The implicit data models and the expected parameters on which they are dependent may introduce biases in the Earth Observation (EO) data analysis methodologies. The estimated parameters can describe only particular, limited observations behavior. The broad diversity of the EO data, as sensing modalities, spatial, spectral, and radiometric resolution, and also the huge variety of the observed scenes make problematic the definition of a general model.
The lecture presents a communication channel approach for image information extraction. The information retrieval is elaborated based on data compression methods independent of the type, form, content or purpose of the data. This paradigm is common to any data type without the weakening effect of specializing it for specific, particular applications fields. This is realized approaching these challenges from an Information Theoretic perspective and using also the latest progress in Algorithmic Information Theory. The objective is re-formulating the definition of the “relevant information” in relation to the notions of “image content” and “context”, for a broader class of data, including scientific and engineering instruments records.
The lecture introduces and explains solution based on the concept of Digital Twins. A Digital Twin is the convergence of the remote sensing physical mechanisms tightly connected, communicating and continuously learning, from and with mathematical models, data analytics, simulations and user interaction.
The presentation covres the major developments, of hybrid, physics aware AI paradigms, at the convergence of forward modelling, inverse problem and machine learning, to discover causalities and make prediction for maximization of the information extracted from EO and related non-EO data.