Miloš Kovačević

Rapid and accurate post-earthquake damage assessment is critical for effective disaster response and enabling sustainable community recovery. This study addresses the urgent need for timely and precise quantification of earthquake-induced building damage, moving beyond simple detection, to inform actionable engineering decisions. It explores AI-driven image classification to expedite damage evaluation by identifying damaged buildings from post-disaster photos much faster than conventional methods. A total of 154,380 indoor image patches (224 × 224 pixels) from photos of buildings affected by the 2020 M6.4 Petrinja, Croatia earthquake, were compiled. These patches include both close-up cracks and wider building context. Two convolutional neural networks (ResNet-18 and ConvNeXt-Tiny) were trained on the patch dataset for binary damage classification. Additionally, large vision-language model (VLM) Gemma 3 27B was evaluated in a zero-shot binary classification setting by providing it with a descriptive prompt to classify each patch as damaged or undamaged. ConvNeXt-Tiny achieved the highest performance, with a macro F1-score of 0.849 and a damaged-class F1-score of 0.731, slightly outperforming ResNet-18. Gemma 3 27B achieved a macro F1-score of approximately 0.6 but a damaged-class F1-score of 0.366, with many false positives. Integrating such a granular approach into rapid loss assessment frameworks significantly enhances decision-making capabilities and post-disaster recovery efforts, providing a more detailed understanding of structural integrity across affected areas.

This article describes a teaching strategy that synergizes computing and management, aimed at the running of complex projects in industry and academia, in the areas of civil engineering, physics, geosciences, and a number of other related fields. The course derived from this strategy includes four parts: (a) Computing with a selected set of modern paradigms—the stress is on Control Flow and Data Flow computing paradigms, but paradigms conditionally referred to as Energy Flow and Diffusion Flow are also covered; (b) Project management that is holistic—the stress is on the wide plethora of issues spanning from the preparation of project proposals, all the way to incorporation activities to follow after the completion of a successful project; (c) Examples from past research and development experiences—the stress is on experiences of leading experts from academia and industry; (d) Student projects that stimulate creativity—the stress is on methods that educators could use to induce and accelerate the creativity of students in general. Finally, the article ends with selected pearls of wisdom that could be treated as suggestions for further elaboration.

This article presents a taxonomy and represents a repository of open problems in computing for numerically and logically intensive problems in a number of disciplines that have to synergize for the best performance of simulation-based feasibility studies on nature-oriented engineering in general and civil engineering in particular. Topics include but are not limited to: Nature-based construction, genomics supporting nature-based construction, earthquake engineering, and other types of geophysical disaster prevention activities, as well as the studies of processes and materials of interest for the above. In all these fields, problems are discussed that generate huge amounts of Big Data and are characterized with mathematically highly complex Iterative Algorithms. In the domain of applications, it has been stressed that problems could be made less computationally demanding if the number of computing iterations is made smaller (with the help of Artificial Intelligence or Conditional Algorithms), or if each computing iteration is made shorter in time (with the help of Data Filtration and Data Quantization). In the domain of computing, it has been stressed that computing could be made more powerful if the implementation technology is changed (Si, GaAs, etc.…), or if the computing paradigm is changed (Control Flow, Data Flow, etc.…).

The representation of land use change (LUC) is often achieved by using data-driven methods that include machine learning (ML) techniques. The main objectives of this research study are to implement three ML techniques, Decision Trees (DT), Neural Networks (NN), and Support Vector Machines (SVM) for LUC modeling, in order to compare these three ML techniques and to find the appropriate data representation. The ML techniques are applied on the case study of LUC in three municipalities of the City of Belgrade, the Republic of Serbia, using historical geospatial data sets and considering nine land use classes. The ML models were built and assessed using two different time intervals. The information gain ranking technique and the recursive attribute elimination procedure were implemented to find the most informative attributes that were related to LUC in the study area. The results indicate that all three ML techniques can be used effectively for short-term forecasting of LUC, but the SVM achieved the highest agreement of predicted changes.

During a construction project lifecycle, an extensive corpus of unstructured or semistructured text documents is generated. The nature of unstructured sources impedes users’ acquisition, analysis, and reuse of relevant information in an integral form, leading to a possible reduction in project performance because of untimely or inadequate decisions. This paper explores the representation of information from unstructured documents in the form of a key-phrase network, intended to provide users with the possibility to visualize and analyze valuable project facts with less effort. A network of key phrases automatically extracted from various types of unstructured documents, with relations based on contextual similarity, was implemented as a graph database, enabling project participants to extract and visualize various patterns in data. With the objective of constructing a domain-independent key-phrase network with minimal expert involvement, an approach to detect key phrases in a multilingual environment was examined by using measures of association between words while avoiding text content from less informative contexts. A possible application is demonstrated using key-phrase networks generated from two complex international construction projects.

Megaprojects are often associated with poor delivery performance and poor benefits realization. This article provides a method of identifying, in a quantitative and rigorous manner, the characteristics related to project management success in megaprojects. It provides an investigation of how stakeholders can use this knowledge to ensure more effective design and delivery for megaprojects. The research is grounded in 44 mega-projects and a systematic, empirically based methodology that employs the Fisher's exact test and machine learning techniques to identify the correlation between megaprojects’ characteristics and performance, paving the way to an understanding of their causation.

Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection and optimal parameters choices. Therefore the main objective of this study is to present and investigate the SVM technique for modeling urban land use change. The SVM model building procedure is presented together with the detailed evaluation of the output results with respect to the choice of datasets, attributes and the change of SVM parameters. Geospatial datasets containing nine land use classes and spatial attributes for the Municipality of Zemun, Republic of Serbia were used for years 2001, 2003, 2007 and 2011. The Correlation‐based Feature Subset method, kappa coefficient, Area Under Receiver Operating Characteristic Curve (AUC) and kappa simulation were used to perform the model evaluation and compare the model outputs with the real land use datasets. The obtained results indicate that the SVM‐based models perform better when implementing balanced data sampling, reduced data sets to informative subsets of attributes and properly identify the optimal learning parameters.