Deep learning-based segmentation of very high-resolution (VHR) satellite images is a significant task providing valuable information for various geospatial applications, specifically for land use/land cover (LULC) mapping. The segmentation task becomes more challenging with the increasing number and complexity of LULC classes. In this research, we generated a new benchmark dataset from VHR Worldview-3 images for twelve distinct LULC classes of two different geographical locations. We evaluated the performance of different segmentation architectures and encoders to find the best design to create highly accurate LULC maps. Our results showed that the DeepLabv3+ architecture with an ResNeXt50 encoder achieved the best performance for different metric values with an IoU of 89.46%, an F-1 score of 94.35%, a precision of 94.25%, and a recall of 94.49%. This design could be used by other researchers for LULC mapping of similar classes from different satellite images or for different geographical regions. Moreover, our benchmark dataset can be used as a reference for implementing new segmentation models via supervised, semi- or weakly-supervised deep learning models. In addition, our model results can be used for transfer learning and generalizability of different methodologies.

Scanned historical maps are available from different sources in various scales and contents. Automatic geographical feature extraction from these historical maps is an essential task to derive valuable spatial information on the characteristics and distribution of transportation infrastructures and settlements and to conduct quantitative and geometrical analysis. In this research, we used the Deutsche Heereskarte 1:200,000 Türkei (DHK 200 Turkey) maps as the base geoinformation source to construct the past transportation networks using the deep learning approach. Five different road types were digitized and labeled to be used as inputs for the proposed deep learning-based segmentation approach. We adapted U-Net++ and ResneXt50_32×4d architectures to produce multi-class segmentation masks and perform feature extraction to determine various road types accurately. We achieved remarkable results, with 98.73% overall accuracy, 41.99% intersection of union, and 46.61% F1 score values. The proposed method can be implemented in DHK maps of different countries to automatically extract different road types and used for transfer learning of different historical maps.

With the increased amount of digitized historical documents, information extraction from them gains pace. Historical maps contain valuable information about historical, geographical and economic aspects of an era. Retrieving information from historical maps is more challenging than processing modern maps due to lower image quality, degradation of documents and the massive amount of non-annotated digital map archives. Convolutional Neural Networks (CNN) solved many image processing challenges with great success, but they require a vast amount of annotated data. For historical maps, this means an unprecedented scale of manual data entry and annotation. In this study, we first manually annotated the Third Military Mapping Survey of Austria-Hungary historical map series conducted between 1884 and 1918 and made them publicly accessible. We recognized different road types and their pixel-wise positions automatically by using a CNN architecture and achieved promising results.

Automatic road extraction from historical maps is an important task to understand past transportation conditions and conduct spatiotemporal analysis revealing information about historical events and human activities over the years. This research aimed to propose the ideal architecture, encoder, and hyperparameter settings for the historical road extraction task. We used a dataset including 7076 patches with the size of $256 \times256$ pixels generated from scanned historical Deutsche Heereskarte 1:200 000 Türkei (DHK 200 Turkey) maps and their corresponding digitized ground truth masks for five different roads types. We first tested the widely used Unet++ and Deeplabv3 architectures. We also evaluated the contribution of attention models by implementing Unet++ with the concurrent spatial and channel-squeeze and excitation block and multiscale attention net. We achieved the best results with split-attention network (Timm-resnest200e) encoder and Unet++ architecture, with 98.99% overall accuracy, 41.99% intersection of union, 51.41% precision, 69.7% recall, and 57.72% F1 score values. Our output weights could be directly used for the inference of other DHK maps and transfer learning for similar or different historical maps. The proposed architecture could also be implemented in different road extraction studies.

Agricultural land abandonment is a globally significant threat to the sustenance of economic, ecological, and social balance. Although the driving forces behind it can be multifold and versatile, rural depopulation and urbanization are significant contributors to agricultural land abandonment. In our chosen case study, focusing on two locations, Ruen and Stamboliyski, within the Plovdiv region of Bulgaria, we use aerial photographs and satellite imagery dating from the 1950s until 1980, in connection with official population census data, to assess the magnitude of agricultural abandonment for the first time from a remote sensing perspective. We use multi-modal data obtained from historical aerial and satellite images to accurately identify Land Use Land Cover changes. We suggest using the rubber sheeting method for the geometric correction of multi-modal data obtained from aerial photos and Key Hole missions. Our approach helps with precise sub-pixel alignment of related datasets. We implemented an iterative object-based classification approach to accurately map LULC distribution and quantify spatio-temporal changes from historical panchromatic images, which could be applied to similar images of different geographical regions.

Historical manuscripts and archival documentation are handwritten texts which are the backbone sources for historical inquiry. Recent developments in the digital humanities field and the need for extracting information from the historical documents have fastened the digitization processes. Cutting edge machine learning methods are applied to extract meaning from these documents. Page segmentation (layout analysis), keyword, number and symbol spotting, handwritten text recognition algorithms are tested on historical documents. For most of the languages, these techniques are widely studied and high performance techniques are developed. However, the properties of Arabic scripts (i.e., diacritics, varying script styles, diacritics, and ligatures) create additional problems for these algorithms and, therefore, the number of research is limited. In this research, we first automatically spotted the Arabic numerals from the very first series of population registers of the Ottoman Empire conducted in the mid-nineteenth century and recognized these numbers. They are important because they held information about the number of households, registered individuals and ages of individuals. We applied a red color filter to separate numerals from the document by taking advantage of the structure of the studied registers (numerals are written in red). We first used a CNN-based segmentation method for spotting these numerals. In the second part, we annotated a local Arabic handwritten digit dataset from the spotted numerals by selecting uni-digit ones and tested the Deep Transfer Learning method from large open Arabic handwritten digit datasets for digit recognition. We achieved promising results for recognizing digits in these historical documents.