Publications by Ivan Lizarazo

Landsat image exploration with terra

27.02.2021

1. Introduction In this notebook I illustrate how to find, download and explore satellite remote sensing data with R. I also show how to create color composites and explore spectral profiles. A lot of the code that follows is based on the notebook written by Aniruddha Ghosh and Robert J. Hijmans which you may find here. However, I expand here bot...

10661 sym R (14814 sym/81 pcs) 15 img

A tutorial on pixel-based land cover classification using random forests

06.04.2021

1. Introduction This notebook explores statistical learning techniques to conduct land cover classification from multispectral imagery. Novel machine learning techniques promise high predictive performance as they seems able to better represent nonlinear relationships or higher-order interactions between predictors than traditional linear models ...

8272 sym R (17156 sym/109 pcs) 5 img

Accuracy assessment of land cover classification

29.03.2021

1. Introduction This notebook illustrates how to assess thematic accuracy of land cover classification. It aims at helping Percepcion Remota students at UNAL to get started with remote sensing image analysis in R. I will use a classified image obtained in a previous notebook. The classification covers the area known as Montes de Maria, in the Co...

3038 sym R (6628 sym/49 pcs) 4 img

My fifth notebook: elevation data

23.03.2021

1. Why this notebook? This is an R Notebook created using R Studio on an old laptop. It illustrates several functionalities to obtain, process and visualize digital elevation models in R. It aims to help Geomatica Basica students at Universidad Nacional to get started with R geospatial capabilities. A few tips for writing your own notebook: Writ...

7678 sym R (12668 sym/52 pcs) 13 img

CART-based land cover classification

22.03.2021

1. Introduction This notebook illustrates how to conduct land cover classification from multispectral imagery using the terra library. It aims at helping Percepcion Remota students at UNAL to get started with remote sensing image analysis in R. I will use a spatial and spectral subset of a Landsat 8 scene collected in 2013. The subset is a seven-...

9527 sym R (15627 sym/93 pcs) 13 img

Evaluaciones Agropecuarias Municipales

09.03.2021

1. Introduction This is the third notebook which Geomatica Basica students have to write to get started with R & RStudio. It aims at learning how to use the dplyr package for data “editing”. Editing refers to choosing a subset of the variables and/or observations in a dataset, as well as filtering (selecting observations based on their variab...

5568 sym R (4698 sym/26 pcs) 4 img

Satellite image contrast enhancement with R

02.03.2021

1. Introduction In this notebook I explore functionalities provided by the imager package developed by Simon Barthelmé as well as the imagerExtra package developed by Shota Ochi. I applied here these packages’ functions to improve remote sensing image visualization. In a earlier notebook, we saw that the terra package provide a few functions t...

3032 sym R (3921 sym/30 pcs) 7 img

Image statistics of a Landsat 8 image

06.03.2021

1. Introduction This notebook illustrates how to calculate uniband and multiband image statistics using the raster library. I will use a spatial and spectral subset of a Landsat 8 scene collected in 2013. The subset is a seven-band image which covers the area known as Montes de Maria, in the Colombian Caribbean region. I explained in a previous n...

5193 sym R (7541 sym/46 pcs) 15 img

Getting climate data from R

15.04.2021

1. Why this notebook? This is an R Notebook written to illustrate how to obtain, process and visualize climate data in R. It aims to help Geomatica Basica students at Universidad Nacional to get started with R geospatial capabilities. Note that, here, I focus on explaining the technical procedure rather than on interpreting or analyzing the outpu...

3881 sym R (9053 sym/45 pcs) 2 img

Healthcare accessibility and population

27.05.2021

The Accessibility to Healthcare 2019 dataset enumerates land-based travel time (in minutes) to the nearest hospital or clinic for all areas between 85 degrees north and 60 degrees south for a nominal year 2019. It also includes “walking-only” travel time, using non-motorized means of transportation only. Major data collection efforts underway...

2326 sym R (4158 sym/10 pcs)