Message Boards

GROUPS:

Staff Picks Data Science Curated Data Graphics and Visualization Import and Export Wolfram Language Statistics and Probability Geographic Information System

Pedro Cabral

2020 Brazilian Wild and Criminal Fires: Analysis and Visualization

Pedro Cabral, Intern Consultant at Wolfram

Posted 21 days ago

1495 Views

7 Replies

20 Total Likes

Follow this post

UPDATED: Added the data from September ─ 2020.

brazilian wild and criminal fires

2020 Brazilian Wild Fires and Criminal Fires: Analysis and Visualization on the NASA MODIS Data.

Pedro Gomes Cabral — Intern Consultant at Wolfram Research, Inc. — pcabral@wolfram.com

ABSTRACT: In this article, inspired by Arnoud Buzing's "Mapping Wildfires" and Mads Bahrami's "US Fire Map", I perform some data parsing, analysis and visualization on the data from the “INPE's Fire Database” that uses the NASA MODIS (Moderate Resolution Imaging Spectroradiometer) data to search for wildfires and automatically extract the geographical position, administrative division and the radioactive fire power. Through some parsing functions, the raw CSV dataset can be transformed into a more computable dataset with entities and quantities.

Introduction

Out[]=

Photography of “Illegal loggers, 2020” and “Apui fire, 2020” taken by Bruno Kelly.

The year of 2020 has been a cruel year, with both wildfires and criminal fires to all the six biomes of Brazil, the Atlantic Forest, Amazon, Pampa, Pantanal, Caatinga, and Cerrado. A couple of news articles claim devastating effects in the 2020 wildfires and criminal fires through all biomes, some include: “On 14 days of this month, the Amazon already has more wildfires than in all September of last year.”, “Burning Amazon 20: Burns consume trees and animals in southern Amazonas”, and “Wildfires leave deep marks in the Amazon”.

In this article, I’ll be analysing the complete NASA MODIS Land data from January 1st to August 31th of the year 2020, performing statistical analysis, and geographical visualization of the data.

Data Parsing

I’ve wrote one helper function that automatically parses the INPE’s Fire Database datasets into a more computable form of dataset, with entities and with the Wolfram Language knowledge.

Set the current directory to the notebook directory.

SetDirectory[NotebookDirectory[]]

In[]:=

/home/peter/Documents/WolframLLC/Articles/BrazillianWildfires

Out[]=

This notebook already contains this raw piece of data, so there is no need for importing or downloading.

Iconized March 2020 dataset.

RawMarchData=

;

In[]:=

Definition of the helper function ParseINPEDataset.

ParseINPEDataset`StateNames=

;

In[]:=

ParseINPEDataset[data_]:=Module[{parsed},(*Deleteafewcolumns.*)parsed=data〚All,{1,4,5,6,7,8,9,10,11,12}〛;(*Renameallcolumns.*)parsed〚1〛={"DateTime","State","County","Biome","DaysWithoutRain","RainIndex","FireRisk","GeoPosition","Longitude","FRP"};(*Interpretdatetimecolumn.*)parsed〚2;;,1〛=DateObject[ToExpression[StringTrim[#]]&/@StringSplit[#,{"/",":"," "}]]&/@parsed〚2;;,1〛;(*Changestatenamestoentities.*)parsed〚2;;,2〛=StringTrim[#]&/@parsed〚2;;,2〛;parsed〚2;;,2〛=parsed〚2;;,2〛//.ParseINPEDataset`StateNames;(*Translateandnormalizebiomenamestoenglish.*)parsed〚2;;,4〛=StringTrim[#]&/@parsed〚2;;,4〛;parsed〚2;;,4〛=parsed〚2;;,4〛/.{"Mata Atlantica""AtlanticForest","Amazonia""Amazon"};(*Convert"DaysWithoutRain"todays,replace-999toMissing["NotAvailable"].*)parsed〚2;;,5〛=If[MatchQ[#,-999]||MatchQ[#,"-999"]||MatchQ[#,""],Missing["NotAvailable"],Quantity[#,"Days"]]&/@parsed〚2;;,5〛;(*Convert"RainIndex"tomilimeters,replace-999toMissing["NotAvailable"].*)parsed〚2;;,6〛=If[MatchQ[#,-999]||MatchQ[#,"-999"]||MatchQ[#,""],Missing["NotAvailable"],Quantity[#,"Millimeters"]]&/@parsed〚2;;,6〛;(*Convert"FireRisk"topercentage,replace-999toMissing["NotAvailable"].*)parsed〚2;;,7〛=If[MatchQ[#,-999]||MatchQ[#,"-999"]||MatchQ[#,""],Missing["NotAvailable"],Quantity[100*#,"Percent"]]&/@parsed〚2;;,7〛;(*Join"Latitude"and"Longitude"intoasingle"GeoPosition"column.*)parsed〚2;;,8〛=parsed〚2;;,{8,9}〛;parsed〚2;;,8〛=GeoPosition[#]&/@parsed〚2;;,8〛;(*Convert"FRP"tomegawatts,replace-999toMissing["NotAvailable"].*)parsed〚2;;,10〛=If[MatchQ[#,-999]||MatchQ[#,"-999"]||MatchQ[#,""],Missing["NotAvailable"],Quantity[#,"Megawatts"]]&/@parsed〚2;;,10〛;(*Transformrowsintoanassociation.*)parsed〚2;;〛=AssociationThread[parsed〚1〛,#]&/@parsed〚2;;〛;(*Drop"Longitude"and"County"row.*)parsed=parsed〚2;;,{1,2,4,5,6,7,8,10}〛;(*Returnflawlesslyparseddataset.*)Return[SortBy[parsed,First]]];

