Technical Solutions – Spatial Points

Category: Technical Solutions

Deep Learning in ArcGIS Pro using your GPU

On April 20, 2022

ArcGIS Pro includes built in tools that allow end-to-end deep learning, all within the Arc interface – from training sample labelling, through model training and final image classification / object detection. This removes the need for coding and installing the correct versions of the required libraries for machine / deep learning in Python.

However, training deep learning models is an extremely processing-heavy task that requires the use of your GPU to even be slightly feasible in terms of processing time.

Although, Deep Learning in ArcGIS Pro is not possible straight out of the box. This post will walk through how to get everything set up, based on my experience with ArcGIS Pro 2.8/2.9 and the graphics cards listed below. Processes / software versions are sure to change in the future, so I will try and keep the instructions as general as possible.

EarthExplorer – AppEEARS platform

By Amelie Jeanneau

On October 10, 2019

In Satellite Data, Technical Solutions

I recently came across the AρρEEARS platform when looking for a quick bulk-download of MODIS satellite imagery. AρρEEARS or Application for Extracting and Exploring Analysis Ready Samples is a web platform hosting a wide range of geospatial datasets (e.g. MODIS, Landsat, ASTER, etc.). To access the website, you just need your USGS login creadentials. A full list of the datasets available can be found here.

The first thing I liked about this platform is the fact that you can pre-process the data before placing the order (e.g. clip to a region of interest (ROI) with a custom shapefile, re-project, pre-select particular bands, etc.).

‘esquisse’ Package & ggplot2 Builder

By Claire Fisk

On June 21, 2019

In R, Technical Solutions

A few nights ago while scrolling twitter I discovered an R package called ‘esquisse’. This package was designed to help users explore and extract data quickly and a brilliant feature of this package is the ‘ggplot2 builder’ add-in.

This add-in opens a GUI interface within RStudio that allows you to interactively explore and visualise your data using the ggplot2 package. Provide it with a data frame and you can effortlessly create bar graphs, scatter plots, histograms, boxplots and much more.

Free R Tutorials for Working with Raster Data

By Boone Law

On August 23, 2018

In R, Technical Solutions

Hey Spatial Information Group folks! I know many of us are learning how to code and generate spatial raster statistics in R Studio. It is a steep learning curve, but alot of fun once you get through the basics. I have always found that I learn best by working through an example tutorial before applying it to real world data, so in that spirit, here’s my “hot tip” for learning R:

Check out the free tutorial and lessons provided by the National Ecological Observatory Network (NEON). The NEON lessons look very well written and presented…and I’m sure most in our group can relate to the example datasets provided.

https://www.neonscience.org/resources/series/introduction-working-raster-data-r

Making python (anaconda) 64 bit and Arcpy 64 bit (ArcGIS python process) play nicely together

By Ken_Clarke

On May 19, 2017

In ArcGIS, Python, Technical Solutions

Calling ArcGIS processes from python can be a wonderful time-saver; allowing the user to code a process to loop through hundreds of data-sets autonomously.

Most ArcGIS processes are only 32 bit, so can slow down significantly when working on large datasets; data has to be shuffled in and out of memory (RAM). However, newer ArcGIS 64 bit processes allow more memory to be addressed, potentially resulting in significant reductions in processing time.

We are the Spatial Sciences Group and Unmanned Research Aircraft Facility at the University of Adelaide

We are a mix of Academics, Post-Docs and PhD's who specialise in a range of applications of GIS and Remote Sensing. We frequently solve small or large image processing, spatial, or related coding problems. However, much of this knowledge remains inside our individual heads, or, it quickly slides out...

This site was created to store the collective solutions of our group. Hopefully they'll be more useful gathered together in a searchable form.

Spatial Points

A collection of notes on remote sensing, spatial science, and solutions to problems encountered