Forest Fires in Brazil 2019 - 2020

Numbers and locations of forest fires and heat spots detected by screening satellite images in Brazil

FAQS

  1. In what context are INPE's fires data useful?

    Monitoring of fires and forest fires in satellite images is particularly useful for remote regions without intensive means and monitoring sites, a condition that represents the general situation in the country. For an area with observation towers continuously manned and maintaining direct communication with brigades fire fighting equipment, satellite data is of marginal interest.

    The detection of vegetation burning spots in the images uses the same fire identification method, in all regions, every day and for years in a row, which allows temporal and spatial analyzes of the occurrence of the fire that would otherwise be impossible, given precariousness, discontinuity and difference in methods in local information sources. In particular, the data from the "reference satellite" allows comparison between any country on the planet.

  2. What products does this INPE fire / fire system offer?

    There are hundreds of products generated and distributed daily, such as: geographic coordinates of the outbreaks, e-mail alerts of occurrences in areas of special interest, meteorological fire risk, smoke concentration estimates, mapping of burnt areas, etc. . Explore the INPE Queimadas Program Portal and see the list of the most recommended on the general presentation page.

  3. Do the products from Queimadas do INPE have any cost?

    No, all data and products are released on the internet by INPE at no cost to the user, about three hours after their generation; it is clear that for the user there is the cost of the internet provider or the use of the telephone line.

  4. Can INPE work with those who burn?

    No. INPE has no powers to inspect, control and combat the use of fire in the country, nor to punish violators. Within its attributions, INPE, through its Queimadas Program, seeks to generate the largest possible number of data related to the use of fire in vegetation so that the government and society benefit from the information generated. See our links page for more information.

  5. What does INPE do with fire data?

    The data generated is distributed in two ways: for the general public, all data and products are available for free access on the Internet about three hours after their generation; for public agents with special operational needs, distribution is immediate to their generation.

  6. Which satellites are used and where are the images received and processed?

    All nine satellites that have optical sensors operating in the thermal-average range of 4um and that INPE can receive are used. (Thermal Infrared Imaging) Currently (September / 2019), images from the polar satellites, the AVHRR / 3 of the NOAA-18, NOAA-19 and METOP are processed operationally in the Imaging Division - DGI and in the Satellite and Environmental Systems Division - DSA -B, the MODIS of NASA TERRA and AQUA and the VIIRS of NPP-Suomi and NOAA-20 and, the images of the geostationary satellites, GOES-16 and MSG-3.

    Each polar orbit satellite produces at least two sets of images per day, and the geostationary generates four images per hour, with a total of INPE automatically processing over 200 images per day specifically to detect vegetation fires. It is also expected to include the reception of images from the Chinese Fenyun polar satellites. The receptions are made at the stations of Cachoeira Paulista, SP (near the border with RJ) and Cuiabá, MT.

Wild fires detected in 2018, numbers divided per state.

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 1806600 entries, 2018-03-10 20:05:35 to 2018-03-11 21:05:40
Data columns (total 11 columns):
 #   Column        Dtype  
---  ------        -----  
 0   satelite      object 
 1   pais          object 
 2   estado        object 
 3   municipio     object 
 4   bioma         object 
 5   diasemchuva   int64  
 6   precipitacao  float64
 7   riscofogo     float64
 8   latitude      float64
 9   longitude     float64
 10  frp           float64
dtypes: float64(5), int64(1), object(5)
memory usage: 165.4+ MB
satelite pais estado municipio bioma diasemchuva precipitacao riscofogo latitude longitude frp
datahora
2018-03-10 20:05:35 GOES-16 Brasil RORAIMA CAROEBE Amazonia 0 0.00 0.06 0.81 -59.72 NaN
2018-03-20 13:35:39 GOES-16 Brasil RORAIMA CARACARAI Amazonia 0 0.00 0.42 1.55 -61.48 NaN
2018-03-24 14:20:36 GOES-16 Brasil RORAIMA CARACARAI Amazonia 0 0.33 0.47 1.15 -60.78 NaN
2018-03-01 16:05:53 GOES-16 Brasil RORAIMA NORMANDIA Amazonia 0 0.00 0.63 3.65 -60.37 NaN
2018-03-22 22:05:47 GOES-16 Brasil RORAIMA MUCAJAI Amazonia 0 0.00 0.62 2.63 -60.99 NaN
latitude longitude
datahora
2018-03-10 20:05:35 0.81000 -59.72000
2018-03-20 13:35:39 1.55000 -61.48000
2018-03-24 14:20:36 1.15000 -60.78000
2018-03-01 16:05:53 3.65000 -60.37000
2018-03-22 22:05:47 2.63000 -60.99000
... ... ...
2018-03-31 17:12:00 -15.63578 -45.77114
2018-03-09 04:48:00 3.19729 -60.01252
2018-02-21 20:20:35 0.95000 -60.08000
2018-03-12 05:30:00 2.61829 -60.60953
2018-03-11 21:05:40 1.75000 -60.38000

