Mapping of hydraulic transmissivity field from inversion of tracer test data using convolutional neural networks. CNN-2T

•Mapping hydraulic transmissivity from temporal data in multiple tracer tests,•Principle based on an encoder-decoder convolutional neural network,•Time required for training is on the order of a Gauss-Newton algorithm,•Provide an end-to-end inversion with an accurate reconstruction, perform instantly,•Reconstruction quality relies on training data, less influenced by data noise.