Next Article in Journal
An Experimental Method for Generating Shear-Free Turbulence Using Horizontal Oscillating Grids
Previous Article in Journal
Effect of Heavy Metal Ions on Steroid Estrogen Removal and Transport in SAT Using DLLME as a Detection Method of Steroid Estrogen
Open AccessArticle

Visualization Framework for High-Dimensional Spatio-Temporal Hydrological Gridded Datasets using Machine-Learning Techniques

Deep Earth Imaging—Future Science Platform (DEI-FSP), Commonwealth Scientific and Industrial Research Organization (CSIRO), Melbourne, Australia
Water 2020, 12(2), 590; https://doi.org/10.3390/w12020590
Received: 18 December 2019 / Revised: 14 February 2020 / Accepted: 19 February 2020 / Published: 21 February 2020
(This article belongs to the Section Hydrology and Hydrogeology)
Numerical modelling increasingly generates massive, high-dimensional spatio-temporal datasets. Exploring such datasets relies on effective visualization. This study presents a generic workflow to (i) project high-dimensional spatio-temporal data on a two-dimensional (2D) plane accurately (ii) compare dimensionality reduction techniques (DRTs) in terms of resolution and computational efficiency (iii) represent 2D projection spatially using a 2D perceptually uniform background color map. Machine learning (ML) based DRTs for data visualization i.e., principal component analysis (PCA), generative topographic mapping (GTM), t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP) are compared in terms of accuracy, resolution and computational efficiency to handle massive datasets. The accuracy of visualization is evaluated using a quality metric based on a co-ranking framework. The workflow is applied to an output of an Australian Water Resource Assessment (AWRA) model for Tasmania, Australia. The dataset consists of daily time series of nine components of the water balance at a 5 km grid cell resolution for the year 2017. The case study shows that PCA allows rapid visualization of global data structures, while t-SNE and UMAP allows more accurate representation of local trends. Furthermore, UMAP is computationally more efficient than t-SNE and least affected by the outliers compared to GTM. View Full-Text
Keywords: machine learning; spatio-temporal gridded datasets; dimensionality reduction; color maps; spatial visualization; quality assessment. machine learning; spatio-temporal gridded datasets; dimensionality reduction; color maps; spatial visualization; quality assessment.
Show Figures

Figure 1

MDPI and ACS Style

Mazher, A. Visualization Framework for High-Dimensional Spatio-Temporal Hydrological Gridded Datasets using Machine-Learning Techniques. Water 2020, 12, 590.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop