A GIS-portal platform from the data perspective to energy hub digitalization solutions- A review and a case study

The emergence of Geographic Information Systems (GIS) web platforms provides unique opportunities for human societies. GIS web platform technology has a two-way function, utilizing data obtained from physical and virtual environments to create harmony between the two. This review and case study paper examines the recent development and implementation of GIS web technology, focusing on urban areas and city scales. Firstly, this article reviews technology trends in online GIS web platform tools by identifying key features and applications, including their role in decision-making support. Secondly, it describes the GIS-Web platform, data sharing framework, the end-user services integrated, case study and project overview, platform digitalization as next generation. Thirdly, a new energy data portal called "NRGYHUB" is introduced for municipal urban areas in Västerås City, Sweden. This GIS portal platform provides hourly data from thousands of energy meters, collected from electrical and heating energy networks to develop, maintain, and showcase a collection of city-wide GIS tools that assist in creating, implementing, and managing innovative services for urban planning in Västerås City. Additionally, this paper presents a Geospatial Artificial Intelligence (GeoAI) approach for generating wind power projection maps using Machine Learning (ML) models which collectively aim to provide insightful wind power forecasts under the effects of climate change focusing on Västerås. Time series data for each grid cell served as inputs for the Radial Basis Functions (RBF) models, incorporating wind speed projections from the Coupled Model Intercomparison Project Phase 6 (CMIP6) along with other influential variables, such as pressure gradient, temperature gradient, humidity, and Digital Elevation Model (DEM) data. The performance of the ML models was rigorously evaluated using multiple statistical metrics, including bias, Mean Absolute Error (MAE), Correlation Coefficient (Corr), Mean Error (ME), and Root Mean Square Error (RMSE). These metrics enabled a thorough assessment of the model's accuracy and bias-correction capabilities, ultimately improving the reliability of wind speed projections for the study area.