Timo Lähivaara

TL;DR: In the approach, locations, heights, and crown shapes of trees are tracked automatically by fitting multiple 3-D crown height models to ALS data of a field plot by an iterative reconstruction method based on Bayesian inversion paradigm.

TL;DR: A method to characterize macroscopically homogeneous rigid frame porous media from impedance tube measurements by deterministic and statistical inversion and finds reliable parameter and uncertainty estimates to the six pore parameters quickly with minimal user input.

TL;DR: In this article, the feasibility of data-based machine learning applied to ultrasound tomography is studied to estimate water-saturated porous material parameters, and the data to train the neural networks is simulated by solving wave propagation in coupled poroviscoelastic-viscoelasticacoustic media.

TL;DR: A high-order discontinuous Galerkin (DG) method for modelling wave propagation in coupled poroelastic–elastic media and experiments where the numerical accuracy of the scheme under consideration is compared to analytic and other numerical solutions are provided.

TL;DR: The feasibility of data based machine learning applied to ultrasound tomography is studied to estimate water-saturated porous material parameters, and a high-order discontinuous Galerkin method is considered, while deep convolutional neural networks are used to solve the parameter estimation problem.