1806600 rows × 2 columns

This plot gives you an idea of the incredible variation in the amount of fires over different places.

bioma ... riscofogo
estado ACRE ... TOCANTINS All
municipio ACRELANDIA ASSIS BRASIL BRASILEIA BUJARI CAPIXABA CRUZEIRO DO SUL EPITACIOLANDIA FEIJO JORDAO MANCIO LIMA ... TAGUATINGA TAIPAS DO TOCANTINS TALISMA TOCANTINIA TOCANTINOPOLIS TUPIRAMA TUPIRATINS WANDERLANDIA XAMBIOA
satelite
AQUA_M-M 1.0 NaN 1.0 1.0 1.0 2.0 NaN NaN NaN 2.0 ... 4.0 6.0 4.0 5.0 2.0 NaN 1.0 3.0 1.0 11346.0
AQUA_M-T 160.0 190.0 505.0 218.0 204.0 463.0 149.0 839.0 142.0 183.0 ... 37.0 40.0 12.0 121.0 35.0 28.0 22.0 38.0 11.0 126181.0
GOES-13 NaN NaN NaN NaN NaN 1.0 NaN 1.0 NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
GOES-16 215.0 174.0 389.0 299.0 270.0 552.0 181.0 465.0 78.0 239.0 ... 103.0 125.0 185.0 201.0 135.0 77.0 79.0 126.0 11.0 NaN
METOP-B 4.0 NaN NaN 1.0 NaN 9.0 NaN 2.0 NaN 2.0 ... 17.0 24.0 29.0 26.0 10.0 7.0 8.0 5.0 1.0 NaN
MSG-03 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN 2.0 NaN NaN
NOAA-15 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... 6.0 8.0 21.0 9.0 NaN NaN 9.0 1.0 NaN NaN
NOAA-15D NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
NOAA-18 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... 10.0 2.0 34.0 5.0 6.0 4.0 28.0 11.0 2.0 NaN
NOAA-18D 3.0 2.0 5.0 6.0 7.0 3.0 12.0 5.0 1.0 1.0 ... NaN 4.0 NaN NaN NaN 1.0 NaN 1.0 NaN NaN
NOAA-19 53.0 16.0 41.0 52.0 41.0 40.0 34.0 79.0 7.0 16.0 ... 25.0 68.0 26.0 71.0 29.0 30.0 30.0 66.0 10.0 NaN
NOAA-19D NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... 5.0 6.0 3.0 4.0 7.0 NaN NaN NaN NaN NaN
NPP-375 710.0 659.0 1809.0 910.0 832.0 1538.0 717.0 3907.0 571.0 658.0 ... 352.0 598.0 160.0 852.0 318.0 145.0 210.0 321.0 89.0 812293.0
TERRA_M-M 7.0 NaN 6.0 8.0 7.0 7.0 3.0 6.0 NaN 2.0 ... 11.0 14.0 21.0 14.0 6.0 5.0 3.0 14.0 1.0 28211.0
TERRA_M-T 29.0 2.0 19.0 27.0 21.0 20.0 18.0 59.0 1.0 7.0 ... 17.0 44.0 9.0 82.0 11.0 19.0 21.0 22.0 5.0 54777.0
All 904.0 851.0 2336.0 1164.0 1065.0 2010.0 886.0 4809.0 714.0 838.0 ... 418.0 678.0 205.0 1070.0 369.0 196.0 250.0 392.0 101.0 1032808.0

16 rows × 43144 columns

The most prolific satellites are: AQUA_M-T, GOES-16, NOAA-19, NPP-375, TERRA_M-M, TERRA_M-T.

