The concept of data spaces has emerged as a structured, scalable solution to streamline and harmonize data sharing across established ecosystems. Simultaneously, the rise of AI services enhances the extraction of predictive insights, operational efficiency, and decision-making. Despite the potential of combining these two advancements, integration remains challenging: data spaces technology is still developing, and AI services require further refinement in areas like ML workflow orchestration and energy-efficient ML algorithms. In this paper, we introduce an integrated architectural framework, developed under the Green.Dat.AI project, that unifies the strengths of data spaces and AI to enable efficient, collaborative data sharing across sectors. A practical application is illustrated through a smart farming use case, showcasing how AI services within a data space can advance sustainable agricultural innovation. Integrating data spaces with AI services thus maximizes the value of decentralized data while enhancing efficiency through a powerful combination of data and AI capabilities.

Spatio-temporal forecasting is a rapidly evolving field, accelerated by the increasing accessibility of sensoring infrastructure and computational hardware, capable of processing the large amount of sampled data. Applications of spatio-temporal forecasts range from traffic, weather, air pollution forecasting and others. Emerging technologies employ deep learning architectures, such as graph, convolutional, recurrent and transformer neural networks. While the state-of-the-art methods provide accurate time series predictions, they are typically limited to providing forecasts only for the direct locations of sampling, whereas coverage of the entire area is often desired by the applications. In this work, we propose a method that addresses this challenge and improves on the shortcomings of related works, which have already tackled the task. The proposed graph convolutional recurrent neural network based method provides forecasts for arbitrary geolocations without available measurement data, formulating predictions based on contextual information of target geolocations and the time series data of nearby measurement geolocations. We evaluate the method on three real-world datasets from meteorological, traffic and air pollution domains, and gauge its performance against the state-of-the-art spatio-temporal forecasting methods. The proposed method achieves 12.26 %, 66.97 % and 42.89 % improvements in the mean absolute percentage errors on the three aforementioned datasets, compared to the best performing state-of-the-art method GConvGRU.

This article introduces a new iterative approach to explainable feature learning. During each iteration, new features are generated, first by applying arithmetic operations on the input set of features. These are then evaluated in terms of probability distribution agreements between values of samples belonging to different classes. Finally, a graph-based approach for feature selection is proposed, which allows for selecting high-quality and uncorrelated features to be used in feature generation during the next iteration. As shown by the results, the proposed method improved the accuracy of all tested classifiers, where the best accuracies were achieved using random forest. In addition, the method turned out to be insensitive to both of the input parameters, while superior performances in comparison to the state of the art were demonstrated on nine out of 15 test sets and achieving comparable results in the others. Finally, we demonstrate the explainability of the learned feature representation for knowledge discovery.

A new method for encoding a sequence of integers, named Binary Adaptive Sequential Coding with Return to Bias, is proposed in this paper. It extends the compressing pipeline for chain codes’ compression consisting of Burrows Wheeler Transform, Move-To-Front Transform, and Adaptive Arithmetic Coding. We also explain when to include the Zero-Run Transform into the above-mentioned pipeline. The Zero-Run Transform generates a sequence of integers corresponding to the number of zero-runs. This sequence is encoded by Golomb coding, Binary Adaptive Sequential Coding, and the new Binary Adaptive Sequential Coding with Return to Bias. Finally, a comparison is performed with the two state-of-the-art methods. The proposed method achieved similar compression efficiency for the Freeman chain code in eight directions. However, for the chain codes with shorter alphabets (Freeman chain code in four directions, Vertex Chain Code, and Three-OrThogonal chain code), the introduced method outperforms the referenced ones.

This article introduces a fast Central Processing Unit (CPU) implementation of geodesic morphological operations using stream processing. In contrast to the current state-of-the-art, that focuses on achieving insensitivity to the filter sizes with efficient data structures, the proposed approach achieves efficient computation of long chains of elementary 3 x 3 filters using multicore and Single Instruction Multiple Data (SIMD) processing. In comparison to the related methods, up to 100 times faster computation of common geodesic operators is achieved in this way, allowing for real-time processing (with over 30 FPS) of up to 1500 filters long chains, applied on 1024 x 1024 images. In addition, the proposed approach outperformed GPGPU, and proved to be more efficient than the comparable streaming method for the computation of morphological erosions and dilations with window sizes up to 183 x 183 in the case of using char and 27 x 27 when using double data types.