Despite a list of national and international efforts to harmonise data management procedures, the categorisation of space and time within datasets in marine spatial planning (MSP) has not been addressed so far. This paper proposes a conceptual framework to categorise the spatial and temporal dimensions of data used in MSP and introduces a method to jointly manage non-spatial information and spatial data in the same geographic information system (GIS). The presented categorisation provides easy and intuitive classifications for a more detailed and transparent data description of spatial and temporal data properties, which can be applied both in attribute tables and in metadata. It allows the differentiation of the vertical and the horizontal dimensions, enabling users to focus on operations taking place at specific parts of the marine environment. The categorisation with predefined attribute domains allows space and time based automatic analyses. The inclusion of non-spatial data within GIS repositories ensures the availability of all relevant data in one database minimising the risk of incomplete data. Overall, the framework provides effective steps towards a more coherent data management and subsequently may foster better use of information in MSP processes.
Accurate and reliable optical remote sensing image-based small-ship detection is crucial for maritime surveillance systems, but existing methods often struggle with balancing detection performance and computational complexity. In this paper, we propose a novel lightweight framework called HSI-ShipDetectionNet that is based on high-order spatial interactions and is suitable for deployment on resource-limited platforms, such as satellites and unmanned aerial vehicles. HSI-ShipDetectionNet includes a prediction branch specifically for tiny ships and a lightweight hybrid attention block for reduced complexity. Additionally, the use of a high-order spatial interactions module improves advanced feature understanding and modeling ability. Our model is evaluated using the public Kaggle and FAIR1M marine ship detection datasets and compared with multiple state-of-the-art models including small object detection models, lightweight detection models, and ship detection models. The results show that HSI-ShipDetectionNet outperforms the other models in terms of detection performance while being lightweight and suitable for deployment on resource-limited platforms.