list
satelite pais estado municipio bioma diasemchuva precipitacao riscofogo latitude longitude frp
datahora
2018-03-10 20:05:35 GOES-16 Brasil RORAIMA CAROEBE Amazonia 0 0.00 0.06 0.81000 -59.72000 NaN
2018-03-20 13:35:39 GOES-16 Brasil RORAIMA CARACARAI Amazonia 0 0.00 0.42 1.55000 -61.48000 NaN
2018-03-24 14:20:36 GOES-16 Brasil RORAIMA CARACARAI Amazonia 0 0.33 0.47 1.15000 -60.78000 NaN
2018-03-01 16:05:53 GOES-16 Brasil RORAIMA NORMANDIA Amazonia 0 0.00 0.63 3.65000 -60.37000 NaN
2018-03-22 22:05:47 GOES-16 Brasil RORAIMA MUCAJAI Amazonia 0 0.00 0.62 2.63000 -60.99000 NaN
... ... ... ... ... ... ... ... ... ... ... ...
2018-03-31 17:12:00 NPP-375 Brasil MINAS GERAIS ARINOS Cerrado 0 0.00 0.51 -15.63578 -45.77114 NaN
2018-03-09 04:48:00 NPP-375 Brasil RORAIMA BONFIM Amazonia 0 0.00 0.34 3.19729 -60.01252 NaN
2018-02-21 20:20:35 GOES-16 Brasil RORAIMA SAO LUIZ Amazonia 0 0.00 0.67 0.95000 -60.08000 NaN
2018-03-12 05:30:00 NPP-375 Brasil RORAIMA CANTA Amazonia 0 0.00 0.24 2.61829 -60.60953 NaN
2018-03-11 21:05:40 GOES-16 Brasil RORAIMA CANTA Amazonia 0 0.00 0.28 1.75000 -60.38000 NaN

1698578 rows × 11 columns

count2018 =FocosState2018.groupby("municipio").count()

satelite pais estado bioma diasemchuva precipitacao riscofogo latitude longitude frp
municipio
ABADIA DE GOIAS 30 30 30 30 30 30 27 30 30 27
ABADIA DOS DOURADOS 45 45 45 45 45 45 45 45 45 37
ABADIANIA 56 56 56 56 56 56 53 56 56 44
ABAETE 62 62 62 62 62 62 61 62 62 60
ABAETETUBA 525 525 525 525 525 525 391 525 525 452
... ... ... ... ... ... ... ... ... ... ...
XIQUE-XIQUE 610 610 610 610 610 610 602 610 610 440
ZABELE 1 1 1 1 1 1 1 1 1 1
ZACARIAS 52 52 52 52 52 52 52 52 52 36
ZE DOCA 419 419 419 419 419 419 419 419 419 169
ZORTEA 13 13 13 13 13 13 13 13 13 13

5125 rows × 10 columns

pais estado bioma diasemchuva precipitacao riscofogo latitude longitude frp
satelite municipio
AQUA_M-T ABADIA DE GOIAS 5 5 5 5 5 5 5 5 5
ABADIA DOS DOURADOS 3 3 3 3 3 3 3 3 3
ABADIANIA 5 5 5 5 5 5 5 5 5
ABAETE 6 6 6 6 6 6 6 6 6
ABAETETUBA 75 75 75 75 75 41 75 75 75
... ... ... ... ... ... ... ... ... ... ...
TERRA_M-T XINGUARA 20 20 20 20 20 13 20 20 20
XIQUE-XIQUE 29 29 29 29 29 29 29 29 29
ZACARIAS 1 1 1 1 1 1 1 1 1
ZE DOCA 6 6 6 6 6 6 6 6 6
ZORTEA 1 1 1 1 1 1 1 1 1

19708 rows × 9 columns

We select here only detections done by the NPP-375 algoritme

satelite pais estado municipio bioma diasemchuva precipitacao riscofogo latitude longitude frp
datahora
2018-02-01 17:06:00 NPP-375 Brasil RORAIMA UIRAMUTA Amazonia 0 0.00 0.35 4.35564 -60.20242 NaN
2018-03-12 05:30:00 NPP-375 Brasil RORAIMA CANTA Amazonia 0 0.00 0.41 2.18465 -60.81395 NaN
2018-03-24 17:36:00 NPP-375 Brasil SANTA CATARINA SANTA CECILIA Mata Atlantica 0 27.85 0.00 -27.06369 -50.48926 NaN
2018-03-13 05:12:00 NPP-375 Brasil RORAIMA CARACARAI Amazonia 0 0.00 0.34 1.71623 -60.99483 NaN
2018-02-27 17:18:00 NPP-375 Brasil RORAIMA CARACARAI Amazonia 0 1.15 0.85 1.96740 -60.78246 NaN
... ... ... ... ... ... ... ... ... ... ... ...
2018-03-19 15:54:00 NPP-375 Brasil MINAS GERAIS ALMENARA Mata Atlantica 0 0.00 0.13 -15.96370 -40.59505 NaN
2018-02-18 04:06:00 NPP-375 Brasil BAHIA RIACHAO DAS NEVES Cerrado 0 0.55 0.23 -11.49848 -44.87274 NaN
2018-03-31 17:12:00 NPP-375 Brasil MINAS GERAIS ARINOS Cerrado 0 0.00 0.51 -15.63578 -45.77114 NaN
2018-03-09 04:48:00 NPP-375 Brasil RORAIMA BONFIM Amazonia 0 0.00 0.34 3.19729 -60.01252 NaN
2018-03-12 05:30:00 NPP-375 Brasil RORAIMA CANTA Amazonia 0 0.00 0.24 2.61829 -60.60953 NaN

894841 rows × 11 columns

plt.figure( figsize= (16, 6)) sns.violinplot(x="riscofogo", y="frp", data= COUNT2018, markersize=2);# scatter #.satelitex="estado", y="satelite", data= count2018

is there a connection between riscofogo at day-1 and frp at day?

