A wildfire or wildland fire is a fire in an area of combustible vegetation that occurs in the countryside or rural area. Wildfires can be characterized in terms of the cause of ignition, their physical properties, the combustible material present, and the effect of weather on the fire. Wildfires can cause damage to property and human life, but they have many beneficial effects on native vegetation, animals, and ecosystems that have evolved with fire. [1].

It’s costly to control and suppress wildfire. In California, the U.S. Forest Service spends about $200 million per year to suppress 98% of wildfires and up to $1 billion to suppress the other 2% of fires that escape initial attack and become large. [2].

In order to have a overall concept of the wildfire in the US, we plot the location, size and season of the wildfires occured in the U.S from 1992 to 2015 on the map below. The data we use here originally comes from Forest Service Research Data Archive.

Here are some interesting facts we can observe from the map:
  1. Most of middle to large scale wildfires occur in west and south of conterminous US and Alaska.
  2. The location and season of the wildfire is highly related. For example, you can most of the wildfire happened during winter time is in south California; Fires in Rocky Mountains happen during the autumn, and fires in Alaska mostly happened during summer.
  3. The occurrences of larger scale wildfire is quite rare compared to that of small scale wildfire. The map is set in default to display the fires over 5000 acres. However, you play with the filter and display fires with smaller scale, you will find much denser points on the map.
  4. The data from some states might be missing or incorrectly recorded in the dataset because when you show all the fires in the map, you will find that the density of occurrences are not continuous when it crosses the state borders.

After having an overall concept of the wildfires in US, we will dive into more specific question about the wildfire in following sections.

How many wildfires are caused by X ?

Wildfires have many different causes, both human and natural. From the stream graph below, you can get a sense of the volume of the number of wildfires that happen due to a certain cause. If we don't consider miscellaneous or undocumented causes, lightning is one of the primary natural causes of wildfires in the United States. Among human causes, arson and debris burning make up a good chunk of occurences compared to other human induced wildfires.

It is worth noting the sudden increases in the wildfire occurences for certain causes. For example, equipment use caused a relatively consistent number of fires up until 2013, with roughly 1000-2000 occurences a year. However, in 2014, the number of reported wildfires doubled, reaching 4472 occurences. We suspect that this is due to a classification or reporting issue. Interestingly enough, the number of miscellaneous caused and undefined caused wildfires decreased.

To an extent, this graph is helpful in visualizing the volume of wildfire causes throughout the years and how certain causes relate to one another.

How is the cause, size, and location of a wildfire related (if at all)?

From the first visualization, we are able to get a general sense of where wildfires are occuring and how big they are. With the second visualization, we are able to get an aggregated view of which cause induces the most wildfires. Let's use a Sankey chart to visualize relationships between cause, size, and location. The data used for this graph is of all the years combined.

There are 6 fire size classes denoted by the letters "A" through "G", with "A" representing the smallest fire sizes (< 0.25 acres), and "G" representing the largest fire sizes (5000+ acres). From this chart, you can see that the majority of wildfires end up being small, in classes "A", "B", or "C". The remaining fire sizes are pretty rare - interestingly enough, big fires (like class "F" and "G") are almost always human induced. Big accidents like powerline failures, or malicious intent like arson tend to be the culprits.

There are also a significant amount of fires that were not able to be defined - these fires mostly ended up in the small ("A" through "C") size classes. This sounds reasonable, as defining the cause of a fire can be somewhat arbitrary when the main focus is to put the fire out.

From this chart, it is not easy to see patterns with regard to how the size of a fire relates to the location of the occurence. However, it is interesting to see that many small fires occur in Georgia, California, and Texas - all of which are generally dry and hot.


Overall, visualizing these three charts gives us a more intuitive sense of wildfires in general. From this story, we want to bring awareness to the issue of wildfires and hope to further the education of these types of disasters. To continue the story, we have built a predictive model, which you can interact with here.