This study is devoted to solving the problem of determining the career guidance of future university student using artificial intelligence systems. It is proposed Fully Connected Feed-Forward Neural Network (FNN) architecture and performed empirical modeling to create a Data Set. Model of artificial intelligence system allows evaluating the processes in an FNN during the execution of multi-label classification of professional areas. A method has been developed for the training process of a machine learning model, which reflects the internal connections between the components of an artificial intelligence system that allow it to “learn” from training data. To train the neural network, a data set of 29 input parameters and 23 output parameters was used; the amount of data in the set is 936 data lines. The software product was developed by Python and uses Keras, Numpy and Pandas libraries. Results of this research can be used to further improve the knowledge and skills necessary for successful professional realization.

This study is devoted to the development of an information system for creating digital twins of construction sites by integrating Building Information Modeling (BIM) technologies and artificial intelligence systems. An artificial intelligence system has been developed that combines the Convolutional Neural Network (CNN) named “You Only Look Once” v3 (YOLOv3) and Feed-Forward Neural Network (FFNN) architectures as a comprehensive mechanism for detecting, classifying, and evaluating individual components, objects, systems and processes of the construction project at all stages of its life cycle. The article describes the inclusion of the Internet of Things (IoT) and Big Data Technologies for recognizing the physical representation of the large-scale array of construction objects used on a construction site in real-time. The effectiveness of identifying the correspondence of a set of BIM-model attributes that provide the circumstances for creating a digital twin of the construction site is determined. The reliability of object recognition by the YOLOv3 model is proved, which is confirmed by the map indicator – 90.04%, which additionally correlates the FFNN model with attributes of the reference BIM model. The results of this study can be used to further improve the concept of developing digital twins using other relevant and key components of the construction project and the latest information technologies.

This study presents a multi-stage approach for building object models (BOMs) on a construction site, aimed at creating an “evolutionary” digital twin. The integration of building information modeling (BIM) and artificial intelligence is used to achieve this goal, with the use of photo modeling using moving cameras and the potential integration of IoT technologies also discussed. A comprehensive artificial intelligence system, combining Convolutional Neural Network (CNN) and Feed Forward Neural Network (FFNN) architectures, has been developed to detect, categorize, and evaluate BIM projects throughout their life cycle. The scalability prospects for point cloud and mesh models, as well as the use of big data technology to optimize the representation of the digital twin, are also addressed. The study determines the effectiveness of construction site conformance detection during the construction of a BIM model, providing consistency and a quantitative evaluation of the processes taking place on the construction site. The findings of this research can be used to enhance BIM modeling methods and concepts toward a multi-stage representation of the digital twin of the construction site.

Background: AI, IoT, and BIM technologies are revolutionizing the building business. This study applies these methods to the multi-stage categorization of construction site modeling items to create an “evolutionary” digital twin.Objective: Develop and test a BIM-AI method integrating CNN and FFNN architectures. The goals are BIM project identification, classification, and assessment throughout their life cycle.Methods: The approach uses moving cameras for picture modeling and IoT integration. Augmented reality and big data technologies explore the dynamic transformation of actual building structures into BIM representations. An AI system that analyzes construction site modeling items using CNN and FFNN is a major part of the study.Results: The article highlights the usefulness of site conformity detection during BIM model building, displaying consistency and quantifying ongoing operations. The study shows that scaling point cloud and mesh models and optimizing the “evolutionary” BIM project of the building site’s digital twin are promising.Conclusion: The findings of this study provide important insights and improve BIM modeling techniques, notably in creating a multi-stage “evolutionary” digital twin of the building site. This pioneering construction site modeling using BIM and AI opens the door to future developments and improvements.

This study focuses on the development of a multi-stage analysis of building object models (BOM) on a construction site for modeling an “evolutionary” digital twin, by integrating building information modeling (BIM) technology and an artificial intelligence system. The concepts of photo modeling of the construction site using a group of moving cameras were outlined, as well as the possibility of integrating IoT technologies. The dynamic transition of real building structures into intermediate BIM representations of digital twins was investigated, with the prospect of enabling augmented reality technology. An artificial intelligence system combining Convolutional Neural Network (CNN) and Feed Forward Neural Network (FFNN) architectures has been developed as a comprehensive mechanism for the detection, categorization, and evaluation of BIM projects at all stages of their life cycle. The paper addresses the scaling prospects for the development of point cloud and mesh models, as well as the use of big data technology while optimizing the representation of the “evolutionary” BIM project of the digital twin of the construction site. The effectiveness of site conformance detection during the step-by-step construction of a BIM model, which shows consistency and provides a quantitative assessment of the processes occurring on the site, has been determined. The results of this research can be used to improve BIM modeling methods and concepts, in particular towards a multi-stage “evolutionary” representation of the digital twin of the construction site.

Accurate estimation of long-term average (LTA) discharge is fundamental for water resource assessment, infrastructure planning, and hydrological modeling, yet it remains a significant challenge, particularly in data-scarce or ungauged basins. This study introduces an advanced machine learning framework to estimate long-term average discharge using globally available hydrological station metadata from the Global Runoff Data Centre (GRDC). The methodology involved comprehensive data preprocessing, extensive feature engineering, log-transformation of the target variable, and the development of multiple predictive models, including a custom deep neural network with specialized pathways and gradient boosting machines (XGBoost, LightGBM, CatBoost). Hyperparameters were optimized using Bayesian techniques, and a weighted Meta Ensemble model, which combines predictions from the best individual models, was implemented. Performance was rigorously evaluated using R², RMSE, and MAE on an independent test set. The Meta Ensemble model demonstrated superior performance, achieving a Coefficient of Determination (R²) of 0.954 on the test data, significantly surpassing baseline and individual advanced models. Model interpretability analysis using SHAP (Shapley Additive explanations) confirmed that catchment area and geographical attributes are the most dominant predictors. The resulting model provides a robust, accurate, and scalable data-driven solution for estimating long-term average discharge, enhancing water resource assessment capabilities and offering a powerful tool for large-scale hydrological analysis.