This chapter highlights the application of Principal Component Analysis (PCA) in order to analyze oil spill contaminants, specifically focusing on PAH as a source identification and dimensionality reduction. This chapter described the dominant linear combinations of original variables that explain variability, filter out less significant parameter while retaining essential data structure. Plus, this chapter also simplifies the oil spill sample datasets which derived from GC-FID and GC–MS methods in order to get better performance in data visualization, noise reduction and also machine learning performance. As conclusion in this chapter shown that PCA is a powerful and essential tool in oil spill fingerprinting. By emphasizing significant PAH patterns, it improves the clarity of chemical datasets and supports environmental forensics through effective source tracing. Principal Component Analysis (PCA) is known as one of the popular techniques for reducing dimensionality in diverse field, including data science and statistics. This technique enables breaking down complicated datasets into a collection of uncorrelated variables known as main components, which represent the greatest amount of variance in the data. Moreover, it has since grown to be a vital tool in exploratory data analysis (Karl in Structure and properties of condensed matter 2:11 (1901), especially for finding correlations, patterns, and trends in high-dimensional datasets. A linear combination of the initial variables makes up each main component in PCA. The largest variance in the data is captured by the first Principal Component, which is followed by the second component, which represents the next biggest variance, and so forth. By applying this technique, the complicated data derived from oil mixtures is made simpler, making the dataset easier to handle and understand. By this procedure, the technique aids in identifying and removing the most important factors that contribute to the variations among the oil samples, making it easier to understand the data in a way that is more relevant and clearer. Assume we have thousands of photos in a massive photo album. Color, brightness, objects, and other details are all present in every image. What would happen, though, if minimization the file size while preserving the most crucial information? Principal Component Analysis, or PCA, is what does that. It allows to preserve the important details while compressing, eliminating noise, visualizing complex data, and enhancing machine learning models. Specific objectives of PCA: • An objective of this technique is to identify linear combinations of the original variables that are useful in accounting for the variation in those variables. This is effectively a clustering of the variables. • It provides information on the most meaningful parameters due to spatial and temporal variations that describe the whole dataset by excluding the less significant parameters with minimum loss of original information.

Contaminant of Polyaromatic Hydrocarbon in Oil Spills

章节
发表日期：

2026年

查看全文

Azimah Ismail,
Hafizan Juahir

摘要

This chapter highlights the application of Principal Component Analysis (PCA) in order to analyze oil spill contaminants, specifically focusing on PAH as a source identification and dimensionality reduction. This chapter described the dominant linear combinations of original variables that explain variability, filter out less significant parameter while retaining essential data structure. Plus, this chapter also simplifies the oil spill sample datasets which derived from GC-FID and GC–MS methods in order to get better performance in data visualization, noise reduction and also machine learning performance. As conclusion in this chapter shown that PCA is a powerful and essential tool in oil spill fingerprinting. By emphasizing significant PAH patterns, it improves the clarity of chemical datasets and supports environmental forensics through effective source tracing. Principal Component Analysis (PCA) is known as one of the popular techniques for reducing dimensionality in diverse field, including data science and statistics. This technique enables breaking down complicated datasets into a collection of uncorrelated variables known as main components, which represent the greatest amount of variance in the data. Moreover, it has since grown to be a vital tool in exploratory data analysis (Karl in Structure and properties of condensed matter 2:11 (1901), especially for finding correlations, patterns, and trends in high-dimensional datasets. A linear combination of the initial variables makes up each main component in PCA. The largest variance in the data is captured by the first Principal Component, which is followed by the second component, which represents the next biggest variance, and so forth. By applying this technique, the complicated data derived from oil mixtures is made simpler, making the dataset easier to handle and understand. By this procedure, the technique aids in identifying and removing the most important factors that contribute to the variations among the oil samples, making it easier to understand the data in a way that is more relevant and clearer. Assume we have thousands of photos in a massive photo album. Color, brightness, objects, and other details are all present in every image. What would happen, though, if minimization the file size while preserving the most crucial information? Principal Component Analysis, or PCA, is what does that. It allows to preserve the important details while compressing, eliminating noise, visualizing complex data, and enhancing machine learning models. Specific objectives of PCA: • An objective of this technique is to identify linear combinations of the original variables that are useful in accounting for the variation in those variables. This is effectively a clustering of the variables. • It provides information on the most meaningful parameters due to spatial and temporal variations that describe the whole dataset by excluding the less significant parameters with minimum loss of original information.