Multivariate Statistical Algorithms Research Articles

Geometallurgical modeling and reconciliation with production data in a fhosphate mine

The characterization of the ore and its performance prediction in the processing unit are essential for the success of mining projects and should be part of the resource model. The greatest difficulties encountered in the elaboration of these models are the characteristics of the metallurgical variables, such as non-additivity and non-linearity, lack of uniformity of the database and the few samples of process tests. The generalization of geometallurgical models from primary attributes is a valid option when the relationships between geological characteristics and metallurgical responses are well established and will be tested in this work. Bench tests that simulate the mineral concentration process were performed and compared with geological and chemical information. Multivariate statistical analyses and computational algorithms allowed the prediction of metallurgical attributes from the properties of the rocks simulated by Gaussian sequential simulation. The results were reconciled with the plant data over a period of one year and proved to be consistent.

Label-free detection of kidney stones urine combined with SERS and multivariate statistical algorithm

Kidney stones are a common urological disease with an increasing incidence worldwide. Traditional diagnostic methods for kidney stones are relatively complex and time-consuming, thus necessitating the development of a quicker and simpler diagnostic approach. This study investigates the clinical screening of kidney stones using Surface-Enhanced Raman Scattering (SERS) technology combined with multivariate statistical algorithms, comparing the classification performance of three algorithms (PCA-LDA, PCA-LR, PCA-SVM). Urine samples from 32 kidney stone patients, 30 patients with other urinary stones, and 36 healthy individuals were analyzed. SERS spectra data were collected in the range of 450–1800 cm−1 and analyzed. The results showed that the PCA-SVM algorithm had the highest classification accuracy, with 92.9 % for distinguishing kidney stone patients from healthy individuals and 92 % for distinguishing kidney stone patients from those with other urinary stones. In comparison, the classification accuracy of PCA-LR and PCA-LDA was slightly lower. The findings indicate that SERS combined with PCA-SVM demonstrates excellent performance in the clinical screening of kidney stones and has potential for practical clinical application. Future research can further optimize SERS technology and algorithms to enhance their stability and accuracy, and expand the sample size to verify their applicability across different populations. Overall, this study provides a new method for the rapid diagnosis of kidney stones, which is expected to play an important role in clinical diagnostics.

Comment on "Raman spectroscopy combined with multivariate statistical algorithms for the simultaneous screening of cervical and breast cancers".

This article discusses current research on the detection of cervical and breast cancer using in vitro Raman spectral analysis of human serum by Cao et al. (2024) which was published in the Lasers in Medical Science journal. Despite the high accuracy of the suggested approach (93%), the demonstrated findings could be treated unclear due to possible overestimation of the classification models.

A strategy integrating GC–MS, UPLC profiling, and DNA metabarcoding for characterization and discrimination of the medicinal and culinary pieces from four Curcuma species

Curcumae pieces prepared in ready-to-use forms, consumed extensively for their significant medicinal and culinary benefits, present a challenge in discrimination due to their heterogeneous origins, analogous morphologies, and varied components. This study explored the metabolites of nine Curcumae pieces (NCPs) by Gas Chromatography-Mass Spectrometry (GC–MS) and Ultra-Performance Liquid Chromatography/Ultra High-Performance Liquid Chromatography–Quadrupole Time of Flight–Mass Spectrometry (UPLC/UHPLC–QTOF–MS) technologies, augmented by multivariate statistical analysis (Principal Component Analysis, PCA; Orthogonal Partial Least Squares Discriminant Analysis, OPLS–DA) and machine learning algorithms (Random Forest, RF). Twenty-six key differential markers in volatile and non-volatile metabolites each were found subsequently. Additionally, DNA metabarcoding was employed to develop specific Single Nucleotide Polymorphism (SNP) markers for the precise identification of Curcuma species in single and mixed samples, and for CRa even contained in Chinese patent prescriptions. The integration of these three methodologies facilitates a more reliable authentication of NCPs, enhancing the overall strategy for their global discrimination. This research contributes to the advancement of quality control and the development of functional foods or products derived from Curcumae pieces, tailored to meet specific health and dietary requirements.

