… market studies on Digital Earth Australia and automation of Victoria’s Vegetation Mapping Through Machine Learning initiative.

Researchers have developed a model that can identify Gamba grass with up to 90 percent accuracy.

The World Geospatial Information Council has launched an initiative to develop a body of knowledge on AI/ML practices to develop a policy framework. The WGIC has announced the first stage of the policy research project, seeking to assess relevance and popularity of AI and machine learning (AI/ML) applications in the geospatial industry. Material released by the WGIC indicates that the study intends to investigate the implications of these techniques on data privacy and personal information, intellectual property control and protection, socio-economic bias and ethics. "While AI/ML uptake brings a myriad of potential opportunities to the geospatial sector, we realise there will also be challenges. Public authorities struggle with their role in policymaking and regulation of this fast-paced AI/ML revolution," he said.

We introduce a probabilistic generative model for disentangling spatio-temporal disease trajectories from series of high-dimensional brain images. The model is based on spatio-temporal matrix factorization, where inference on the sources is constrained by anatomically plausible statistical priors. To model realistic trajectories, the temporal sources are defined as monotonic and time-reparametrized Gaussian Processes. To account for the non-stationarity of brain images, we model the spatial sources as sparse codes convolved at multiple scales. The method was tested on synthetic data favourably comparing with standard blind source separation approaches. The application on large-scale imaging data from a clinical study allows to disentangle differential temporal progression patterns mapping brain regions key to neurodegeneration, while revealing a disease-specific time scale associated to the clinical diagnosis.