Machine learning based temperature prediction of poly(N-isopropylacrylamide)-capped plasmonic nanoparticle solutions

Sudaraka Mallawaarachchi, Yiyi Liu, San H. Thang, Wenlong Cheng, Malin Premaratne

Research output: Contribution to journalArticleResearchpeer-review

Abstract

The temperature-dependent optical properties of gold nanoparticles that are capped with the thermo-sensitive polymer: 'poly(N-isopropylacrylamide)' (PNIPAM), have been studied extensively for several years. Also, their suitability to function as nanoscopic thermometers for bio-sensing applications has been suggested numerous times. In an attempt to establish this, many have studied the temperature-dependent optical resonance characteristics of these particles; however, developing a simple mathematical relationship between the optical measurements and the solution temperature remains an open challenge. In this paper, we attempt to systematically address this problem using machine learning techniques to quickly and accurately predict the solution-temperature, based on spectroscopic data. Our emphasis is on establishing a simple and practically useful solution to this problem. Our dataset comprises spectroscopic absorption data from both nanorods and nanobipyramids capped with PNIPAM, measured at discretely varied and pre-set temperature states. Specific regions of the spectroscopic data are selected as features for prediction using random forest (RF), gradient boosting (GB) and adaptive boosting (AB) regression techniques. Our prediction results indicate that RF and GB techniques can be used successfully to predict solution temperatures instantly to within 1 °C of accuracy.

Original languageEnglish
Pages (from-to)24808-24819
Number of pages12
JournalPhysical Chemistry Chemical Physics
Volume21
Issue number44
DOIs
Publication statusPublished - 28 Nov 2019

Cite this

@article{7b433d86395947dba51d503a017bec50,
title = "Machine learning based temperature prediction of poly(N-isopropylacrylamide)-capped plasmonic nanoparticle solutions",
abstract = "The temperature-dependent optical properties of gold nanoparticles that are capped with the thermo-sensitive polymer: 'poly(N-isopropylacrylamide)' (PNIPAM), have been studied extensively for several years. Also, their suitability to function as nanoscopic thermometers for bio-sensing applications has been suggested numerous times. In an attempt to establish this, many have studied the temperature-dependent optical resonance characteristics of these particles; however, developing a simple mathematical relationship between the optical measurements and the solution temperature remains an open challenge. In this paper, we attempt to systematically address this problem using machine learning techniques to quickly and accurately predict the solution-temperature, based on spectroscopic data. Our emphasis is on establishing a simple and practically useful solution to this problem. Our dataset comprises spectroscopic absorption data from both nanorods and nanobipyramids capped with PNIPAM, measured at discretely varied and pre-set temperature states. Specific regions of the spectroscopic data are selected as features for prediction using random forest (RF), gradient boosting (GB) and adaptive boosting (AB) regression techniques. Our prediction results indicate that RF and GB techniques can be used successfully to predict solution temperatures instantly to within 1 °C of accuracy.",
author = "Sudaraka Mallawaarachchi and Yiyi Liu and Thang, {San H.} and Wenlong Cheng and Malin Premaratne",
year = "2019",
month = "11",
day = "28",
doi = "10.1039/c9cp04544a",
language = "English",
volume = "21",
pages = "24808--24819",
journal = "Physical Chemistry Chemical Physics",
issn = "1463-9076",
publisher = "The Royal Society of Chemistry",
number = "44",

}

Machine learning based temperature prediction of poly(N-isopropylacrylamide)-capped plasmonic nanoparticle solutions. / Mallawaarachchi, Sudaraka; Liu, Yiyi; Thang, San H.; Cheng, Wenlong; Premaratne, Malin.

In: Physical Chemistry Chemical Physics, Vol. 21, No. 44, 28.11.2019, p. 24808-24819.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Machine learning based temperature prediction of poly(N-isopropylacrylamide)-capped plasmonic nanoparticle solutions

AU - Mallawaarachchi, Sudaraka

AU - Liu, Yiyi

AU - Thang, San H.

AU - Cheng, Wenlong

AU - Premaratne, Malin

PY - 2019/11/28

Y1 - 2019/11/28

N2 - The temperature-dependent optical properties of gold nanoparticles that are capped with the thermo-sensitive polymer: 'poly(N-isopropylacrylamide)' (PNIPAM), have been studied extensively for several years. Also, their suitability to function as nanoscopic thermometers for bio-sensing applications has been suggested numerous times. In an attempt to establish this, many have studied the temperature-dependent optical resonance characteristics of these particles; however, developing a simple mathematical relationship between the optical measurements and the solution temperature remains an open challenge. In this paper, we attempt to systematically address this problem using machine learning techniques to quickly and accurately predict the solution-temperature, based on spectroscopic data. Our emphasis is on establishing a simple and practically useful solution to this problem. Our dataset comprises spectroscopic absorption data from both nanorods and nanobipyramids capped with PNIPAM, measured at discretely varied and pre-set temperature states. Specific regions of the spectroscopic data are selected as features for prediction using random forest (RF), gradient boosting (GB) and adaptive boosting (AB) regression techniques. Our prediction results indicate that RF and GB techniques can be used successfully to predict solution temperatures instantly to within 1 °C of accuracy.

AB - The temperature-dependent optical properties of gold nanoparticles that are capped with the thermo-sensitive polymer: 'poly(N-isopropylacrylamide)' (PNIPAM), have been studied extensively for several years. Also, their suitability to function as nanoscopic thermometers for bio-sensing applications has been suggested numerous times. In an attempt to establish this, many have studied the temperature-dependent optical resonance characteristics of these particles; however, developing a simple mathematical relationship between the optical measurements and the solution temperature remains an open challenge. In this paper, we attempt to systematically address this problem using machine learning techniques to quickly and accurately predict the solution-temperature, based on spectroscopic data. Our emphasis is on establishing a simple and practically useful solution to this problem. Our dataset comprises spectroscopic absorption data from both nanorods and nanobipyramids capped with PNIPAM, measured at discretely varied and pre-set temperature states. Specific regions of the spectroscopic data are selected as features for prediction using random forest (RF), gradient boosting (GB) and adaptive boosting (AB) regression techniques. Our prediction results indicate that RF and GB techniques can be used successfully to predict solution temperatures instantly to within 1 °C of accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85075108911&partnerID=8YFLogxK

U2 - 10.1039/c9cp04544a

DO - 10.1039/c9cp04544a

M3 - Article

VL - 21

SP - 24808

EP - 24819

JO - Physical Chemistry Chemical Physics

JF - Physical Chemistry Chemical Physics

SN - 1463-9076

IS - 44

ER -