Urban change detection (CD) is crucial for informed decision-making but faces various challenges, including complex features, rapid changes, and extensive human interventions. These challenges underscore the urgent need for innovative multiclass CD (MCD) techniques that extensively incorporate deep learning (DL). Despite several successes achieved with the DL-based MCD methods, still certain shortcomings persist, including the disregard for spatial principles, which significantly hinders the seamless integration of geoscience-knowledge and artificial-intelligence. In this article, a novel DL model known as the position-aware graph-convolutional neural network (CNN) fusion network (PGCFN) is introduced, integrating spatial position encoding to effectively detect urban changes. The model’s first part encodes geospatial positions following Tobler’s first law (TFL) of geography. It then integrates encoded positions into an MCD model, combining a graph attention network (GAT) with a CNN to enhance performance. The model was tested on 0.5-m resolution remote sensing (RS) images, achieving an impressive minimum mean intersection over union (MIoU) score of 91.20%. Additionally, the model’s position-aware graph attention module exhibited a strong emphasis on geographic proximity when evaluating connections between superpixels. Overall, these findings affirm that our model could effectively addresses urban CD challenges and significantly enhances the integration of geoscience knowledge and artificial intelligence (AI).

Digital systems storing cadastral data in vector format are considered effective due to their ability of offering interactive services to citizens and other land-related systems. The adoption of such systems is ubiquitous, but when adopted, they create two non-compatible systems with paper-based cadastral systems whose information needs to be digitised. This study proposes a new approach that is fast and accurate for transforming paper-based cadastral data into digital systems. The proposed method involves deep-learning techniques of the LCNN and ResNet-50 for detecting cadastral parcels and their numbers, respectively, from the cadastral plans. It also contains four functions defined to speed up transformations and compilations of the cadastral plan’s data in digital systems. The LCNN is trained and validated with 968 samples. The ResNet-50 is trained and validated with 106,000 samples. The Structural-Average-Precision (sAP10) achieved with the LCNN was 0.9057. The Precision, Recall and F1-Score achieved with the ResNet-50 were 0.9650, 0.9648 and 0.9649, respectively. These results confirmed that the new method is accurate enough for implementation, and we tested it with a huge set of data from Tanzania. Its performance from the experimented data shows that the proposed method could effectively transform paper-based cadastral data into digital systems.

Past and current cadastral records are among the most valuable information that different countries need to solve land management and planning problems. However, many countries still face critical challenges in adopting modern temporal cadastral systems, including a sound integration of time constructs, efficient data integration and representation methods in the designed models. This research developed a new temporal GIS model to manage spatial and non-spatial temporal cadastral data, namely cadastral parcels, land-use and land-ownerships. Three-time dimensions defined by decision and valid and transaction times were formulated to qualify parcels data. A hybrid approach fusing on the Base State with Amendment and Space-Time Composite models is used to store significant parcel changes and their relationships in two interdependent sub-databases. We used administrative plot identifiers to associate with land use and ownership records, experiencing distinct temporal variations in the third sub-database within the same main repository. We experimented our model with data from Tanzania, and the results from queries demonstrate that the designed model can store all three temporal cadastral data and track their variations semantically and effectively. This model is very useful for storing cadastral parcels, reasons, events, and the transformed parcels’ values to improve decision-making processes.

Compared with traditional magnetic disks, flash memory has many advantages and has been used as external storage media for a wide spectrum of electronic devices (such as PDA, MP3, digital camera and mobile phone). As the capacity increases and price drops, it looks like a perfect alternative for magnetic disks. However, due to hardware limitations of flash memory, techniques including storage subsystem and indexing originally designed for magnetic disks can not run smoothly in a flash memory without any modification. In this paper we explore problems of indexing flash-resided data and present a new dynamical hash index for flash memory in two schemas. The analysis and experimental results validate the efficiency of our design.