Understanding how built structures and urban vegetation jointly relate to population patterns is increasingly important for sustainable urban planning. This study used airborne LiDAR data to analyze three-dimensional urban morphology across Zagreb, Croatia, at neighborhood and district scales. A 1 m nDSM and classified rasters were used to derive canopy, building, height, volumetric, and built–vegetation balance metrics. Spatial clustering was assessed using Moran’s I, LISA, and Getis–Ord Gi*, while relationships with population density were evaluated using correlation and spatial regression models. At the neighborhood level, canopy cover ranged from 4.5% to 84.7%, while UMI ranged from 0.002 to 10.368. UMI showed significant spatial clustering (Moran’s I = 0.457, p = 0.001), with 24 high–high and 64 low–low clusters. Composite balance metrics outperformed individual vegetation or building indicators; logUMI provided the strongest performance for log-transformed population-density models, with SLM pseudo-R2 = 0.903. Agreement assessment showed high consistency for canopy cover (R2 = 0.997), while building height agreement was weaker for global datasets. Results indicate that transformed built–vegetation balance metrics provide useful complementary indicators for describing urban morphology and population density patterns.

Road traffic fatalities are a significant concern worldwide, as highlighted by data from the World Health Organization (WHO) and other international organizations. One approach to enhancing road safety is through the assessment of specific characteristics or features that contribute to the overall safety condition of roads. The International Road Safety Assessment Program (iRAP) identifies several attributes that have a direct impact on road safety. Some of these attributes can be collected from satellite imagery. One of first steps in using satellite imagery as source for road attributes collection is road extraction. Quality road extraction can provide a quality base for detection of road attributes. In this paper Random forests, Extreme Gradient Boosting and U-net algorithms were analyzed to get insight into which one is most suitable for road extraction. Analysis was performed on very high-resolution satellite imagery with four spectral bands and spatial resolution of 0.3m. Analysis has shown that U-net outperformed Random forests and XGBoost in each of evaluation measures and it is suggested as best option for road extraction as support of road infrastructure assessment process.

The European Commission (EC) has published a European Union (EU) Road Safety Framework for the period 2021 to 2030 to reduce road fatalities. In addition, the EC with the EU Directive 2019/1936 requires a much more detailed recording of road attributes. Therefore, automatic detection of school routes, four classes of crosswalks, and divided carriageways were performed in this paper. The study integrated satellite imagery as a data source and the Yolo object detector. The satellite Pleiades Neo 3 with a spatial resolution of 0.3 m was used as the source for the satellite images. In addition, the study was divided into three phases: vector processing, satellite imagery processing, and training and evaluation of the You Only Look Once (Yolo) object detector. The training process was performed on 1951 images with 2515 samples, while the evaluation was performed on 651 images with 862 samples. For school zones and divided carriageways, this study achieved accuracies of 0.988 and 0.950, respectively. For crosswalks, this study also achieved similar or better results than similar work, with accuracies ranging from 0.957 to 0.988. The study also provided the standard performance measure for object recognition, mean average precision (mAP), as well as the values for the confusion matrix, precision, recall, and f1 score for each class as benchmark values for future studies.

The United Nations (UN) stated that all new roads and 75% of travel time on roads must be 3+ star standard by 2030. The number of stars is determined by the International Road Assessment Program (iRAP) star rating module. It is based on 64 attributes for each road. In this paper, a framework for highly accurate and fully automatic determination of two attributes is proposed: roadside severity-object and roadside severity-distance. The framework integrates mobile Lidar point clouds with deep learning-based object detection on road cross-section images. The You Only Look Once (YOLO) network was used for object detection. Lidar data were collected by vehicle-mounted mobile Lidar for all Croatian highways. Point clouds were collected in .las format and cropped to 10 m-long segments align vehicle path. To determine both attributes, it was necessary to detect the road with high accuracy, then roadside severity-distance was determined with respect to the edge of the detected road. Each segment is finally classified into one of 13 roadside severity object classes and one of four roadside severity-distance classes. The overall accuracy of the roadside severity-object classification is 85.1%, while for the distance attribute it is 85.6%. The best average precision is achieved for safety barrier concrete class (0.98), while the worst AP is achieved for rockface class (0.72).

