Water resource modeling is an important means of studying the distribution, change, utilization, and management of water resources. By establishing various models, water resources can be quantitatively described and predicted, providing a scientific basis for water resource management, protection, and planning. Traditional hydrological observation methods, often reliant on experience and statistical methods, are time-consuming and labor-intensive, frequently resulting in predictions of limited accuracy. However, machine learning technologies enhance the efficiency and sustainability of water resource modeling by analyzing extensive hydrogeological data, thereby improving predictions and optimizing water resource utilization and allocation. This review investigates the application of machine learning for predicting various aspects, including precipitation, flood, runoff, soil moisture, evapotranspiration, groundwater level, and water quality. It provides a detailed summary of various algorithms, examines their technical strengths and weaknesses, and discusses their potential applications in water resource modeling. Finally, this paper anticipates future development trends in the application of machine learning to water resource modeling.

Concrete compressive strength testing is crucial for construction quality control. The traditional methods are both time-consuming and labor-intensive, while machine learning has been proven effective in predicting the compressive strength of concrete. However, current machine learning-based algorithms lack a thorough comparison among various models, and researchers have yet to identify the optimal predictor for concrete compressive strength. In this study, we developed 12 distinct machine learning-based regressors to conduct a thorough comparison and to identify the optimal model. To study the correlation between compressive strength and various factors, we conducted a comprehensive analysis and selected blast furnace slag, superplasticizer, age, cement, and water as the optimized factor subset. Based on this foundation, grid search and fivefold cross-validation were employed to establish the hyperparameters for each model. The results indicate that the Deepforest-based model demonstrates superior performance compared to the 12 models. For a more comprehensive evaluation of the model’s performance, we compared its performance with state-of-the-art models using the same independent testing dataset. The results demonstrate that our model achieving the highest performance (R² of 0.91), indicating its accurate prediction capability for concrete compressive strength.

As one of the most important post-transcriptional modifications, m6Am plays a fairly important role in conferring mRNA stability and in the progression of cancers. The accurate identification of the m6Am sites is critical for explaining its biological significance and developing its application in the medical field. However, conventional experimental approaches are time-consuming and expensive, making them unsuitable for the large-scale identification of the m6Am sites. To address this challenge, we exploit a CatBoost-based method, m6Aminer, to identify the m6Am sites on mRNA. For feature extraction, nine different feature-encoding schemes (pseudo electron–ion interaction potential, hash decimal conversion method, dinucleotide binary encoding, nucleotide chemical properties, pseudo k-tuple composition, dinucleotide numerical mapping, K monomeric units, series correlation pseudo trinucleotide composition, and K-spaced nucleotide pair frequency) were utilized to form the initial feature space. To obtain the optimized feature subset, the ExtraTreesClassifier algorithm was adopted to perform feature importance ranking, and the top 300 features were selected as the optimal feature subset. With different performance assessment methods, 10-fold cross-validation and independent test, m6Aminer achieved average AUC of 0.913 and 0.754, demonstrating a competitive performance with the state-of-the-art models m6AmPred (0.905 and 0.735) and DLm6Am (0.897 and 0.730). The prediction model developed in this study can be used to identify the m6Am sites in the whole transcriptome, laying a foundation for the functional research of m6Am.

This paper studies the flow characteristics and disk friction loss of the rear chamber in a centrifugal pump at a design flow condition with six values of the balance holes at diameters from 0 to 12 mm. The results show that the turbulent boundary layer in the rear chamber is greatly affected by the leakage flow. When the balance hole diameter increases, the flow characteristics of the rear chamber is mainly restricted by the mainstream flow field of the volute. However, when the balance hole diameter is larger than the design value, the disk friction loss of the rear chamber remains basically unchanged. On the contrary, when the balance hole diameter is smaller than the design value, the larger the balance hole diameter the smaller the friction loss of the disk in the rear chamber area. The results of this paper provide a reference for reducing axial force and stable operation of a centrifugal pump.

Accurately predicting the collapsibility coefficient of loess is crucial for mitigating the hazards associated with loess collapsibility in engineering projects, natural environment, and socio-economic activities. The traditional method for determining the collapsibility coefficient is time-consuming, labor-intensive, and expensive. In recent years, researchers have increasingly employed machine learning techniques to predict collapsibility coefficient and have obtained promising results. However, the process of hyperparameter optimization in previous studies was not sufficiently comprehensive, leading to suboptimal model performance. Therefore, in this study, Bayesian optimization was employed to fine-tune the hyperparameters of six different regressors, and the performance of these models was evaluated on both a training set and an independent testing set. The results demonstrated that the Random Forest-based model achieved the best performance, with R² values of 0.915 and 0.965 on the training and independent testing sets, respectively. These findings indicate that the proposed model is capable of reliably predicting the collapsibility coefficient of loess.