The accurate long-term forecasting of hydrometeorological time series is crucial for ensuring the sustainability of water resources, environmental conservation, and other related fields. However, hydrometeorological time series usually have strong nonlinearity, non-stationarity, and complexity. Therefore, it is extremely challenging to make long-term forecasts of hydrometeorological series. Deep learning has been widely applied in time series prediction across various fields and exhibits exceptional performance. Among the many deep learning techniques, Long Short-Term Memory (LSTM) neural networks possess robust long-term predictive capabilities for time series analysis. Signal decomposition technology is utilized to break down the time series into multiple low complexity and highly stationary sub-sequences, which are then individually trained using LSTM before being reconstructed to generate accurate predictions. This approach has significantly advanced the field of time series prediction. Therefore, we propose an EEMD-LSTM-PSO model, which employs Ensemble Empirical Mode Decomposition (EEMD), to decompose the hydrometeorological time series and subsequently construct an LSTM model for each component. Furthermore, the Particle Swarm Optimization (PSO) algorithm is utilized to optimize the coefficients and reconstruct the final prediction outcomes. The performance of the EEMD-LSTM-PSO model is evaluated by comparing it with four other models using four evaluation indicators: root mean square error (RMSE), mean absolute percentage error (MAPE), correlation coefficient (R), and Nash coefficient (NSE) on three real hydrometeorological time series. The experimental results show that the proposed model exhibits exceptional performance compared with the other four models, and effectively predicts long-term hydrometeorological time series.

Traditional laboratory microscopy for identifying bovine milk somatic cells is subjective, time-consuming, and labor-intensive. The accuracy of the recognition directly through a single classifier is low. In this paper, a novel algorithm that combined the feature extraction algorithm and fusion classification model was proposed to identify the somatic cells. First, 392 cell images from four types of bovine milk somatic cells dataset were trained and tested. Secondly, filtering and the K-means method were used to preprocess and segment the images. Thirdly, the color, morphological, and texture features of the four types of cells were extracted, totaling 100 features. Finally, the gradient boosting decision tree (GBDT)-AdaBoost fusion model was proposed. For the GBDT classifier, the light gradient boosting machine (LightGBM) was used as the weak classifier. The decision tree (DT) was used as the weak classifier of the AdaBoost classifier. The results showed that the average recognition accuracy of the GBDT-AdaBoost reached 98.0%. At the same time, that of random forest (RF), extremely randomized tree (ET), DT, and LightGBM was 79.9, 71.1, 67.3 and 77.2%, respectively. The recall rate of the GBDT-AdaBoost model was the best performance on all types of cells. The F1-Score of the GBDT-AdaBoost model was also better than the results of any single classifiers. The proposed algorithm can effectively recognize the image of bovine milk somatic cells. Moreover, it may provide a reference for recognizing bovine milk somatic cells with similar shape size characteristics and is difficult to distinguish.

Wavelength selection is one of the key steps in quantitative spectral analysis, which reduces the computation time while also improving the prediction accuracy of the model. In this paper, we propose a wavelength selection algorithm based on the ant colony optimization (ACO), in which the absolute value of the regression coefficient of the multiple linear regression (MLR) model is used as the basis for evaluating the importance of wavelengths, and the absolute value of the regression coefficient after full wavelength MLR modeling is used as the initial pheromone value of the ant colony optimization (MLR-ACO). In each iteration, the absolute value of the regression coefficient corresponding to each wavelength of the individual with the highest fitness value is used as the basis for a pheromone update. The crossover operator is introduced in MLR-ACO (MLR-ACO-GA), and the individuals with the top 100 fitness values in MLR-ACO are used as the initial population of the genetic algorithm (GA). A selected frequency of wavelengths greater than the threshold among MLR-ACO individuals is calculated. A number of coarse interval points are generated according to the selected frequency, and a coarse crossover operation is performed at the coarse interval points. Fine crossover points are randomly generated within the coarse interval, and fine crossover operations are performed within the coarse interval to exploit the potential of combining excellent individuals in MLR-ACO with each other as much as possible. MLR-ACO can well solve the problem of traditional ACO initial pheromone scarcity, and MLR-ACO-GA can avoid MLR-ACO falling into a local optimum to a certain extent and be more flexible in the selection of the number of wavelengths, which can give full play to the advantages of MLR-ACO.

Somatic cell count (SCC) is a fundamental approach for determining the quality of cattle and bovine milk. So far, different classification and recognition methods have been proposed, all with certain limitations. In this study, we introduced a new deep learning tool, i.e., an improved ResNet50 model constructed based on the residual network and fused with the position attention module and channel attention module to extract the feature information more effectively. In this paper, macrophages, lymphocytes, epithelial cells, and neutrophils were assessed. An image dataset for milk somatic cells was constructed by preprocessing to increase the diversity of samples. PolyLoss was selected as the loss function to solve the unbalanced category samples and difficult sample mining. The Adam optimization algorithm was used to update the gradient, while Warm-up was used to warm up the learning rate to alleviate the overfitting caused by small sample data sets and improve the model's generalization ability. The experimental results showed that the classification accuracy, precision rate, recall rate, and comprehensive evaluation index F value of the proposed model reached 97%, 94.5%, 90.75%, and 92.25%, respectively, indicating that the proposed model could effectively classify the milk somatic cell images, showing a better classification performance than five previous models (i.e., ResNet50, ResNet18, ResNet34, AlexNet andMobileNetv2). The accuracies of the ResNet18, ResNet34, ResNet50, AlexNet, MobileNetv2, and the new model were 95%, 93%, 93%, 56%, 37%, and 97%, respectively. In addition, the comprehensive evaluation index F1 showed the best effect, fully verifying the effectiveness of the proposed method in this paper. The proposed method overcame the limitations of image preprocessing and manual feature extraction by traditional machine learning methods and the limitations of manual feature selection, improving the classification accuracy and showing a strong generalization ability.

Due to the influence of global climate change and human activities, the time series data of river runoff become complex and non-stationary. These properties make sequence prediction difficult and with low accuracy. In order to improve the prediction accuracy, Empirical Mode Decomposition (EMD) was introduced to Long Short-Term Memory (LSTM) networks in this paper. The EMD decomposed a non-stationary time series into multiple components. We trained an LSTM network for each component, and added their predictions to obtain the final forecasting value of original sequence. At last, the EMD-LSTM model was applied to the annual runoff sequence in the upper Heihe River. By comparing with single LSTM, it shows that the EMD-LSTM has higher accuracy for the long-term prediction of river runoff.