Unmanned Aerial Vehicles (UAVs) represent easy, affordable, and simple solutions for many tasks, including the collection of traffic data. The main aim of this study is to propose a new, low-cost framework for the determination of highly accurate traffic flow parameters. The proposed framework consists of four segments: terrain survey, image processing, vehicle detection, and collection of traffic flow parameters. The testing phase of the framework was done on the Zagreb bypass motorway. A significant part of this study is the integration of the state-of-the-art pre-trained Faster Region-based Convolutional Neural Network (Faster R-CNN) for vehicle detection. Moreover, the study includes detailed explanations about vehicle speed estimation based on the calculation of the Mean Absolute Percentage Error (MAPE). Faster R-CNN was pre-trained on Common Objects in COntext (COCO) images dataset, fine-tuned on 160 images, and tested on 40 images. A dual-frequency Global Navigation Satellite System (GNSS) receiver was used for the determination of spatial resolution. This approach to data collection enables extraction of trajectories for an individual vehicle, which consequently provides a method for microscopic traffic flow parameters in detail analysis. As an example, the trajectories of two vehicles were extracted and the comparison of the driver's behavior was given by speed-time, speed-space, and space-time diagrams.

Main goal of the most breeding programs is to develop highly adaptive hybrids in various environments, and the most important limitation are complex interactions between genotype, environment and management. Every hybrid breeding program follows certain strategy for new hybrid development. One possible strategy is to develop hybrids with lower adaptability, achieving best performance in “high input” environments (breeding for “race-horses”). However, another approach is to breed for hybrids with higher adaptability and stable performance across a wide range of environments (breeding for “work-horses”). High stability needs to be accompanied by high yield performance to insure profits, so stability should be monitored along with performance in breeding trials. Aim of this research was to analyze the new germplasm developments and their performances in the pre-registration trials in Turkey by the means of BLUP and GGE models. Heritability estimates for grain yield ranged from 0.58 to 0.85, and relative stability of all hybrids and checks is detected across all years. Cause of the high estimates of G×L interaction were crossovers of genotype performances across locations. The location Altinova was the least stable location across years. One hybrid was selected as a future check based on stability parameters across environments. As G×E interaction remains the greatest challenge in modern maize breeding, more research is needed in this field. Therefore mixed-model based approach is a valuable tool for analysis of genotype performances in maize breeding trials.

The western corn rootworm (Diabrotica virgifera virgifera LeConte; WCR) is a serious maize pest in Croatia. The species was first registered in Europe in the early 1990s and since then became one of the most dangerous maize pests, especially in parts of Central and Southeast Europe. Larvae that feed on the maize roots cause the most serious damages in maize fields. Management of this pest is difficult and expensive, with possible serious impact on the environment. Native (or host-plant) resistance of maize against WCR could provide new economically and ecologically sustainable options in WCR management. Main goal of this study was to assess the variability of maize germplasm, correlations among resistance traits, and detect potential sources of resistance that could be used in breeding programs in order to develop hybrids with higher level of resistance against WCR. To our knowledge, the first native resistant hybrid is yet to be registered. Results showed great variability of estimated germplasm. Effect of the genotype was significant in all environments, as well as many interactions between genotype and the environment. Significant interactions emphasize the importance of the environment in WCR native resistance research. Significant positive correlations among all traits were detected. Several inbred lines were selected as a potentially useful germplasm for resistance breeding programs.

Nine maize lines, commonly used as female parents of maize hybrid (B1=?2-48; B2=?1767/99; B3=?87-24; B4=?135-88, B5=?84-28; B6=?84-44; B7=?438-95; B8=?30-8; B9=?B-73) were grown under field conditions on Podgorac acid soil in Osijek-Baranya County for two growing seasons (2006 and 2007). The ear-leaves at flowering and grain at maturity were taken from each basic plot (14 m2) for chemical analysis with inductively coupled plasma atomic emission spectroscopy (ICP-OES). Average concentrations (2-year means: g kg-1 in dry matter) were as follows: 3.21 and 3.00 (P), 20.8 and 3.45 (K), 6.60 and 0.05 (Ca), 2.44 and 1.04 (Mg) for leaves and grain, respectively. Differences among genotypes were from 2.69 to 3.95 and from 2.70 to 3.57 (P), from 18.0 to 23.3 and from 3.03 to 3.71 (K), from 5.45 to 8.02 and from 0.04 to 0.07 (Ca), from 1.35 to 3.09 and from 0.84 to 1.36 (Mg), for leaves and grain, respectively. Specifies of leaf composition of individual genotypes were as follows: B1 (the highest Ca and Mg), B2 (the highest P), B4 (the lowest Ca, Mg and P), B6 (the highest K) and B7 (the lowest K). Grain composition was mainly in accordance with specifies of leaf composition. Very high correlation in maize mineral composition under identical environmental conditions for nine genotypes between two years (0.97***, 0.97*** and 0.91*** for K, Ca and Mg, respectively) are indication of high hereditary effects, while P was more under environmental impact (r = 0.43). Significant correlations were found between grain-P and grain-K (0.55*), grain-Ca (0.49*) and grain-Mg (0.86***), grain-Ca and grain-Mg (0.54*). However, regarding mineral composition of leaves, only leaf-Ca and leaf-P had significant correlation (-0.46*).