Sparse and hybrid modelling of relative humidity: the Krško basin case study

Abstract

This study describes an application of hybrid modelling for an atmospheric variable in the Krško basin. The hybrid model is a combination of a physics‐based and data‐driven model and has some properties of both modelling approaches. In the authors’ case, it is used for the modelling of an atmospheric variable, namely relative humidity in a particular location for the purpose of using the predictions of the model as an input to the air‐pollution‐dispersion model for radiation exposure. The presented hybrid model is a combination of a physics‐based atmospherical model and a Gaussian‐process (GP) regression model. The GP model is a probabilistic kernel method that also enables evaluation of prediction confidence. The problem of poor scalability of GP modelling was solved using sparse GP modelling; in particular, the fully independent training conditional method was used. Two different approaches to dataset selection for empirical model training were used and multiple‐step‐ahead predictions for different horizons were assessed. It is shown in this study that the accuracy of the predicted relative humidity in the Krško basin improved when using hybrid models over using the physics‐based model alone and that predictions for a considerable length of horizon can be used.

A Hybrid Newton–Raphson and Particle Swarm Optimization Method for Target Motion Analysis by Batch Processing

“…The hybrid optimization algorithm proposed in this paper, i.e., Newton–Raphson particle swarm optimization (NRPSO), combines the advantages of NRM and PSO in BO-TMA. Interest in hybrid optimization methods has increased over the past few decades [ 14 , 15 , 16 , 17 , 22 , 23 , 24 ]. Early hybridization was mainly done between several metaheuristic algorithms.…”

“…Currently, hybrid methods combining different types of methods are being studied in various fields. In order to accurately predict the relative humidity in the atmosphere in a specific geographical location, a hybrid model combining the physics-based numerical weather prediction (NWP) model and the data-driven Gaussian process (GP) model has been proposed [ 14 ]. In addition, a study was conducted to find a combination of usual industrial radioactive sources that achieves the highest precision in dual-energy radiation-based three-phase flow meters, in which a hybrid model, an adaptive neural fuzzy reasoning system (ANFIS) trained through gray wolf optimization (GWO), was used [ 15 ].…”