Earthen sites are important cultural heritages. Non-destructive quantitative analysis for moisture content in earthen sites is always appealing and important to heritage conservation. In this study, two ranges of hyperspectral imaging (HSI) systems, visible-near infrared (Vis-NIR: 400–1000 nm) and short-wave infrared (SWIR: 1000–2500 nm), are compared for the quantitative analysis of moisture content in simulated samples. To obtain the optimal prediction model, the raw data were pre-processed by several methods. The characteristic wavelengths were extracted by successive projection algorithm (SPA). Partial least squares (PLS) regression, support vector regression (SVR) and principal component regression (PCR) models were developed using the processed data, respectively. The results indicate that compared to Vis-NIR, the moisture content prediction model developed based on SWIR has good performance, with Rp2>0.903 and RMSEP <3.6%. The optimal model SG-SPA-PCR in SWIR was successfully used to visualize the moisture content distribution of the simulated earthen sites with time.
NogueiraRFerreira PintoAGomesA. Artificial ageing by salt crystallization: test protocol and salt distribution patterns in lime-based rendering mortars. J Cult Herit2020; 45: 180–192.
2.
RichardsJGuoQVilesH, et al.Moisture content and material density affects severity of frost damage in earthen heritage. Sci Total Environ2022; 819: 153047.
3.
ShenYChenWKuangJ, et al.Effect of salts on earthen materials deterioration after humidity cycling. J Cent South Univ2017; 24: 796–806.
4.
FortRFeijooJVaras–MurielM, et al.Appraisal of non-destructive in situ techniques to determine moisture and salt crystallization-induced damage in dolostones. J Build Eng2022; 53: 104525.
5.
ChatzigrigoriouAManoudisPNKarapanagiotisI. Fabrication of water repellent coatings using waterborne resins for the protection of the cultural heritage. Macromol Symp2013; 331-332(1): 158–165.
6.
GerminarioLOguchiCT. Underground salt weathering of heritage stone: lithological and environmental constraints on the formation of sulfate efflorescences and crusts. J Cult Herit2021; 49(3): 85–93.
7.
DongJLiuX. Application of improved enzyme induced calcium carbonate precipitation (EICP) technology in surface protection of earthen sites. J Cult Herit2022; 54: 146–154.
8.
MorillasHMagureguiMGallego-CartagenaE, et al.The influence of marine environment on the conservation state of Built Heritage: an overview study. Sci Total Environ2020; 745: 140899.
9.
SripauryaTSengchuaiKBooranawongA, et al.Gros Michel banana soluble solids content evaluation and maturity classification using a developed portable 6 channel NIR device measurement. Measurement2021; 173: 108615.
10.
ZhaoXQueHSunX, et al.Hybrid convolutional network based on hyperspectral imaging for wheat seed varieties classification. Infrared Phys Technol2022; 125: 104270.
11.
ChenJBaiTZhangN, et al.Hyperspectral detection of sugar content for sugar-sweetened apples based on sample grouping and SPA feature selecting methods. Infrared Phys Technol2022; 125: 104240.
12.
JiaBWangWNiX, et al.Essential processing methods of hyperspectral images of agricultural and food products. Chemometr Intell Lab2020; 198: 103936.
13.
DongCAnTYangM, et al.Quantitative prediction and visual detection of the moisture content of withering leaves in black tea (Camellia sinensis) with hyperspectral image. Infrared Phys Technol2022; 123: 104118.
14.
JaySGuillaumeMMinghelliA, et al.Hyperspectral remote sensing of shallow waters: considering environmental noise and bottom intra-class variability for modeling and inversion of water reflectance. Sci Total Environ2017; 200: 352–367.
15.
PyoJCKwonYSMinJH, et al.Effect of hyperspectral image-based initial conditions on improving short-term algal simulation of hydrodynamic and water quality models. J Environ Manage2021; 294(3): 112988.
16.
MedusLDSabanMFrancés-VílloraJV, et al.Hyperspectral image classification using CNN: application to industrial food packaging. Food Control2021; 125(3): 107962.
17.
ElMasryGGouPAl-RejaieS. Effectiveness of specularity removal from hyperspectral images on the quality of spectral signatures of food products. J Food Eng2021; 289: 110148.
18.
BaianoA. Applications of hyperspectral imaging for quality assessment of liquid based and semi-liquid food products: a review. J Food Eng2017; 214: 10–15.
19.
ZhangXZhaoH. Hyperspectral-cube-based mobile face recognition: a comprehensive review. Inf Fusion2021; 74: 132–150.
20.
