AI-based decision support solutions require life cycles that adequately address critical steps, such as (i) finding suitable machine learning (ML) methods for the problem at hand, (ii) preparing and executing adequate data acquisition processes and (iii) tractable evaluation of the overall solution. Understanding the data generating processes is key in achieving this. Training and test data can be seen as a result of a causal data generation process, a sampling process in which the data is collected from different sources that are influenced by multiple interdependent phenomena. This is represented by a Qualitative Model of Data Generation Processes (QM-DGP), a causal graphical model. QM-DGP facilitates analysis of the complexity of the underlying data generating processes that can inform the development of trustable ML-based solutions in multiple ways. Firstly, this analysis is the basis for the determination of the required complexity of the ML models. Secondly, it facilitates the determination of the quantities of training data supporting good learning results. Thirdly, it can provide guidance for a systematic simplification of the models, supporting tractable solutions without significantly reduced performance. The construction of QM-DGP and the analysis benefit from sound theoretical concepts, such as d-separation and I-Maps. Experimental results with simulated data indicate that the approach can be effective in predicting the required quantities of training data and the determination of the modelling complexity using different types of models.

This paper introduces a probabilistic approach for forecasting vessel trajectories. It combines a Dynamic Bayesian Network (DBN) and an auxiliary position determination process to iteratively sample future vessel positions in a scalable and computationally efficient manner. The DBN is a discrete probabilistic model of typical vessel behaviors. It is used for ancestral sampling to predict the speed and orientation of a vessel which, in turn, are used by the auxiliary process to predict the vessel's position in a discretized representation of the space. The DBN is event based and uses latent variables that efficiently encode the context influencing the dynamics of different types of vessels. The parameters of the DBN are learned in an unsupervised fashion by using the Expectation Maximization (EM) algorithm. The experiments with real world data confirm the accuracy and effectiveness of the proposed approach.