Fecha de publicación: 23/07/2019 Fuente: Wipo "precision farming" The present disclosure addresses the technical problem of enabling automated inference of changes in spatio-temporal images by leveraging the high level robust features extracted from a ConvolutionalNeural Network (CNN) trained on varied contexts instead of data dependent feature methods. Unsupervised clustering on the high level features eliminates the cumbersome requirement of labeling the images. Since models are not trained on any specific context, any image may be accepted. Real time inference is enabled by a certain combination of unsupervised clustering and supervised classification. Acloud-edge topology ensures real time inference even when connectivity is not available by ensuring updated classification models are deployed on the edge. Creating a knowledge ontology based on adaptive learning enables inference of an incoming image with varying levels of precision. Precision farming may be an application of the present disclosure.