For those of you at or affiliated with SNAP, you are probably aware of our ALFRESCO software for modeling past, present, and projected wildfire behavior in Alaska as well as some of western Canada in the context of climate change. When calibrating the model, it can be necessary to run the model many times, and this can be a bit tedious. After ALFRESCO produces gigabytes of output, that data must be post-processed, analyzed, and interpreted, which is where I use R further. This too can be a bit tedious to do over and over from the Linux command line, nor is that approach accessible to everyone.
I put together a proof of concept web application using R and the shiny package which allows a user to launch ALFRESCO simulations conveniently from their browser, and post-processing of the simulation results in R with additional scripts (in non-interactive mode of course) is piggybacked on top of this so everything happens sequentially once the entire process is launched from the browser.
Recently I came across this blog post on making heatmaps in R for the US states which are more heat than map. The idea is simple, the plot basic, the purpose straightforward, utility apparent. The statebins package is convenient, but I felt like making one using base graphics instead of ggplot2, which statebins relies on, among other packages.
I was recently searching for a web-based collaborative coding option for R. There are plenty of free collaborative coding environments available online for a number of popular languages, but at first I wasn’t finding any which offered syntax highlighting for R. In fact, what I did seem to find was other useRs like me groaning about how silly it was that R is still excluded from them all. It’s not like a number of other coding environments don’t already support syntax highlighting for R, like text editors (Notepad++, SublimeText, etc.). So why not here? Well, I found one! Maybe there are more. But after finding one, I simply stopped searching. Squad.
Continuing from part three where I plotted lightning strikes over Alaska in June and July of 2012 color coded by strike multiplicity and strike strength, in this post I begin the transition from descriptive statistics to inferential statistics. This is still exploratory data analysis, however, in the sense that I know nothing arrived at here will be conclusive. Statistical modeling in general, including the spatial statistics performed on the lightning data here using variogram modeling and kriging, is a process that gradually transitions from exploratory to confirmatory in nature.
Here are some screenshots of plots comparing CMIP3 and CMIP5 climate models. The plots come from the web application I have been developing in R for comparing and evaluating SNAP’s downscaled CMIP3 and CMIP5 GCM data. The app is still under development and not yet released. The plots I’ve shared here focus exclusively on CMIP5 RCP 6.0. CMIP3 can be assumed absent unless specifically mentioned in a plot caption. When present in comparison to CMIP5, I used the SRES A1B scenario. The plots make use of the five models SNAP has previously evaluated as being most sensible for our purposes in Alaska and the Arctic. Continue reading →
A while back I posted some screenshots of an RShiny web application I’d been working on. It demonstrates integration of the plot3D and rgl packages into a Shiny app for 2D and 3D plotting. The rgl functionality is assisted by the shinyRGL package. The app is still under development but a number of changes and code improvements have been made.
Continuing from part two where I used kernel density estimation to interpolate and map the density of lightning strikes over Alaska in June and July of 2012, next we take our first look at some data associated with the observed lightning strike locations. Specifically, strike multiplicity and strike strength.