2) The spatial-spectral features were effectively extracted to reduce the model degradation in the dataset with the limited samples, complex and difficult-to-distinguish land cover classification. On the WHU-Hi-Hanchuan dataset, the DBDA algorithm was focused on the extraction of spectral information. The better performance was achieved in the tasks of crop classification with sufficient samples, indicating the high f1 scores for the strawberry, Cowpea, soybean, and sorghum (99.60%, 99.10%, 99. 41%, and 99.71%, respectively). However, the significant degradation of the model was observed to classify the lack-sample targets, where the f1 scores for the watermelon and bare soil were only 86.30% and 91.07%, respectively. By contrast, the DBDS algorithm improved the recognition accuracy of various crops with the f1 scores of 96.65% and 98.23% for the watermelon and bare soil, respectively, indicating the effective extraction and utilization of spatial and spectral features. Therefore, the higher accurate and efficient classification was achieved in the fine-grained crop in the regions with the imbalanced samples and the diverse types of land covering. Therefore, 2D convolution-based hyperspectral classification algorithms can be expected to obtain the effective extraction of spatial-spectral features with comparable accuracy to 3D convolution with fewer parameter computations. This finding can also provide important implications and strong references for the target recognition tasks using hyperspectral data.

This study aims to clarify the influence of various root zone temperatures and fertilizer concentrations on the strawberry growth. The parameters were collected from the Jiangsu Province from 2021 to 2023. Nine hierarchy indices were applied to conduct analytic hierarchy process (AHP) and Criteria importance using intercriteria correlation (CRITIC). A combined hierarchy of indices was closely related to strawberry growth. These indices included the firmness, sugar acid ratio, soluble solid, single fruit weight, yield, fertilizer partial productivity (PFP), and water utilization rate (WUE). Technique for order preference by similarity to ideal solution (TOPSIS) was also used to evaluate the comprehensive growth evaluation system for strawberry. The result showed that the root zone heating shared a positive effect on the growth of facility strawberries. There was the more significant behavior, as the heating time increased. In the first crop, the highest content of soluble solid was observed under T1 treatment. Nevertheless, the low fertilizer concentrations (0.5 g/L) led to the highest single fruit weight among all three-temperature treatments. While the high fertilizer concentrations resulted in the smallest single fruit weight. The highest PFP was observed in the T8 treatment, indicating the significantly higher than the rest. In the second crop, the highest single fruit weight was observed under the low fertilizer concentrations, whereas the lowest was found under the high fertilizer concentrations. The highest yield and PFP were achieved under the T5 treatment, which was the higher than the rest. The highest WUE was also found under T5 treatment, which was significantly higher than that under T1, T2, T3, T4, T6, and T7 treatment. There was no significant difference, compared with the T8 and T9 treatments. In the third crop, the highest yield was achieved under the T5 treatment, which was significantly higher than that under T1 and T7 treatment. As such, the better performance was found in the medium fertilizer concentration at medium temperature. The single-factor effect analysis of root zone temperature and fertilizer concentration showed that the highest single fruit weight, PFP and WUE were found at a fertilizer concentration of 1.5 g/L. Therefore, the moderate concentration of fertilizer was optimized for the WUE and economic benefits. The highest yield, PFP and WUE were obtained at a root zone temperature of 16 ℃, followed by 22 ℃, and lowest under 8 ℃ (without heating). The moderate heating of root zone was effectively enhanced the root absorption capacity, while the excessively high temperatures of root zone presented an inhibitory effect. The multi-objective evaluation was obtained to optimize the quality, yield, PFP, and WUE in the strawberry production. The AHP and CRITIC were used to define the subjective and objective weights, in order to evaluate strawberry production, respectively. The weight was calculated and then ranked in the descending order of the yield, fruit weight, sugar acid ratio, PFP, soluble solid, WUE, and hardness. The TOPSIS indicated that the T5 (16 ℃, 1.5 g/L) shared the highest score among all treatments, followed by the T8 (16 ℃, 0.5 g/L) and T3 (2 ℃, 2.5 g/L). The lowest score was found under the T7 (8 ℃, 0.5 g/L). A binary quadratic regression equation was also constructed for the growth control of facility strawberries, according to the root zone temperature and fertilizer concentration. Additionally, the equation was statistically significant at the significance level of 0.05. The bivariate quadratic regression equation was converted into a contour map of the comprehensive score of strawberry by root zone temperature and fertilizer concentration. Dividing the optimal closed loop interval of root zone temperature and fertilizer concentration coupling based on a comprehensive evaluation of more than 82%, the root zone temperature amount of 13.10-18.47 ℃ and the fertilizer concentration amount of 1.43-1.87 g/L were the most beneficial to strawberry growth. The findings can provide the theoretical reference to evaluate the relationship between root zone temperature and fertilizer, particularly for the precision management in strawberry production.

The deployment of intelligent surveillance systems to monitor tomato plant growth poses substantial challenges due to the dynamic nature of disease patterns and the complexity of environmental conditions such as background and lighting. In this study, an integrated cascade framework that synergizes detectors and trackers was introduced for the simultaneous identification of tomato leaf diseases and fruit counting. We applied an autonomous robot with smartphone camera to collect images for leaf disease and fruits in greenhouses. Further, we improved the deep learning network YOLO-TGI by incorporating Ghost and CBAM modules, which was trained and tested in conjunction with premier lightweight detection models like YOLOX and NanoDet in evaluating leaf health conditions. For the cascading with various base detectors, we integrated state-of-the-art trackers such as Byte-Track, Motpy, and FairMot to enable fruit counting in video streams. Experimental results indicated that the combination of YOLO-TGI and Byte-Track achieved the most robust performance. Particularly, YOLO-TGI-N emerged as the model with the least computational demands, registering the lowest FLOPs at 2.05 G and checkpoint weights at 3.7 M, while still maintaining a mAP of 0.72 for leaf disease detection. Regarding the fruit counting, the combination of YOLO-TGI-S and Byte-Track achieved the best R² of 0.93 and the lowest RMSE of 9.17, boasting an inference speed that doubles that of the YOLOX series, and is 2.5 times faster than the NanoDet series. The developed network framework is a potential solution for researchers facilitating the deployment of similar surveillance models for a broad spectrum of fruit and vegetable crops.