The Tisza River is the longest tributary of the Danube, draining the eastern part of the Carpathian Basin (Central Europe). Five countries share its catchment with different waste production and management practices. Large amounts of waste, including macroplastics (MaPs), are washed into the river. Some of the litter is trapped by the riparian vegetation forming litter accumulations. The study aimed to map the amount of litter by a citizen science program and remote sensing data and to compare the MaP data to the amount of microplastic fragments in sediments. Volunteers reported 3216 riverine litter accumulations from five countries along the entire length of the Tisza (2016–2022). The results suggest that low flow conditions (e.g., impoundment by dams) support litter and MaP trapping. The volume of large accumulations registered by the citizens showed a good correlation with the area of drifting litter revealed on Sentinel-2 images (2016–2022) using machine learning algorithms. Though the MaPs probably fragmentate during their fluvial transport, no clear connection was found between the volume of litter accumulations and the mean microplastic fragment content of sediments (2019–2022). The “Clean Tisza Map“ reveals the high degree of stranded pollutants along rivers and supports public cleanup activities.

Monitoring the condition of railway infrastructure is essential for maintaining safety standards and preventing accidents. The regular inspections required for this task are still typically carried out in many countries with costly and time-consuming on-site human inspections. LiDAR point clouds collected by mobile laser scanning (MLS) already proved to be suitable for recognizing important railroad infrastructure elements, such as cables and the rail tracks. However, the computational requirement for processing large data sets like these often extremely dense point clouds is still a challenge nowadays, resulting in longer execution time than practically applicable. In our research, we have implemented and comparatively analyzed railroad fragmentation and object segmentation algorithms with the focus on robustness and high effectiveness: prioritizing automation and prerequisite reduction (e.g. the spatial relationship between the position of the railway track and the overhead contact line). These aspects also enable the easy parallelization for the processing of larger railroad segments.

Developers' fluctuation in the lifetime of a software product might deteriorate the understanding of the source code to a level where developer expertise of some modules drops to a dangerously low point. It is important for the project management to identify such critical modules to avoid complete knowledge loss. This paper presents a developer-centered static analysis tool that is intended to show individual expertise in large software projects. The expertise value is computed for each file through repository mining of the version control system of the project. The calculated value is based on the quality of commits per developer. The results of the proposed method have been validated on the CodeChecker open-source project, comparing against the findings of a user questionnaire filled by developers of the project on their expertise.