A highly sensitive SERS substrate of porous membrane-Ag NPs for kidney cancer detection

BackgroundThe substrate employed in surface-enhanced Raman spectroscopy (SERS) constitutes an essential element in the cancer detection methodology. In this research, we introduce a three-dimensional (3D) structured SERS substrate that integrates a porous membrane with silver nanoparticles to enhance SERS spectral signals through the utilization of the aggregation effect of silver nanoparticles. This enhancement is crucial because accurate detection results strongly depend on the intensity of specific peaks in Raman spectroscopy. A highly sensitive SERS substrate can significantly improve the accuracy of detection results. ResultsWe collected 66 plasma samples from individuals with kidney cancer and control individuals, including both bladder cancer patients and healthy individuals. Then, we utilized substrates with and without porous membranes to acquire the SERS spectra of the samples, enabling us to evaluate the enhancement effect of our SERS substrate. The spectral analysis demonstrated enhanced peak intensities in the experimental group (with porous substrate) compared to the control group (without porous substrate). The uniformity and reproducibility of the SERS substrate are also significantly enhanced, which is very helpful for improving the accuracy of detection results. Additionally, the Principal Component Analysis-Linear Discriminant Analysis algorithm (PCA-LDA) was employed to classify the SERS spectra of both groups. In the experimental group, the classification accuracy was 98.5 % for kidney cancer, and 83.3 % for kidney and bladder cancer. Compared to the control group, it improved by 3 % and 12.6 % respectively. SignificantThis indicates that our 3D structured SERS substrate combined with multivariate statistical algorithms PCA-LDA can not only improve the accuracy of SERS detection technology in single cancer detection, but also has great potential in multiple cancer detection. This 3D structured SERS substrate is expected to become a new auxiliary means for cancer detection.

Low-abundance proteins-based label-free SERS approach for high precision detection of liver cancer with different stages

BackgroundSurface-enhanced Raman scattering (SERS) technology have unique advantages of rapid, simple, and highly sensitive in the detection of serum, it can be used for the detection of liver cancer. However, some protein biomarkers in body fluids are often present at ultra-low concentrations and severely interfered with by the high-abundance proteins (HAPs), which will affect the detection of specificity and accuracy in cancer screening based on the SERS immunoassay. Clearly, there is a need for an unlabeled SERS method based on low abundance proteins, which is rapid, noninvasive, and capable of high precision detection and screening of liver cancer. ResultsSerum samples were collected from 60 patients with liver cancer (27 patients with stage T1 and T2 liver cancer, 33 patients with stage T3 and T4 liver cancer) and 40 healthy volunteers. Herein, immunoglobulin and albumin were separated by immune sorption and Cohn ethanol fractionation. Then, the low abundance protein (LAPs) was enriched, and high-quality SERS spectral signals were detected and obtained. Finally, combined with the principal component analysis-linear discriminant analysis (PCA-LDA) algorithm, the SERS spectrum of early liver cancer (T1-T2) and advanced liver cancer (T3-T4) could be well distinguished from normal people, and the accuracy rate was 98.5% and 100%, respectively. Moreover, SERS technology based on serum LAPs extraction combined with the partial least square-support vector machine (PLS-SVM) successfully realized the classification and prediction of normal volunteers and liver cancer patients with different tumor (T) stages, and the diagnostic accuracy of PLS-SVM reached 87.5% in the unknown testing set. SignificanceThe experimental results show that the serum LAPs SERS detection combined with multivariate statistical algorithms can be used for effectively distinguishing liver cancer patients from healthy volunteers, and even achieved the screening of early liver cancer with high accuracy (T1 and T2 stage). These results showed that serum LAPs SERS detection combined with a multivariate statistical diagnostic algorithm has certain application potential in early cancer screening.

Raman spectroscopy combined with multivariate statistical algorithms for the simultaneous screening of cervical and breast cancers.

Breast and cervical cancers are becoming the leading causes of death among women worldwide, but current diagnostic methods have many drawbacks, such as being time-consuming and high cost. Raman spectroscopy, as a rapid, reliable, and non-destructive spectroscopic detection technique, has achieved many breakthrough results in the screening and prognosis of various cancer tumors. Therefore, in this study, Raman spectroscopy technology was used to diagnose breast cancer and cervical cancer. A total of 225 spectra were recorded from 87 patients with cervical cancer, 60 patients with breast cancer, and 78 healthy individuals. The obvious difference in Raman spectrum between the three groups was mainly shown at 809cm-1 (tyrosine), 958cm-1 (carotenoid), 1004cm-1 (phenylalanine), 1154cm-1 (β-carotene), 1267cm-1 (Amide III), 1445cm-1 (phospholipids), 1515cm-1 (β-carotene), and 1585cm-1 (C = C olefinic stretch). We used one-way analysis of variance for these peaks and demonstrated that they were significantly different. Then, we combined the detected Raman spectra with multivariate statistical calculations using the principal component analysis-linear discrimination algorithm (PCA-LDA) to discriminate between the three groups of collected serum samples. The diagnostic results showed that the model's accuracy, precision, recall, and F1 score of the model were 92.90%, 92.62%, 92.10%, and 92.36%, respectively. These results suggest that Raman spectroscopy can achieve ultra-sensitive detection of serum, and the developed diagnostic models have great potential for the prognosis and simultaneous screening of cervical and breast cancers.

