Application of physics-informed neural networks to inverse problems in unsaturated groundwater flow

GMDH Type Neural Networks and Their Application to the Identification of the Inverse Kinematics Equations of Robotic Manipulators (RESEARCH NOTE)

Groundwater recharge simulation using a coupled saturated-unsaturated flow model

Abstract The coupled MODFLOW-HYDRUS software package was used to produce a saturated-unsaturated flow model for a Flood Spreading System (FSS) and its associated aquifer. The study aim to improve simulations of near-surface hydrological processes, including temporal and spatial variation in groundwater recharge rates. The coupled model was built with average RMSE=1.1 and 1.3 for calibration ...

Application of the Pseudo-Transient Technique to a Real-World Unsaturated Flow Groundwater Problem

Modeling unsaturated flow using numerical techniques such as the finite element method can be especially difficult because of the highly nonlinear nature of the governing equations. This problem is even more challenging when a steady-state solution is needed. This paper describes the implementation of a pseudo-transient technique to drive the solution to steady-state and gives results for a rea...

Application of neural networks to inverse lens distortion modelling

The accurate and quick modelling of inverse lens distortion to rectify images or predict the image coordinates of real world objects has long been a challenge. This work investigates the use of artificial neural networks to perform this modelling. Several architectures are investigated and multiple methods of training the networks are used to achieve the best results. The error is expressed as ...

Application of Artificial Neural Networks in Particle Physics

The application of artificial neural networks in particle physics is reviewed. The use of feed-forward nets is most common for event classification and function approximation. This network type is best suited for a hardware implementation and special VLSI chips are available which are used in fast trigger processors. Also discussed are fully connected networks of the Hopfield type for pattern r...