In[]:=

For parsing the data, just call ParseINPEDataset with a proper INPE’s Fire Database CSV dataset.

Parse the first 10 elements of the unprocessed fire dataset with the ParseINPEDataset function.

Dataset[ParseINPEDataset[RawMarchData〚1;;11〛]]

In[]:=

DateTime	State	Biome	DaysWithoutRain	RainIndex	FireRisk	GeoPosition	FRP
Sun 1 Mar 2020 15:35:00	Pernambuco, Brazil	AtlanticForest	8days	1.4mm	90. %	8.063°S 35.13°W	10.7MW
Sun 1 Mar 2020 15:35:00	Pernambuco, Brazil	AtlanticForest	9days	0mm	100 %	8.664°S 35.31°W	28.2MW
Sun 1 Mar 2020 15:35:00	Pernambuco, Brazil	AtlanticForest	9days	0mm	100 %	8.593°S 35.18°W	18.3MW
Sun 1 Mar 2020 15:35:00	Pernambuco, Brazil	AtlanticForest	9days	0mm	100 %	8.591°S 35.16°W	56.3MW
Sun 1 Mar 2020 17:10:00	Parana, Brazil	AtlanticForest	3days	1.4mm	50. %	24.28°S 51.49°W	12.4MW
Sun 1 Mar 2020 17:10:00	Parana, Brazil	AtlanticForest	4days	0mm	80. %	26.23°S 52.95°W	11.8MW
Sun 1 Mar 2020 17:10:00	Rio Grande Do Sul, Brazil	AtlanticForest	4days	0mm	—	29.23°S 51.34°W	14.8MW
Sun 1 Mar 2020 17:10:00	Rio Grande Do Sul, Brazil	AtlanticForest	4days	0mm	30. %	29.47°S 51.48°W	16MW
Sun 1 Mar 2020 17:10:00	Rio Grande Do Sul, Brazil	Pampa	9days	0mm	90. %	31.72°S 53.26°W	8MW
Sun 1 Mar 2020 17:10:00	Santa Catarina, Brazil	AtlanticForest	4days	0mm	20. %	29.09°S 49.54°W	5.6MW

Out[]=

Downloading the Datasets

The dataset can be downloaded directly from the Wolfram Cloud. The file consists of a Wolfram Binary Dump, it’s a space and memory efficient way of holding computable data without any effort, the only downside is that you cannot read it as a raw file. This file will be monthly updated until the end of 2020 by me.

Define FireData as a CloudObject.

FireData=CloudObject["BrazilianFireData_2020.mx"]

In[]:=

CloudObject

https://www.wolframcloud.com/obj/pcabral/BrazilianFireData_2020.mx



Out[]=

Information about the FireData CloudObject.

Information[FireData]

In[]:=

Cloud Object

f3bc4dba-e384-47e5-b7dd-a36ef3cd0c66

Path	pcabral/BrazilianFireData_2020.mx
Display Name	BrazilianFireData_2020.mx
Owner Cloud User UUID	02809256-05a7-4298-ac6d-bae97887163a
Owner Cloud User ID	pcabral@wolfram.com
MIME Type
File Type	File
File Byte Count	14206008
File Hash MD5	185975514566130149850085397421757189410
Created	Fri 2 Oct 2020 14:05:10GMT-3.
Last Accessed	Fri 2 Oct 2020 14:05:10GMT-3.
Last Modified	Fri 2 Oct 2020 14:25:48GMT-3.
Permissions	{All{Read},Owner{Read,Write,Execute}}
Active	True

Out[]=

For importing, you can use CloudImport[] or just import locally using Import[].

Retrieve the FireData CloudObject as BrazilianFireData.

BrazilianFireData=CloudImport[FireData];

In[]:=

Import the FireData Dataset as BrazilianFireData.

BrazilianFireData=Import["./BrazilianFireData_2020.mx"];

In[]:=

Dataset Information

The dataset is a list of associations, containing 8 rules. In terms of the Wolfram Language, the dataset is equivalent to a list of associations, containing 8 rules for each list. Here is a description of all columns.

