This study proposes a novel nondestructive methodology for determining the formation time of inkjet-printed documents throug

h the integration of hyperspectral imaging technology with machine learning regression algorithms. Experimental data were collected from chronologically printed samples produced by nine inkjet printers of distinct brands and models. The methodology framework comprises two principal phases：dimensionality reduction of hyperspectral data and subsequent regression modeling.In the initial phase，principal component analysis（PCA） and partial least squares regression（PLSR） were employed to address the high dimensionality inherent in hyperspectral datasets. The interpretation rate of dimensional reduction of principal components derived from these dimensionality reduction techniques were systematically quantified，providing preliminary interpretability for the model architecture. This phase effectively condensed the hyperspectral information while preserving critical temporal features associated with document aging.Four advanced regression methodologies were subsequently implemented on the dimensionality-reduced data：least absolute shrinkage and selection operator regression（LASSO），partial least squares regression（PLSR），ridge regression（RR），and Bayesian regression（BR）. The dataset was partitioned into training and testing subsets at a 1∶4 ratio to ensure robust model validation. Quantitative evaluation metrics revealed exceptional model performance across all regression approaches. The coefficient of determination（

<math id="M3"><msup><mrow><mi>R</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msup></math>

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=95149412&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=95149411&type=

3.38666677

2.96333337

） values for LA

SSO-PLSR，PLSR，RR，and BR models consistently approached unity（

<math id="M4"><msup><mrow><mi>R</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msup><mo>></mo><mn mathvariant="normal">0.99</mn></math>

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=95149413&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=95149389&type=

15.32466698

2.96333337

），indicating near-perfect explanatory power. Furthermore，all models demonstrated minimal error metrics：mean absolute error（MAE），mean squared error（MSE），and root mean squared error（RMSE） values were all proximate to zero，confirming high predictive accuracy.Statistical significance testing yielded

F

-statistic values of substantial magnitude（

p

<

0.001） for all PLSR-based regression models，confirming the exceptional statistical validity of the results. Comparative analysis revealed superior performance characteristics in PLSR and BR models relative to LASSO and RR implementations.Further explain the relationship between principal components and spectral bands through the PLSR weight coefficients to clarify the role of key spectral bands.External validation using independent hyperspectral datasets confirmed the models' generalizability，with

<math id="M5"><msup><mrow><mi>R</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msup></math>

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=95149391&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=95149390&type=

3.38666677

2.96333337

values exceeding 0.9（

p<

0.05） across all test scenarios. Error analysis indicated that residual variations fell within acceptable methodological thresholds，confirming measurement reliability. This investigation establishes that hyperspectral imaging technology exhibits significant potential for forensic document analysis，particularly in temporal authentication of inkjet-printed materials. The implemented machine learning framework successfully decouples temporal signatures from complex spectral data while maintaining complete non-invasiveness. The method proposed in this article provides a new solution for the problem of dating documents，offering substantial improvements over conventional destructive chemical analysis methods.