Supervised Principal Component Analysis Research Articles

A Polarimetric Decomposition and Copula Quantile Regression Approach for Soil Moisture Estimation From Radarsat-2 Data Over Vegetated Areas

This paper proposes a novel framework for probabilistic estimation of surface soil moisture (SSM) based on polarimetric decomposition and copula quantile regression, mainly focusing on solving the low correlation between synthetic aperture radar (SAR) backscattering coefficients and SSM in corn-covered areas. Cloude-Pottier decomposition and adaptive non-negative eigenvalue decomposition can extract more polarization parameters, explaining the implicit information in polarization data from different theoretical levels. Polarization parameters and the backscattering coefficients for different polarizations constitute predictor variable parameters for estimating the SSM. The dimensionality of the predictor variable parameters is reduced by supervised principal component analysis (SPCA) to derive the first principal component. SPCA ensures a high correlation between the first principal component and the SSM. Finally, the Archimedes copula function simply and effectively constructs the nonlinear relationship between SSM and the first principal component to complete the quantile regression estimation of SSM. Results show that the root-mean-square error (RMSE) range of SSM estimation is 0.039-0.078 cm <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{3}$</tex-math></inline-formula> /cm <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{3}$</tex-math></inline-formula> and the correlation coefficient (R) is 0.401-0.761. In addition, copula quantile regression constructs an uncertainty range for the SSM estimate, which can be used to judge the reliability of the estimate.

The establishment of Air Quality Health Index in China: A comparative analysis of methodological approaches

BackgroundThe Air Quality Index (AQI) has been criticized because it does not adequately account for the health effect of multi-pollutants. Although the developed Air Quality Health Index (AQHI) is a more effective communication tool, little is known about the best method to construct AQHI on long time and large spatial scales. ObjectivesTo further evaluate the validity of existing approaches to the establishment of AQHI on both long time and larger spatial scales. MethodsBy introducing 3 approaches addressing multi-pollutant exposures: cumulative risk index (CRI), supervised principal component analysis (SPCA), and Bayesian multi-pollutants weighted model (BMP), we constructed CRI-AQHI, SPCA-AQHI, BMP-AQHI and standard-AQHI on cardiovascular mortality in China from 2015 to 2019 at both the national and geographic regional levels. We further assessed the performance of the four methods in estimating the joint effect of multi-pollutants by simulations under various scenarios of pollution effect. ResultsThe results of national China showed that the BMP-AQHI improved the goodness of fit of the standard-AQHI by 108.24%, followed by CRI-AQHI (5.02%), and all AQHIs performed better than AQI, consistent with 6 geographic regional results. In addition, the simulation result showed that the BMP method provided stable and relatively accurate estimations of the short-term combined effect of exposure to multi-pollutants. ConclusionsAQHI based on BMP could communicate the air pollution risk to the public more effectively than the current AQHI and AQI.

Supervised Regularized Multidimensional Scaling Using Weighted Stress Measure

Supervised Regularized Multidimensional Scaling (SRMDS), a non-linear variant of classical Multi-Dimensional Scaling (cMDS) is proposed recently which involves Radial basis function. The method is focused on the effective selection of centers of the radial basis functions in transforming data from a higher dimensional space to a lower dimension. The transformation matrix is determined by minimizing stress. Weights of components of the stress that are of great importance for classification of data got less focus in Supervised Regularized Multidimensional Scaling. In this article, we have investigated several forms of non-linear functions which may be used as weights of the stress measure. A new form of Z-shape weight function dependent on intraclass information of the dataset is introduced which prefers to preserve global structure of the dataset. The efficiency of the proposed approach is illustrated on several benchmarking datasets which shows that the weighted Supervised Regularized Multidimensional Scaling (WSRMDS) outperforms the base method and some other state of the art approaches such as Linear Discriminant Analysis (LDA), and Supervised Principal Component Analysis (SPCA). Observing the finding of this research, among different weight functions, Z-shape weight function is recommended to use since it works better then any other weight functions for most of the data sets.

Implementation of supervised principal component analysis for global sensitivity analysis of models with correlated inputs.