Early on–site detection of strawberry anthracnose using portable Raman spectroscopy

We developed a method for the early on–site detection of strawberry anthracnose using a portable Raman system with multivariate statistical analysis algorithms. By using molecular markers based on Raman spectra, the proposed method can detect anthracnose in strawberry stems 3 days after exposure to Colletotrichum gloeosporioides. A fiber–optic probe was applied for the portable Raman system, and the acquisition time was 10 s. We found that the molecular markers were closely related to the following subjects: i) an increase in amide III and fatty acids of C. gloeosporioides invading strawberry stems (Raman bands at 1180–1310 cm−1) and ii) a decrease in metabolites in strawberry plants, such as phenolic compounds and terpenoids (Raman bands at 760, 800, and 1523 cm−1). We also found that the increased fluorescence background caused by various chromophores within the invading C. gloeosporioides could serve as a marker. A two–dimensional cluster plot obtained by principal component analysis (PCA) showed that the three groups (control, fungal infection, and pathogen) were distinguishable. The linear discriminant analysis (LDA)–based prediction algorithm could identify C. gloeosporioides infection with a posterior probability of over 40%, even when no symptoms were visible on the inoculated strawberry plants.

Multivariate statistical algorithms for landslide susceptibility assessment in Kailash Sacred landscape, Western Himalaya

Landslide susceptibility mapping plays an imperative role in mitigating hazards and determining the future direction of developmental activities in mountainous regions. Here, we used 518 landslide occurrences and nine landslide-conditioning parameters to build landslide vulnerability models in the Kailash Sacred Landscape (KSL), India. Four multivariate statistical models were applied, namely the generalized linear model (GLM), maximum entropy (MaxEnt), Mahalanobis D2 (MD), and support vector machine (SVM), to calibrate and compare four maps of landslide susceptibility. The results demonstrated the outperformance of Mahalanobis D2 for predictability compared to other models obtained from the area under the receiver operating characteristic curve (ROC). The ensemble model data shows that 10.5% of the landscape has susceptible conditions for future landslides, whereas 89.50% of the landscape falls under the safe zone. The occurrence of landslides in the KSL is linked to the middle elevations, vicinity to water bodies, and the motorable roads. Furthermore, the observed patterns and the resulting models exhibit the major variables that cause landslides and their respective significance. The current modelling approach could provide baseline data at the regional scale to improve the developmental planning in the KSL.

Label‐free surface‐enhanced Raman spectroscopy detection of prostate cancer combined with multivariate statistical algorithm

AbstractThe purpose of this study was to detect human plasma for screening prostate cancer (PCa) and benign prostatic hyperplasia (BPH) based on surface‐enhanced Raman spectroscopy (SERS) and multivariate statistical algorithms. The test was to detect 106 plasma samples, which originated from 39 normal subjects, 26 patients with PCa and 41 patients with BPH. Significant differences in peak intensity at 495, 636, 1135, 1205, and 1675 cm−1 can be observed from the difference spectrogram, which contributes to initially distinguish the cancer group from the normal group. Then, the multivariate statistical techniques, including principal component analysis (PCA) and linear discriminant analysis (LDA) diagnostic algorithms, as well as recursive weighted partial least square (PLS) method and support vector machine (SVM) algorithm, were used to analyze the spectral data. For PCa versus normal group and BPH versus normal group, the classification accuracy of PCA‐LDA was 96.80% and 97.50%, respectively, and the classification accuracy of PLS‐SVM was 100.00% and 100.00%, respectively. In the diagnosis of PCa and BPH, the sensitivity, specificity and accuracy of PCA‐LDA were 65.40%, 75.60%, and 71.06% respectively, and the area under the curve (AUC) value of the receiver operating characteristic (ROC) curve was 0.788, while the sensitivity, specificity and accuracy of PLS‐SVM were 88.46%, 87.80%, and 88.06%, respectively, and the AUC value was 0.881. The diagnostic results of PLS‐SVM are better than PCA‐LDA, which supported that PLS‐SVM algorithm has greater potential than PCA‐LDA algorithm in the pre‐diagnosis and screening of PCa.