YangGZhaoCHuangW, et al.Extension of the Hapke bidirectional reflectance model to retrieve soil water content. Hydrol Earth Syst Sci2011; 15: 2317–2326.
21.
ReisASRodriguesMSantosGLAA, et al.Detection of soil organic matter using hyperspectral imaging sensor combined with multivariate regression modeling procedures. Remote Sens Appl2021; 22: 100492.
22.
WangSGuanKZhangC, et al.Using soil library hyperspectral reflectance and machine learning to predict soil organic carbon: assessing potential of airborne and spaceborne optical soil sensing. Remote Sens Environ2022; 271: 112914.
23.
YuanJWangXYanCX, et al.Soil moisture retrieval model for remote sensing using reflected hyperspectral information. Remote Sens2019; 11(3): 366.
24.
SharmaSSumeshKCSirisomboonP. Rapid ripening stage classification and dry matter prediction of durian pulp using a pushbroom near infrared hyperspectral imaging system. Measurement2022; 189: 110464.
25.
TianJPhilpotWD. Relationship between surface soil water content, evaporation rate, and water absorption band depths in SWIR reflectance spectra. Remote Sens Environ2015; 169: 280–289.
26.
SarathjithMCDasBSVasavaHB, et al.Diffuse reflectance spectroscopic approach for the characterization of soil aggregate size distribution. Soil Sci Soc Am J2014; 78(2): 369–376.
27.
Mustafa HilalAAl-WesabiFNAlthobaitiMM, et al.An Intelligent deep learning based hyperspectral Signal classification scheme for complex measurement systems. Measurement2022; 188: 110540.
28.
XiaCRenMWangB, et al.Acquisition and analysis of hyperspectral data for surface contamination level of insulating materials. Measurement2021; 173: 108560.
29.
LiGMaSLiK, et al.Heterogeneity classification based on hyperspectral transmission imaging and multivariate data analysis. Infrared Phys Technol2022; 123: 104180.
30.
ChangCWLairdDAMausbachMJ, et al.Near‐infrared reflectance spectroscopy-principal components regression analyses of soil properties. Soil Sci Soc Am J2001; 65(2): 480–490.
31.
LoweBSmithCFraser-MillerS, et al.Light-ageing characteristics of Māori textiles: colour, strength and molecular change. J Cult Herit2017; 24: 60–68.
32.
XiaKXiaSShenQ, et al.Moisture spectral characteristics and hyperspectral inversion of fly ash-filled reconstructed soil. Spectrochim Acta2021; 253: 119590.
33.
KochMSchodlokMCGuggenbergerG, et al.Effects of water tension and surface roughness on soil hyperspectral reflectance. Geoderma2021; 385: 114888.
34.
HaubrockS-ChabrillatSLemmnitzC, et al.Surface soil moisture quantification models from reflectance data under field conditions. Int J Rem Sens2008; 29(1): 3–29.
StevensANocitaMTóthG, et al.Prediction of soil organic carbon at the European scale by visible and near infrared reflectance spectroscopy. PLoS One2013; 8(6): e66409.
37.
BećKBGrabskaJHuckCW. Biomolecular and bioanalytical applications of infrared spectroscopy-A review. Anal Chim Acta2020; 1133: 150–177.
38.
BabletAViallefont-RobinetFJacquemoudS, et al.High-resolution mapping of in-depth soil moisture content through a laboratory experiment coupling a spectroradiometer and two hyperspectral cameras. Remote Sens Environ2020; 236: 111533.
39.
WuSWangCLiuY, et al.Mapping the salt content in soil profiles using vis‐NIR hyperspectral imaging. Soil Sci Soc Am J2018; 82(5): 1259–1269.
40.
BurudIMoniCFloA, et al.Qualitative and quantitative mapping of biochar in a soil profile using hyperspectral imaging. Soil Res2016; 155: 523–531.
41.
XuSWangMShiX, et al.Integrating hyperspectral imaging with machine learning techniques for the high-resolution mapping of soil nitrogen fractions in soil profiles. Sci Total Environ2021; 754: 142135.
42.
HeXXuMZhangH, et al.An exploratory study of the deterioration mechanism of ancient wall-paintings based on thermal and moisture expansion property analysis. J Archaeol Sci2014; 42: 194–200.
43.
KennardRWStoneLA. Computer aided design of experiments. Technometrics. 1969; 11: 137–148.
44.
PudełkoAChodakMRoemerJ, et al.Application of FT-NIR spectroscopy and NIR hyperspectral imaging to predict nitrogen and organic carbon contents in mine soils. Measurement2020; 164: 108117.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