Global Sensitivity Analysis (GSA) plays a significant role in quantifying the tangible impact of model inputs on the uncertainty of response variable. As GSA results are strongly affected by correlated inputs, several studies have considered this issue, but most of them are computationally expensive, labor-intensive, and difficult to implement. Accordingly, this paper puts forward a novel regression-based strategy based on the Supervised Principal Component Analysis (SPCA), benefiting from the Reproducing Kernel Hilbert Space. Indeed, by conducting one kind of variance-based sensitivity analysis, a renowned method exclusively customized for models with orthogonal inputs, on SPCA regression, the impact of the correlation structure of input variables is considered. The ability of the suggested technique is evaluated with five test cases as well as three hydrologic and hydraulic models, and the results are compared with those obtained from the correlation ratio method; Taken as a benchmark solution, which is a robust but quite complicated approach in terms of programming. It is found that the proposed method satisfactorily identifies the sensitivity ordering of model inputs. Furthermore, it is proved in this study that the performance of the proposed approach is also supported by the total contribution index in the derived covariance decomposition equation. Moreover, the proposed method compared with the correlation ratio method, is found to be computationally efficient and easy to implement. Overall, the proposed scheme is appropriate for high dimensional, quite strong nonlinear or expensive models with correlated inputs, whose coefficient of determination between the original model and regression-based SPCA model is larger than 0.33.

Weather indices for heat-health watch and warning systems

BACKGROUND AND AIM: Extreme heat events have important impacts on human life and health, and have been shown to increase daily mortality and hospitalization. The heat waves of recent years led many countries to establish their heat health watch and warning systems (HHWWS) to prevent the effects of heat. The existing HHWWS usually contain weather indices and their corresponding thresholds. However, the weather indices, which are defined as linear combinations of lagged weather variables, are often unrelated to the variable of interest (over-mortality or over-hospitalization in case of HHWWS). Thus, in order to reduce the subjectivity, it is of interest to construct weather indices which are linked to the variable of interest. METHODS: Indeed, according to the definition of the weather indices, deriving indices can be seen as a dimension reduction problem. Considering the relationship with variable of interest, the most common example is the supervised dimension reduction methods, in our case, it is more about supervised principal component analysis (SPCA) based methods. RESULTS:Therefore, the main objective of this study is to determine weather indices by using SPCA based methods. The comparison results show that the obtained weather indices have better performance than the classic indices in warning system. CONCLUSIONS:These weather indices linked with health variables are then expected to be useful to improve current indices. KEYWORDS: weather indices, HHWWS, heat wave, mortality

Enhanced Supervised Principal Component Analysis for Cancer Classification

In this paper, a new hybridization of supervised principal component analysis (SPCA) and stochastic gradient descent techniques is proposed, and called as SGD-SPCA, for real large datasets that have a small number of samples in high dimensional space. SGD-SPCA is proposed to become an important tool that can be used to diagnose and treat cancer accurately. When we have large datasets that require many parameters, SGD-SPCA is an excellent method, and it can easily update the parameters when a new observation shows up. Two cancer datasets are used, the first is for Leukemia and the second is for small round blue cell tumors. Also, simulation datasets are used to compare principal component analysis (PCA), SPCA, and SGD-SPCA. The results show that SGD-SPCA is more efficient than other existing methods.

The construction of the air quality health index (AQHI) and a validity comparison based on three different methods

The most common currently used air quality risk communication tool, the Air Quality Index (AQI), has been criticized. As a result, Canada proposed the Air Quality Health Index (AQHI) to communicate the health risks of multiple pollutants. However, the AQHI is calculated by directly summing the excess risks from single-pollutant models, which may overestimate the effects of the pollutants. To solve this problem, we introduced two methods for estimating the joint effects of multiple pollutants: the cumulative risk index (CRI) and supervised principal component analysis (SPCA). Based on three methods, i.e., the standard, CRI and SPCA methods, we constructed three types of AQHIs and compared their validity to select the best communication tool. Our results showed that compared with the AQI, all three AQHIs had a linear relationship with mortality. In addition, the CRI-AQHI had the best goodness of fit and captured the overall health risk of pollution mixtures most robustly among various cause-specific mortalities when identifying health risks. Our study indicated that the CRI-AQHI may have the potential to be a better alternative to the standard AQHI in communicating air pollution-related health risks to the public.

High-dimensional lag structure optimization of fuzzy time series

Lag-selection is a high dimensional hyper-parameter in the fuzzy time series (FTS) which requires complex optimization process and computational capacity particularly in high frequency dataset (e.g. daily, hourly). Multivariate high order FTS suffers from establishing long logical relationships, and the difficulty of rule matching is proportional to the time lags and number of variables. In the vast majority of FTS literature, a grid search algorithm or evolutionary algorithms are run to find singular time-lags. In addition, some researchers determine the lag structure arbitrarily. However, grid search in high dimensional problems is not practical especially when recursive predictions are generated and evolutionary algorithms suffer from the randomness which may generate different solutions. This paper proposes an alternative approach to the lag selection problem by utilizing supervised principal component analysis (SPCA), and the lag structure is reduced to low dimensional space. SPCA has been developed to project the high dimensional lagged variables into the first principal component. An empirical study is conducted to validate the proposed approach by using global shipping industry data in the world.

Test Assets and Weak Factors

Estimation and testing of factor models in asset pricing requires choosing a set of test assets. The choice of test assets determines how well different factor risk premia can be identified: if only few assets are exposed to a factor, that factor is weak, which makes standard estimation and inference incorrect. In other words, the strength of a factor is not an inherent property of the factor: it is a property of the cross-section used in the analysis. We propose a novel way to select assets from a universe of test assets and estimate the risk premium of a factor of interest, as well as the entire stochastic discount factor, that explicitly accounts for weak factors and test assets with highly correlated risk exposures. We refer to our methodology as supervised principal component analysis (SPCA), because it iterates an asset selection step and a principal-component estimation step. We provide the asymptotic properties of our estimator, and compare its limiting behavior with that of alternative estimators proposed in the recent literature, which rely on PCA, Ridge, Lasso, and Partial Least Squares (PLS). We find that the SPCA is superior in the presence of weak factors, both in theory and in finite samples. We illustrate the use of SPCA by applying it to estimate the risk premia of several tradable and nontradable factors, to evaluate asset managers’ performance, and to de-noise asset pricing factors.

Test Assets and Weak Factors

Estimation and testing of factor models in asset pricing requires choosing a set of test assets. The choice of test assets determines how well different factor risk premia can be identified: if only few assets are exposed to a factor, that factor is weak, which makes standard estimation and inference incorrect. In other words, the strength of a factor is not an inherent property of the factor: it is a property of the cross-section used in the analysis. We propose a novel way to select assets from a universe of test assets and estimate the risk premium of a factor of interest, as well as the entire stochastic discount factor, that explicitly accounts for weak factors and test assets with highly correlated risk exposures. We refer to our methodology as supervised principal component analysis (SPCA), because it iterates an asset selection step and a principal-component estimation step. We provide the asymptotic properties of our estimator, and compare its limiting behavior with that of alternative estimators proposed in the recent literature, which rely on PCA, Ridge, Lasso, and Partial Least Squares (PLS). We find that the SPCA is superior in the presence of weak factors, both in theory and in finite samples. We illustrate the use of SPCA by applying it to estimate the risk premia of several tradable and nontradable factors, to evaluate asset managers' performance, and to de-noise asset pricing factors.

Long-lead Prediction of ENSO Modoki Index using Machine Learning algorithms

The focus of this study is to evaluate the efficacy of Machine Learning (ML) algorithms in the long-lead prediction of El Niño (La Niña) Modoki (ENSO Modoki) index (EMI). We evaluated two widely used non-linear ML algorithms namely Support Vector Regression (SVR) and Random Forest (RF) to forecast the EMI at various lead times, viz. 6, 12, 18 and 24 months. The predictors for the EMI are identified using Kendall’s tau correlation coefficient between the monthly EMI index and the monthly anomalies of the slowly varying climate variables such as sea surface temperature (SST), sea surface height (SSH) and soil moisture content (SMC). The importance of each of the predictors is evaluated using the Supervised Principal Component Analysis (SPCA). The results indicate both SVR and RF to be capable of forecasting the phase of the EMI realistically at both 6-months and 12-months lead times though the amplitude of the EMI is underestimated for the strong events. The analysis also indicates the SVR to perform better than the RF method in forecasting the EMI.