Multi-Scale Process Monitoring Based on Time-Frequency Analysis and Feature Fusion

Data-driven process monitoring is an important tool to ensure safe production and smooth operation. Generally, implicit information can be mined through data processing and analysis algorithms to detect process disturbances on the basis of historical production data. In industrial practice, signals with different sources of disturbance show different distribution patterns along with the time domain and frequency domain, that is, noise and pulse-type changes are usually contained in the high-frequency portion while most process dynamic is contained in the low-frequency portion. However, feature extraction is usually implemented at a single scale in traditional multivariate statistical algorithms. With this concern, a novel multi-scale process monitoring method is proposed in this work, by which wavelet packet decomposition is first employed for time-frequency analysis. After decomposition, multivariate statistical models are established for each scale to construct process statistics. For the high-frequency part, the classical principal component analysis (PCA) algorithm is adopted to construct squared prediction error (SPE) and Hotelling T2(T2) statistics. While for the low-frequency part, the slow feature analysis (SFA) algorithm is adopted to construct T2, Te2, S2 and Se2 statistics for the extraction of the long-term slowly changing trend. Then the monitoring statistics, obtained from each method at different scales, are integrated by a support vector data description (SVDD) method to give a final fault detection decision. The performance of the proposed method is verified on the benchmark Tennessee Eastman Process (TEP) and an industrial continuous catalytic reforming heat exchange unit by comparing with related multivariate statistical methods, which only focus on a single scale.

Electronic noses based on metal oxide nanowires: A review

Abstract Metal oxides are ideal for the fabrication of gas sensors: they are sensitive to many gases while allowing the device to be simple, tiny, and inexpensive. Nonetheless, their lack of selectivity remains a limitation. In order to achieve good selectivity in applications with many possible interfering gases, the sensors are inserted into an electronic nose that combines the signals from nonselective sensors and analyzes them with multivariate statistical algorithms in order to obtain selectivity. This review analyzes the scientific articles published in the last decade regarding electronic noses based on metal oxide nanowires. After a general introduction, Section 2 discusses the issues related to poor intrinsic selectivity. Section 3 briefly reviews the main algorithms that have hitherto been used and the results they can provide. Section 4 classifies the recent literature into fundamental research, agrifood, health, security. In Section 5, the literature is analyzed regarding the metal oxides, the surface decoration nanoparticles, the features that differentiate the sensors in a given array, the application for which the device was developed, the algorithm used, and the type of information obtained. Section 6 concludes by discussing the present state and points out the requirements for their use in real-world applications.

Towards the direct detection of viral materials at the surface of protective face masks via infrared spectroscopy

The ongoing COVID-19 pandemic represents a considerable risk for the general public and especially for health care workers. To avoid an overloading of the health care system and to control transmission chains, the development of rapid and cost-effective techniques allowing for the reliable diagnosis of individuals with acute respiratory infections are crucial. Uniquely, the present study focuses on the development of a direct face mask sampling approach, as worn (i.e., used) disposable face masks contain exogenous environmental constituents, as well as endogenously exhaled breath aerosols. Optical techniques—and specifically infrared (IR) molecular spectroscopic techniques—are promising tools for direct virus detection at the surface of such masks. In the present study, a rapid and non-destructive approach for monitoring exposure scenarios via medical face masks using attenuated total reflection infrared spectroscopy is presented. Complementarily, IR external reflection spectroscopy was evaluated in comparison for rapid mask analysis. The utility of a face mask-based sampling approach was demonstrated by differentiating water, proteins, and virus-like particles sampled onto the mask. Data analysis using multivariate statistical algorithms enabled unambiguously classifying spectral signatures of individual components and biospecies. This approach has the potential to be extended towards the rapid detection of SARS-CoV-2—as shown herein for the example of virus-like particles which are morphologically equivalent to authentic virus—without any additional sample preparation or elaborate testing equipment at laboratory facilities. Therefore, this strategy may be implemented as a routine large-scale monitoring routine, e.g., at health care institutions, nursing homes, etc. ensuring the health and safety of medical personnel.

IonFlow: a galaxy tool for the analysis of ionomics data sets

IntroductionInductively coupled plasma mass spectrometry (ICP-MS) experiments generate complex multi-dimensional data sets that require specialist data analysis tools.ObjectiveHere we describe tools to facilitate analysis of the ionome composed of high-throughput elemental profiling data.MethodsIonFlow is a Galaxy tool written in R for ionomics data analysis and is freely accessible at https://github.com/wanchanglin/ionflow. It is designed as a pipeline that can process raw data to enable exploration and interpretation using multivariate statistical techniques and network-based algorithms, including principal components analysis, hierarchical clustering, relevance network extraction and analysis, and gene set enrichment analysis.Results and ConclusionThe pipeline is described and tested on two benchmark data sets of the haploid S. Cerevisiae ionome and of the human HeLa cell ionome.

Unsupervised methods in LC-MS data treatment: Application for potential chemotaxonomic markers search

The combination of Liquid Chromatography and Mass Spectrometry (LC-MS) is commonly used to determine and characterize biologically active compounds because of its high resolution and sensitivity. In this work we explore the interpretation of LC-MS data using multivariate statistical analysis algorithms to extract useful chemical information and identify clusters of similar samples. Samples of leaves from 19 plants belonging to the Apiaceae family were analyzed in unified LC conditions by high- and low-resolution mass spectrometry in a wide range scan mode. LC-MS data preprocessing was performed followed by statistical analysis using tensor decomposition in the form of Parallel Factor Analysis (PARAFAC); matrix factorization following tensor unfolding with principal component analysis (PCA), independent component analysis (ICA), non-negative matrix factorization (NMF); or unsupervised feature selection (UFS). The optimal number of components for each of these methods were found and results were compared using four different metrics: silhouette score, Davies-Bouldin index, computational time, number of noisy components. It was found that PCA, ICA and UFS give the best results across the majority of the criteria for both low- and high-resolution data. An algorithm for biomarker signal selection is suggested and 23 potential chemotaxonomic markers were tentatively identified using MS2 data. Dendrograms constructed by the methods were compared to the molecular phylogenic tree by calculating pixel-wise mean square error (MSE). Therefore, the suggested approach can support chemotaxonomic studies and yield valuable chemical information for biomarker discovery.

A holistic methodology to study geochemical and geomorphological control of the distribution of potentially toxic elements in soil

Control of Potentially Toxic Elements (PTEs) in soil-polluted areas is needed to address the potential risk that pollution poses to public health and the environment. This study describes an innovative holistic methodology to assess the distribution of PTEs. It is based on the application of multi-variate statistical and geostatistical algorithms, soil pollution indices and geochemical & geomorphological/climate variables (element concentration, watercourses, winds, slope, orientation and visibility). The methodology proposed is exemplified through a comprehensive soil sampling in an area surrounding a former As-Hg mine that presents several sources of pollutants (abandoned mining spoil heaps, metallurgical waste, old chimneys, etc.). Factor analysis identified four main pollutants of concern: Hg, As, Pb and Sb. The mobility of the most abundant PTEs, especially As, and, to a minor extent, Hg, showed a clear influence of climatic/geomorphological variables. Moreover, the pollution indices confirmed that although the soils in the areas around the spoil heaps contain higher concentrations of the pollutants, the influence of the chimneys is present in the whole study area and depends on factors such as orientation and visibility. In contrast, the fingerprint of the spoil heaps showed a PTE distribution more associated with the slope factor and the presence of watercourses eroding the heaps. All things considered, the methodology proposed revealed PTE sources and distribution in a highly complex site and may therefore find application in similar scenarios of contamination.

Raman spectroscopy of follicular fluid and plasma with machine-learning algorithms for polycystic ovary syndrome screening

Polycystic ovary syndrome (PCOS) is the main cause of anovulatory infertility and affects women throughout their lives. The specific diagnostic method is still under investigation. In the present study, we aimed to identify the metabolic tracks of the follicular fluid and plasma samples from women with PCOS by performing Raman spectroscopy with principal component analysis and spectral classification models. Follicular fluid and plasma samples obtained from 50 healthy (non-PCOS) and 50 PCOS women were collected and measured by Raman spectroscopy. Multivariate statistical methods and different machine-learning algorithms based on the Raman spectra were established to analyze the results. The principal component analysis of the Raman spectra showed differences in the follicular fluid between the non-PCOS and PCOS groups. The stacking classification models based on the k-nearest-neighbor, random forests and extreme gradient boosting algorithms yielded a higher accuracy of 89.32% by using follicular fluid than the accuracy of 74.78% obtained with plasma samples in classifying the spectra from the two groups. In this regard, PCOS may lead to the changes of metabolic profiles that can be detected by Raman spectroscopy. As a novel, rapid and affordable method, Raman spectroscopy combined with advanced machine-learning algorithms have potential to analyze and characterize patients with PCOS.

