A K-Nearest Neighbors Algorithm in Python for Visualizing the 3D Stratigraphic Architecture of the Llobregat River Delta in NE Spain

Abstract

The k-nearest neighbors (KNN) algorithm is a non-parametric supervised machine learning classifier; which uses proximity and similarity to make classifications or predictions about the grouping of an individual data point. This ability makes the KNN algorithm ideal for classifying datasets of geological variables and parameters prior to 3D visualization. This paper introduces a machine learning KNN algorithm and Python libraries for visualizing the 3D stratigraphic architecture of sedimentary porous media in the Quaternary onshore Llobregat River Delta (LRD) in northeastern Spain. A first HTML model showed a consecutive 5 m-equispaced set of horizontal sections of the granulometry classes created with the KNN algorithm from 0 to 120 m below sea level in the onshore LRD. A second HTML model showed the 3D mapping of the main Quaternary gravel and coarse sand sedimentary bodies (lithosomes) and the basement (Pliocene and older rocks) top surface created with Python libraries. These results reproduce well the complex sedimentary structure of the LRD reported in recent scientific publications and proves the suitability of the KNN algorithm and Python libraries for visualizing the 3D stratigraphic structure of sedimentary porous media, which is a crucial stage in making decisions in different environmental and economic geology disciplines.

A Python Application for Visualizing an Imbricate Thrust System: Palomeque Duplex (SE, Spain)

“…To get a model of another location, the procedures presented here can be mimicked, but these must be adapted to the new data of the new location, and researchers must make their own choices of how the model should be. Python has been used by us to produce other geological models in the recent past, but with a different perspective and different kind of data, as is the case of the Llobregat River Delta (Barcelona, Spain) [28][29][30][31].…”

“…Our previous experience with Python libraries for 3D visualization, including geological data handling [28][29][30][31], has been very important to develop new applications for visualizing 3D structural and stratigraphic geological features. These new applications included Jupyter notebooks, describing the methodology, and a Python code operative version, which are downloadable from the GitHub repository (https://github.com/bullejos/ visualizing-an-imbricate-thrust-system accessed on 4 July 2023).…”

A novel approach for surface defectdetection of lithium battery based on improved K-Nearest Neighbor and Euclidean clustering segmentation

“…Considering the roughness and height of surface defect detection, 3-dimensional visual measurement system would be an effective way to solve the problem. Based on the past work on K-neighbors algorithm [7] and Euclidean clustering segmentation [8] , this paper tries to tackle this problem.…”

Study of a high-precision complex 3D geological modelling method based on a fine KNN and kriging coupling algorithm: a case study for Jiangsu, China

“…In complex geological conditions, lithology and strata can be used as important indicators to distinguish the accuracy of the model. By using machine learning algorithms, lithology can be well predicted (Wang et al, 2018;Guo et al, 2019;Pratama, 2019;Jia et al, 2021;Zhu et al, 2021;Li et al, 2022;Erdogan Erten et al, 2022;Chen et al, 2023) and strata (Zhou et al, 2019;Shi and Wang, 2021;Bullejos et al, 2022;Xiong and Liu, 2022;Wang et al, 2023;Wang et al, 2023). Supervised learning for solving classification problems in machine learning is more suitable for the above work.…”

“…Supervised learning for solving classification problems in machine learning is more suitable for the above work. The application of supervised learning algorithms in geological modeling mainly includes the following categories; 1) k-nearest neighbor algorithm (Pratama, 2019;Potratz et al, 2021;Bullejos et al, 2022); 2) bayesian algorithm (Olierook et al, 2021;Zhang et al, 2021); 3) decision tree algorithm (Bacal et al, 2019;Zhou et al, 2020); 4) support vector machine algorithm (Wang et al, 2019;Ghezelbash et al, 2021;Hu et al, 2022); 5) neural network algorithm (Bai and Tahmasebi, 2020;Hillier et al, 2021). The above algorithms have their own advantages, as shown in Table 1 below.…”