How Deep Should be the Depth of Convolutional Neural Networks: a Backyard Dog Case Study

The work concerns the problem of reducing a pre-trained deep neuronal network to a smaller network, with just few layers, whilst retaining the network’s functionality on a given task. In this particular case study, we are focusing on the networks developed for the purposes of face recognition. The proposed approach is motivated by the observation that the aim to deliver the highest accuracy possible in the broadest range of operational conditions, which many deep neural networks models strive to achieve, may not necessarily be always needed, desired or even achievable due to the lack of data or technical constraints. In relation to the face recognition problem, we formulated an example of such a use case, the ‘backyard dog’ problem. The ‘backyard dog’, implemented by a lean network, should correctly identify members from a limited group of individuals, a ‘family’, and should distinguish between them. At the same time, the network must produce an alarm to an image of an individual who is not in a member of the family, i.e. a ‘stranger’. To produce such a lean network, we propose a network shallowing algorithm. The algorithm takes an existing deep learning model on its input and outputs a shallowed version of the model. The algorithm is non-iterative and is based on the advanced supervised principal component analysis. Performance of the algorithm is assessed in exhaustive numerical experiments. Our experiments revealed that in the above use case, the ‘backyard dog’ problem, the method is capable of drastically reducing the depth of deep learning neural networks, albeit at the cost of mild performance deterioration. In this work, we proposed a simple non-iterative method for shallowing down pre-trained deep convolutional networks. The method is generic in the sense that it applies to a broad class of feed-forward networks, and is based on the advanced supervise principal component analysis. The method enables generation of families of smaller-size shallower specialized networks tuned for specific operational conditions and tasks from a single larger and more universal legacy network.

Determinants of Latrine Use Behavior: The Psychosocial Proxies of Individual-Level Defecation Practices in Rural Coastal Ecuador.

There is increasing appreciation that latrine access does not imply use-many individuals who own latrines do not consistently use them. Little is known, however, about the determinants of latrine use, particularly among those with variable defecation behaviors. Using the integrated behavior model of water, sanitation, and hygiene framework, we sought to characterize determinants of latrine use in rural Ecuador. We interviewed 197 adults living in three communities with a survey consisting of 70 psychosocial defecation-related questions. Questions were excluded from analysis if responses lacked variability or at least 10% of respondents did not provide a definitive answer. All interviewed individuals had access to a privately owned or shared latrine. We then applied adaptive elastic nets (ENET) and supervised principal component analysis (SPCA) to a reduced dataset of 45 questions among 154 individuals with complete data to select determinants that predict self-reported latrine use. Latrine use was common, but not universal, in the sample (76%). The SPCA model identified six determinants and adaptive ENET selected five determinants. Three indicators were represented in both models-latrine users were more likely to report that their latrine is clean enough to use and also more likely to report daily latrine use; while those reporting that elderly men were not latrine users were less likely to use latrines themselves. Our findings suggest that social norms are important predictors of latrine use, whereas knowledge of the health benefits of sanitation may not be as important. These determinants are informative for promotion of latrine adoption.

Gen Ekspresyon Verilerinde Yapay Sinir Ağlarına Dayalı Yeni Bir Denetimli Temel Bileşenler Analizi’nin Geliştirilmesi

The aim of this study is dimension reduction of multidimensional gene expression data using supervised principal component analysis (S-PCA) and –proposed as a new approach- supervised principal component analysis with artificial neural networks (S-ANN-PCA) and to compare performances of these two methods by using random survival forests (RSF). In simulation application 5000 genes were generated according to multivariate normal distribution and then survival time that is correlated to these gene data were generated for 100 units. Simulation step was carried out with 1000 repetitions. In addition, gene expression data for 240 individuals with extensive B-cell lymphoma (DLBCL) were used. Dimension reduction was done using Wald statistic in selection of important genes. The new data sets obtained from the methods were analyzed using RSF analysis.In the simulation application, it was obtained that the explanatoriness of S-PCA was significantly different from S-ANN-PCA (p<0.001). In the DLBCL data application, it was found that the error rate for the S-PCA was 36.78% and 43% for the S-ANN-PCA as a result of RSF. The importance value of S-PCA method was found to be higher and its error rate was found to be lower than the other method.S-PCA performed better than S-ANN-PCA in analyzing gene expression data experiencing a multidimensional problem.

Satellite-Based Probabilistic Assessment of Soil Moisture Using C-Band Quad-Polarized RISAT1 Data

This paper attempts to probabilistically estimate the surface soil moisture content (SMC) by using the synthetic aperture radar data provided by radar imaging satellite1. The novelty of this paper lies in: 1) developing a combined index to understand the role of all the backscattering coefficients with different polarization and soil texture information in influencing the SMC; 2) using normalized incidence angles, which enables the model to be applicable for different incidence angles; and 3) determination of uncertainty range of the estimated SMC. The dimensionality problem, which is frequently observed in the multivariate analysis, is reduced in the development of the combined index by the use of supervised principal component analysis (SPCA). The SPCA also ensures the maximum attainable association between the developed combined index and surface SMC above wilting point (WP). The association between the combined index and the surface SMC above WP is modeled through joint probability distribution by using the Frank copula. The model is developed and validated with the field soil moisture values over 334 monitoring points within the study area. The outcomes obtained by applying the proposed model indicate an encouraging potential of the model to be applied for bareland and vegetated land (<30 cm height).

