Rain affects the building envelope's durability, increasing the amount of water available on the surfaces due to the wind pressure. Water can activate and accelerate chemical and biological processes causing algae and cyanobacteria growth. The velocity of this process depends on several parameters, such as temperature, relative humidity (RH%), surface characteristics (i.e. roughness, porosity) and water availability on the building surfaces considering that algae and cyanobacteria fall into a latent state without water. Wind plays a significant role: it can push the rain against the facades, wetting them and increasing the growth speed. This paper analyzes the impact of rain on algae growth on building facades, considering wind influence, through a neural network (NN). Experimental data collected imposing different combinations of temperature, RH% and water availability on the surface, also due to rain and WDR, of 5 different porous materials (bricks) were used to train and test the NN. The NN was tested showing an accuracy of 82% (r-squared) in predicting algae growth concerning experimental data, based on the imposed parameters: wind speed, wind direction; air temperature; RH%; surface characteristics (porosity, roughness). Three different UE locations, characteristics of different Koppen-Geiger climates, and four different exposures for each location were selected. The application of the trained NN in different climates, considering different orientations, demonstrates that WDR is the main factor affecting microalgae growth. WDR can increase by more than two times the area covered by algae in a year, depending on the climate and the orientation.

Influence of the rain on algae growth on building facades. A predictive model based on neural networks / D'Orazio, M.; Quagliarini, E.; Gianangeli, A.. - In: BUILDING AND ENVIRONMENT. - ISSN 0360-1323. - ELETTRONICO. - 246:(2023). [10.1016/j.buildenv.2023.110990]

Influence of the rain on algae growth on building facades. A predictive model based on neural networks

D'Orazio M.
Primo
Writing – Original Draft Preparation
;
Quagliarini E.
Secondo
Writing – Review & Editing
;
Gianangeli A.
Ultimo
Writing – Review & Editing
2023-01-01

Abstract

Rain affects the building envelope's durability, increasing the amount of water available on the surfaces due to the wind pressure. Water can activate and accelerate chemical and biological processes causing algae and cyanobacteria growth. The velocity of this process depends on several parameters, such as temperature, relative humidity (RH%), surface characteristics (i.e. roughness, porosity) and water availability on the building surfaces considering that algae and cyanobacteria fall into a latent state without water. Wind plays a significant role: it can push the rain against the facades, wetting them and increasing the growth speed. This paper analyzes the impact of rain on algae growth on building facades, considering wind influence, through a neural network (NN). Experimental data collected imposing different combinations of temperature, RH% and water availability on the surface, also due to rain and WDR, of 5 different porous materials (bricks) were used to train and test the NN. The NN was tested showing an accuracy of 82% (r-squared) in predicting algae growth concerning experimental data, based on the imposed parameters: wind speed, wind direction; air temperature; RH%; surface characteristics (porosity, roughness). Three different UE locations, characteristics of different Koppen-Geiger climates, and four different exposures for each location were selected. The application of the trained NN in different climates, considering different orientations, demonstrates that WDR is the main factor affecting microalgae growth. WDR can increase by more than two times the area covered by algae in a year, depending on the climate and the orientation.
2023
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/324751
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact