-
trophic (phytoplankton growth and loss) variables of the Thau lagoon and the Mediterranean Sea (Station 00SETE) in an innovative way using in situ data from high-frequency automated sensors; 2) linking
-
, including variational auto-encoders, generative adversarial networks (GANs) and more recently probabilistic diffusion denoising models. On the other hand the CRIStAL laboratory has a strong expertise in
-
over the course of the project. References: - Deneu B et al (2021) Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment. PLoS Comput
Searches related to sensor network
Enter an email to receive alerts for sensor-network positions in france