Hydroclimatic modelling of local sea level rise and its projection in future

Studies on sea level rise (SLR) in the context of climate change are gaining importance in the recent past. Whereas there is some clear evidence of SLR at global scale, its trend varies significantly from location to location. The role of different meteorological variables on sea level change (SLC) is explored. We hypothesise that the role of such variables varies from location to location and modelling of local SLC requires a proper identification of specific role of individual factors. After identifying a group of various local meteorological variables, Supervised Principal Component Analysis (SPCA) is used to develop a location specific Combined Index (CI). The SPCA ensures that the developed CI possesses highest possible association with the historical SLC at that location. Further, using the developed CI, an attempt is made to model the local sea level (LSL) variation in synchronous with the changing climate. The developed approach, termed as hydroclimatic semi-empirical approach, is found to be potential for local SLC at different coastal locations. The validated hydroclimatic approach is used for future projection of SLC at those coastal locations till 2100 for different climate change scenarios, i.e. different Representative Concentration Pathways (RCPs). Future hydrometeorological variables are obtained from Global Climate Models (GCMs) for different such scenarios, i.e. RCP2.6, RCP4.5 and RCP8.5. Effect of glacial isostatic readjustment (GIA) is not included in this study. However, if the reliable information on GIA is available for a location, the same can be arithmetically added to the final outcome of the proposed hydrometeorological approach.

Radiomic Profiling of Glioblastoma: Identifying an Imaging Predictor of Patient Survival with Improved Performance over Established Clinical and Radiologic Risk Models

Purpose To evaluate whether radiomic feature-based magnetic resonance (MR) imaging signatures allow prediction of survival and stratification of patients with newly diagnosed glioblastoma with improved accuracy compared with that of established clinical and radiologic risk models. Materials and Methods Retrospective evaluation of data was approved by the local ethics committee and informed consent was waived. A total of 119 patients (allocated in a 2:1 ratio to a discovery [n = 79] or validation [n = 40] set) with newly diagnosed glioblastoma were subjected to radiomic feature extraction (12 190 features extracted, including first-order, volume, shape, and texture features) from the multiparametric (contrast material-enhanced T1-weighted and fluid-attenuated inversion-recovery imaging sequences) and multiregional (contrast-enhanced and unenhanced) tumor volumes. Radiomic features of patients in the discovery set were subjected to a supervised principal component (SPC) analysis to predict progression-free survival (PFS) and overall survival (OS) and were validated in the validation set. The performance of a Cox proportional hazards model with the SPC analysis predictor was assessed with C index and integrated Brier scores (IBS, lower scores indicating higher accuracy) and compared with Cox models based on clinical (age and Karnofsky performance score) and radiologic (Gaussian normalized relative cerebral blood volume and apparent diffusion coefficient) parameters. Results SPC analysis allowed stratification based on 11 features of patients in the discovery set into a low- or high-risk group for PFS (hazard ratio [HR], 2.43; P = .002) and OS (HR, 4.33; P < .001), and the results were validated successfully in the validation set for PFS (HR, 2.28; P = .032) and OS (HR, 3.45; P = .004). The performance of the SPC analysis (OS: IBS, 0.149; C index, 0.654; PFS: IBS, 0.138; C index, 0.611) was higher compared with that of the radiologic (OS: IBS, 0.175; C index, 0.603; PFS: IBS, 0.149; C index, 0.554) and clinical risk models (OS: IBS, 0.161, C index, 0.640; PFS: IBS, 0.139; C index, 0.599). The performance of the SPC analysis model was further improved when combined with clinical data (OS: IBS, 0.142; C index, 0.696; PFS: IBS, 0.132; C index, 0.637). Conclusion An 11-feature radiomic signature that allows prediction of survival and stratification of patients with newly diagnosed glioblastoma was identified, and improved performance compared with that of established clinical and radiologic risk models was demonstrated. (©) RSNA, 2016 Online supplemental material is available for this article.

