Deep Learning algorithms are used by many different disciplines for various purposes, thanks to their ever-developing data processing skills. Convolutional neural network (CNN) are generally developed and used for this integration purpose. On the other hand, the widespread usage of Unmanned Aerial Vehicles (UAV) enables the collection of aerial photographs for Photogrammetric studies. In this study, these two fields were brought together and it was aimed to find the equivalents of the objects detected from the UAV images using deep learning in the global coordinate system and to evaluate their accuracy over these values. For these reasons, v3 and v4 versions of the YOLO algorithm, which prioritizes detecting the midpoint of the detected object, were trained in Google Colab’s virtual machine environment using the prepared data set. The coordinate values read from the orthophoto and the coordinate values of the midpoints of the objects, which were derived according to the estimations made by the YOLO-v3 and YOLOV4-CSP models, were compared and their spatial accuracy was calculated. Accuracy of 16.8 cm was obtained with the YOLO-v3 and 15.5 cm with the YOLOv4-CSP. In addition, the mAP value was obtained as 80% for YOLOv3 and 87% for YOLOv4-CSP. F1-score is 80% for YOLOv3 and 85% for YOLOv4-CSP.

On February 6, 2023, the earthquakes centered on Kahramanmaraş-Pazarcık and Kahramanmaraş-Elbistan affected several provinces in the region and generated a vast amount of demolition waste. This study aims to develop a site selection model for the most suitable landfill areas after the earthquake using open-source Geographic Information Systems (GIS) software and the Best-Worst Method (BWM). First, the study identifies decision criteria with a Delphi expert panel. Next, it determines the weights using the BWM based on pairwise comparison. Spatial data of the determinants were obtained from open data portals, and proximity, overlay, and slope analyses were carried out for the disaster region. Combining the output data layer of each criterion, a suitability map of the landfills was produced. As a result, 36,2% (29,826 kms square) of the study area was classified as suitable and very suitable. In this study, a cloud GIS-based decision support platform was developed to act quickly and initiate recovery processes within the scope of disaster management of the destructive earthquake. The suitability map and potential sites were shared with the responsible teams in the disaster area so that the potential sites could be displayed on the map and the suitable areas could be navigated on appropriate routes. The findings of the study revealed that the use of open data and cloud GIS framework in the disaster management process enables quick, reliable, and cost-effective actions in the immediate aftermath of disasters.

In this study, the static and kinematic positioning performance of the Garmin GPSMAP 66sr handheld GNSS receiver has been tested. For the static test, GNSS data was collected for 24 h and divided into shorter sessions of 1, 2, and 4 h to assess the performance of the receiver as a function of occupation time. The whole and subgroup data were processed by the relative method for different satellite constellations using three reference stations, to form a very short (45 m), short (5.1 km), and relatively long (73.2 km) baselines. For the kinematic test, the data was collected for approximately 1 h and processed with the relative method. Additionally, the whole and subgroup static and kinematic GNSS data of the Garmin receiver were also processed with the Canadian Spatial Reference System-Precise Point Positioning (CSRS-PPP) online service. All Garmin static and kinematic solutions (both relative and PPP) were compared with those calculated by the geodetic receiver. The overall static results show that the Garmin GPSMAP 66sr handheld receiver provides accuracy in a few centimeters with the relative method when integer ambiguities were correctly fixed and in the decimeter-to-meter level using the PPP technique. For the kinematic scenario, the results were relatively poor within the level of decimeters with the relative method while the level of meters with the PPP technique.