Abstract 1922: Tamoxifen detection by molecular fluorescence in breast cancer patients as a screening for metabolizer classification

Abstract Breast cancer patients with polymorphic changes in the CYP2D6 gene show considerable variations in tamoxifen (TMX) bioavailability due to the need for bioactivation of this drug. Therefore, patients with such allelic changes have a worse prognosis compared to controls. Biospectroscopy allows the analysis of biofluids, providing the complete characterization of all molecules present in the biological matrix. Among spectroscopic techniques, molecular fluorescence stands out for its high analytical sensitivity in the broad identification of information obtained by the excitation-emission fluorescence matrix (EEM). This allows the specific measurement of fluorescent species in the sample. Quantification of TMX by fluorescence spectroscopy provides a phenotypic assessment of the patient's pharmacological metabolizing status, leading to a personalized and effective pharmacological therapy. We applied fluorescence spectroscopy to blood samples from n=20 women, who had genotyping of the CYP2D6*4_g.1846G>A allele, which confers decreased protein activity. We were able to demonstrate that the fluorescence signal generated by the TMX structure in plasma solution could be detected using our methodology. The data collected exhibited signal interference due to the numerous molecular species present in this matrix. However, using multivariate statistical algorithms we could extract relevant information from the analyte, improving the signal / noise of the emission-excitation matrix. Finally, we were able to demonstrate that low cost method, which can be performed rapidly, may allow for a simple point of care stratification of patients by the CYP2D6 status, which in turn may allow for increased personalization of tamoxifen therapy for breast cancer patients. Citation Format: Lorenna Larissa Ferreira Costa, Daniel Lucas Dantas de Freitas, Kassio Michell Gomes de Lima, Tirzah Braz Petta Lajus. Tamoxifen detection by molecular fluorescence in breast cancer patients as a screening for metabolizer classification [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 1922.

Virtual Patients: An Enabling Technology for Multivariable Control of Biomedical Systems

This paper presents the development of virtual patients to enable the simulation evaluation and assessment of multivariable control algorithms for biomedical systems. The virtual patients are generated by fitting the parameters of the models to clinical experimental data, followed by the estimation of the multivariate distribution of the actual patient parameters. The estimated multivariate distribution is then incorporated with constraints to ensure the sampling of synthetic virtual patients conforms to the actual patient parameter bounds. The sampled synthetic virtual patients are analyzed through multivariate statistical techniques and data clustering algorithms to prune out virtual subjects with similar characteristics or unrealistic dynamics, yielding a virtual patient population that is diverse and with individually distinct characteristics. The generated virtual patient population is used to evaluate multivariable nonlinear and adaptive control algorithms for insulin dosing in people with Type 1 diabetes.

Multivariate statistical applications for quantifying contribution of seismic data to production prediction in the Wolfcamp, Midland Basin

A workflow with the objective of quantifying the added value of seismic-based information to improved prediction of oil production in the Wolfcamp section of the Midland Basin is described. A variety of multivariate statistical algorithms are employed in the workflow: unsupervised and supervised classification, categorical-based nonlinear regression, and spatial regression for well log estimation. Porosity is estimated from elastic inversion volumes within the context of lithotype classification originating with well logs. Porosity feet becomes the primary driver in production prediction. Two parallel analyses are performed. In the first, only well logs are used to predict porosity along all vertical wellbores. As a proxy for the impact of well spacing, different minimum search distances are investigated for porosity estimation error and associated error in prediction of cumulative oil production at six months. The second analysis is similar except, along each wellbore, porosity is extracted from the seismic porosity volume and then used as soft data. These two analysis flows are then applied to horizontal wellbores, which have no original porosity logs, to compare how well each predicts known cumulative production. The incorporation of seismic-based information does show significant error reduction.