Generate a dataset called ColumnsDescription with the description of all columns.

ColumnsDescription=Dataset[Association["DateTime""Date and time of the fire.","State""The federal unit (administrative division, state) in which the fire happened.","Biome""The biome in which the fire happened.","DaysWithoutRain""Number of days without rain until the fire was reported.","RainIndex""The rain index for the region until the fire was reported, measured in millimeters.","FireRisk""Risk of fire determined by the INPE-NASA MODIS algorithm, measured in percent.","GeoPosition""Geographic position of the fire, containing latitude and longitude.","FRP""Fire radiative power, measured in megawatts."]]

In[]:=

DateTime	Date and time of the fire.
State	The federal unit (administrative division, state) in which the fire happened.
Biome	The biome in which the fire happened.
DaysWithoutRain	Number of days without rain until the fire was reported.
RainIndex	The rain index for the region until the fire was reported, measured in millimeters.
FireRisk	Risk of fire determined by the INPE-NASA MODIS algorithm, measured in percent.
GeoPosition	Geographic position of the fire, containing latitude and longitude.
FRP	Fire radiative power, measured in megawatts.

Out[]=

Get a random sample of the BrazilianFireData dataset.

RandomSample[BrazilianFireData,1]

In[]:=

DateTime

Thu 30 Apr 2020 17:40:00GMT-3.

,State

Mato Grosso, Brazil

,BiomeAmazon,DaysWithoutRain

days

,RainIndex

0.7

,FireRisk

100

,GeoPositionGeoPosition[{-14.588,-59.658}],FRP



Out[]=

Get five random samples of the BrazilianFireData dataset and display as a formatted dataset.

Dataset[RandomSample[BrazilianFireData,5]]

In[]:=

DateTime	State	Biome	DaysWithoutRain	RainIndex	FireRisk	GeoPosition	FRP
Tue 16 Jun 2020 16:55:00	Mato Grosso do Sul, Brazil	AtlanticForest	10days	0mm	100 %	22.09°S 54.28°W	53.8MW
Mon 15 Jun 2020 16:15:00	Maranhao, Brazil	Cerrado	0days	0mm	20. %	4.826°S 43.76°W	12.3MW
Wed 30 Sep 2020 17:30:00	Mato Grosso, Brazil	Pantanal	3days	0mm	100 %	17.09°S 58.2°W	47.9MW
Fri 4 Sep 2020 16:55:00	Para, Brazil	Amazon	11days	0mm	100 %	7.743°S 50.88°W	20.3MW
Wed 16 Sep 2020 17:20:00	Mato Grosso, Brazil	Amazon	114days	0mm	100 %	12.88°S 53.42°W	28.2MW

Out[]=

Dataset Segmentation

For the easiness of manipulation of the dataset, it’s possible to segment the data by month and date.

Segment the BrazilianFireData dataset into lists by month.

BrazilianFireDataMonthly=GatherBy[BrazilianFireData,DateValue[First[#],"Month"]&];

In[]:=

Segment the BrazilianFireData dataset into lists by day.

BrazilianFireDataDaily=GatherBy[BrazilianFireData,{DateValue[First[#],"Day"],DateValue[First[#],"Month"]}&];

In[]:=

Statistical Analysis and Visualization

In this section, many statistical functions and different plotting methods will be applied on the dataset. For the easiness of visualization and interaction of this notebook, every interactive plot is saved, so it’s not necessary to run them again.

Let’s visualize the trend of the amount of fires per day, and the mean fire radiative power per day.

Plot a list line graphic of the amount of fires reported per day.

ListLinePlotLength[#]&/@BrazilianFireDataDaily,



In[]:=

Out[]=

Plot a list line graphic of the mean fire radiative power per day.

ListLinePlotMean[#]&/@DeleteMissing[BrazilianFireDataDaily〚All,All,"FRP"〛],



In[]:=

Out[]=

Plot a histogram of the amount of days without rain.

ListAnimateTableHistogramCounts[BrazilianFireDataMonthly〚n,All,"DaysWithoutRain"〛],5,

,{n,1,Length[BrazilianFireDataMonthly]},DeployedTrue

In[]:=

Out[]=

Plot a bar chart of the fires and their biomes.

ListAnimateTableBarChartCounts[BrazilianFireDataMonthly〚n,All,"Biome"〛],

,{n,1,Length[BrazilianFireDataMonthly]},DeployedTrue

In[]:=

Out[]=

Data Querying and Comparison

Some interesting questions can be computationally extracted from the datasets.

Q: What was the most affected biome by the fires?

Dataset of the count for every biome from the reverse sorted dataset.

Dataset[Counts[BrazilianFireData〚All,"Biome"〛]//ReverseSort]

In[]:=

Amazon	76030
Cerrado	46007
Pantanal	18259
AtlanticForest	13948
Caatinga	4680
Pampa