A Comparative Study of Five Association Tests Based on CpG Set for Epigenome-Wide Association Studies.

An epigenome-wide association study (EWAS) is a large-scale study of human disease-associated epigenetic variation, specifically variation in DNA methylation. High throughput technologies enable simultaneous epigenetic profiling of DNA methylation at hundreds of thousands of CpGs across the genome. The clustering of correlated DNA methylation at CpGs is reportedly similar to that of linkage-disequilibrium (LD) correlation in genetic single nucleotide polymorphisms (SNP) variation. However, current analysis methods, such as the t-test and rank-sum test, may be underpowered to detect differentially methylated markers. We propose to test the association between the outcome (e.g case or control) and a set of CpG sites jointly. Here, we compared the performance of five CpG set analysis approaches: principal component analysis (PCA), supervised principal component analysis (SPCA), kernel principal component analysis (KPCA), sequence kernel association test (SKAT), and sliced inverse regression (SIR) with Hotelling’s T2 test and t-test using Bonferroni correction. The simulation results revealed that the first six methods can control the type I error at the significance level, while the t-test is conservative. SPCA and SKAT performed better than other approaches when the correlation among CpG sites was strong. For illustration, these methods were also applied to a real methylation dataset.

Çok Boyutlu Sağkalım Verilerinde Denetimli Temel Bileşenler Analizine Alternatif Bir Boyut İndirgeme Yaklaşımı

Objective: This study aims at comparing the performances of supervised principal component analysis (SPCA) which is used for dimension reduction and an alternatively proposed approach of nonlinear principal component analysis using artificial neural networks performed by gene selection with survival tree (survival tree based NLPCA- NN). Material and Methods: Gene expression data set from Rosenwald et al.(2002) pertaining to 240 patients with diffuse large B-cell lymphoma (DLBCL) is used. While Cox scores are used for determining important genes from high dimensional gene expression data in SPCA, in survival tree based NLPCA-NN approach, importance values of the survival tree are used. Important genes according to the Cox scores are reduced to three principal components by singular value decomposition. Important genes determined by the survival tree are taken as input variables in neural networks and reduced to three principal components. The performances of SPCA and survival tree based NLPCA-NN are compared by using Cox regression models (CRM). C index is calculated to compare obtained Cox regression models. Results: According to Cox scores, 121 genes are determined; according to importance values of survival tree 114 genes are determined. The percentages of variances explained by SPCA and survival tree based NLPCA-NN were 18.2% and 35.1% respectively. Harrell?s C indexes are calculated as 0.726 for CRM-1, 0.687 for CRM-2. Conclusion: As a result, while SPCA takes only the linear relationships into consideration, survival tree based NLPCA-NN also takes non-linear relationships into account and has more variance explanation and NLPCA-NN can be evaluated as an alternative method to SPCA.

A hydrometeorological approach for probabilistic simulation of monthly soil moisture under bare and crop land conditions

AbstractThis study focuses on the probabilistic estimation of monthly soil moisture variation by considering (a) the influence of hydrometeorological forcing to model the temporal variation and (b) the information of Hydrological Soil Groups (HSGs) and Agro‐Climatic Zones (ACZs) to capture the spatial variation. The innovative contributions of this study are: (i) development of a Combined Hydro‐Meteorological (CHM) index to extract the information of different influencing hydrometeorological variables, (ii) consideration of soil‐hydrologic characteristics (through HSGs) and climate regime‐based zoning for agriculture (through ACZs), and (iii) quantification of uncertainty range of the estimated soil moisture. Usage of Supervised Principal Component Analysis (SPCA) in the development of the CHM index helps to eliminate the “curse of dimensionality,” typically arises in the multivariate analysis. The usage of SPCA also ensures the maximum possible association between the developed CHM index and soil moisture variation. The association between these variables is modeled through their joint distribution which is obtained by using the theory of copula. The proposed approach is also spatially transferable, since the information on HSGs and ACZs is considered. The “leave‐one‐out” cross‐validation (LOO‐CV) approach is adopted for stations belong to a particular HSG to examine the spatial transferability. The simulated soil moisture values are also compared with a few existing soil moisture data sets, derived from different Land Surface Models (LSMs) or retrieved from different satellite‐based missions. The potential of the proposed approach is found to be promising and even applicable to crop land also, though with a lesser degree of efficiency as compared to bare land conditions.