Novel Model Based on Artificial Neural Networks to Predict Short-Term Temperature Evolution in Museum Environment.

Alessandro Bile,Anna Maria Siani,Francesca Frasca,Hamed Tari,Eugenio Fazio,Andreas Grinde

doi:10.3390/s22020615

Abstract

The environmental microclimatic characteristics are often subject to fluctuations of considerable importance, which can cause irreparable damage to art works. We explored the applicability of Artificial Intelligence (AI) techniques to the Cultural Heritage area, with the aim of predicting short-term microclimatic values based on data collected at Rosenborg Castle (Copenhagen), housing the Royal Danish Collection. Specifically, this study applied the NAR (Nonlinear Autoregressive) and NARX (Nonlinear Autoregressive with Exogenous) models to the Rosenborg microclimate time series. Even if the two models were applied to small datasets, they have shown a good adaptive capacity predicting short-time future values. This work explores the use of AI in very short forecasting of microclimate variables in museums as a potential tool for decision-support systems to limit the climate-induced damages of artworks within the scope of their preventive conservation. The proposed model could be a useful support tool for the management of the museums.

Highlights

Data-driven models developed with wide range of machine learning algorithms are largerly used in climate and atmospheric modelling [1] Their use, related to microclimate data in cultural heritage domain, is up to now limited and poorly explored
When training a neural network, it is important to analyze the relationship between the forecast errors and the time steps, called time lags [20]
The two predictive networks were optimized for the analysis and forecasting of the time series of the “Stone Corridor” exhibition hall of the Rosenborg Castle in Denmark

Summary

Introduction

Data-driven models developed with wide range of machine learning algorithms are largerly used in climate and atmospheric modelling [1] Their use, related to microclimate data in cultural heritage domain, is up to now limited and poorly explored. This is mainly due to the limited availability of long-term series of key environmental variables at the sites where the artifacts are exhibited or stored. Computers learn from previous processing to produce results and take decisions that are reliable

Objectives

Results

Conclusion