Symbolic regression techniques are constantly gaining ground in materials informatics as the machine learning counterpart capable of providing analytical equations exclusively derived from data. When the feature space is unknown, unsupervised learning is incorporated to discover and explore hidden connections between data points and may suggest a regional solution, specific for a group of data. In this work, we develop a Lennard–Jones fluid descriptor based on density and temperature values and investigate the similarity between data corresponding to diffusion coefficients. Descriptions are linked with the aid of clustering algorithms, which lead to fluid groups with similar behavior, bound to physical laws. Keeping in mind that the fluid data space goes over the gas, liquid, and supercritical states, we compare clustering results to this categorization and found that the proposed methods can detect the gas and liquid states, while distinct supercritical region characteristics are discovered, where fluid density and temperature affect the diffusion coefficient in a more complex way. The incorporation of symbolic regression algorithms on each cluster provides an in-depth investigation on fluid behavior, and regional expressions are proposed.

Buildings are responsible for around 30% and 42% of the consumed energy at the global and European levels, respectively. Accurate building power consumption estimation is crucial for resource saving. This research investigates the combination of graph convolutional networks (GCNs) and long short-term memory networks (LSTMs) to analyze power building consumption, thereby focusing on predictive modeling. Specifically, by structuring graphs based on Pearson’s correlation and Euclidean distance methods, GCNs are employed to discern intricate spatial dependencies, and LSTM is used for temporal dependencies. The proposed models are applied to data from a multistory, multizone educational building, and they are then compared with baseline machine learning, deep learning, and statistical models. The performance of all models is evaluated using metrics such as the mean absolute error (MAE), mean squared error (MSE), R-squared (R²), and the coefficient of variation of the root mean squared error (CV(RMSE)). Among the proposed computation models, one of the Euclidean-based models consistently achieved the lowest MAE and MSE values, thus indicating superior prediction accuracy. The suggested methods seem promising and highlight the effectiveness of GCNs in improving accuracy and reliability in predicting power consumption. The results could be useful in the planning of building energy policies by engineers, as well as in the evaluation of the energy management of structures.

Understanding the underlying processes and extracting detailed characteristics of rivers is critical and has not yet been fully developed. The purpose of this study was to examine the performance of non-linear time series methods on environmental data. Specifically, we performed an analysis of water level measurements, extracted from sensors, located on specified stations along the Nestos River (Greece), with Recurrence Plots (RP) and Recurrence Quantification Analysis (RQA) methods. A more detailed inspection with the sliding windows (epoqs) method was applied on the Recurrence Rate, Average Diagonal Line and Trapping Time parameters, with results showing phase transitions providing useful information about the dynamics of the system. The suggested method seems to be promising for the detection of the dynamical transitions that can characterize distinct time windows of the time series and reveals information about the changes in state within the whole time series. The results will be useful for designing the energy policy investments of producers and also will be helpful for dam management assessment as well as government energy policy.

This study investigates the dynamical behavior of hydrological time series using nonlinear analysis methods, with emphasis on the Visual Boundary Recurrence Plots (VBRPs) approach. Water level data from three monitoring stations along the Nestos River (Greece) are analyzed to uncover underlying system dynamics and variability across different hydrological settings. The VBRP methodology is employed to identify and quantify recurrent and non-recurrent structures in the time series, enabling the detection of temporal persistence, fluctuations, and transitions between system states. The derived VBRP rates reveal significant differences among the examined stations, reflecting variations in basin characteristics such as topography, flow organization, and storage capacity. Specifically, the Temenos (E6) station exhibits higher recurrence-related structure, indicating a more coherent and rapidly responding system, while the Arkoudorema (E8) station shows increased non-recurrent behavior, suggesting stronger fluctuations associated with tributary dynamics. The Papades (E7) station displays intermediate characteristics. The results demonstrate that VBRP provides physically interpretable insights into hydrological dynamics and constitutes a robust tool for the analysis of complex environmental time series, complementing traditional nonlinear approaches.