Number of heatspots detected by satellites in 2018 (daily)

satelite
datahora
2018-01-01 353
2018-01-02 2025
2018-01-03 1592
2018-01-04 1514
2018-01-05 1386
... ...
2018-12-27 3992
2018-12-28 5348
2018-12-29 2168
2018-12-30 1577
2018-12-31 1072

365 rows × 1 columns

FocosState2018LL_gdf = geopandas.read_file(FocosState2018LL) #, layer='countries'

latitude longitude geometry
datahora
2018-03-10 20:05:35 0.81 -59.72 POINT (-59.72000 0.81000)
2018-03-20 13:35:39 1.55 -61.48 POINT (-61.48000 1.55000)
2018-03-24 14:20:36 1.15 -60.78 POINT (-60.78000 1.15000)
2018-03-01 16:05:53 3.65 -60.37 POINT (-60.37000 3.65000)
2018-03-22 22:05:47 2.63 -60.99 POINT (-60.99000 2.63000)
UsageError: %%capture is a cell magic, but the cell body is empty.

Kde plot Latitude vs Longitude 2018

<seaborn.axisgrid.JointGrid at 0x2529a5e1790>

Total number of wild fires in the year 2019 based on satellite imagery.

Valor Porcentagem do Total de Focos
Campo
AQUA_M-T 197632 100.00%

Total number of wild fires in the year 2019 by biome.

Valor Porcentagem do Total de Focos
Campo
Amazônia 89176 45.12%
Cerrado 63874 32.32%
Mata Atlântica 18177 9.20%
Caatinga 14960 7.57%
Pantanal 10025 5.07%
Pampa 1420 0.72%
197632
<class 'pandas.core.frame.DataFrame'>
Int64Index: 27 entries, 11 to 3
Data columns (total 4 columns):
 #   Column                         Non-Null Count  Dtype 
---  ------                         --------------  ----- 
 0   Campo                          27 non-null     object
 1   Valor                          27 non-null     int64 
 2   Porcentagem do Total de Focos  27 non-null     object
 3   State                          27 non-null     object
dtypes: int64(1), object(3)
memory usage: 1.1+ KB

Total number of wild fires in the year 2019 by state.

Campo Valor Porcentagem do Total de Focos State
11 ACRE 6802 3.44% Acre
24 ALAGOAS 232 0.12% Alagoas
18 AMAPÁ 1277 0.65% Amapá
4 AMAZONAS 12676 6.41% Amazonas
9 BAHIA 7371 3.73% Bahia
13 CEARÁ 4304 2.18% Ceará
25 DISTRITO FEDERAL 213 0.11% Distrito Federal
23 ESPÍRITO SANTO 622 0.31% Espírito Santo
10 GOIÁS 7160 3.62% Goiás
2 MARANHÃO 18521 9.37% Maranhão
0 MATO GROSSO 31169 15.77% Mato Grosso
5 MATO GROSSO DO SUL 11653 5.90% Mato Grosso do Sul
8 MINAS GERAIS 9999 5.06% Minas Gerais
14 PARANÁ 3314 1.68% Paraná
19 PARAÍBA 1184 0.60% Paraíba
1 PARÁ 30165 15.26% Pará
20 PERNAMBUCO 840 0.43% Pernambuco
7 PIAUÍ 10894 5.51% Piauí
22 RIO DE JANEIRO 712 0.36% Rio de Janeiro
21 RIO GRANDE DO NORTE 730 0.37% Rio Grande do Norte
15 RIO GRANDE DO SUL 3196 1.62% Rio Grande do Sul
6 RONDÔNIA 11230 5.68% Rondônia
12 RORAIMA 4784 2.42% Roraima
17 SANTA CATARINA 1804 0.91% Santa Catarina
26 SERGIPE 81 0.04% Sergipe
16 SÃO PAULO 3074 1.56% São Paulo
3 TOCANTINS 13625 6.89% Tocantins
197632
197632
Campo Valor Porcentagem do Total de Focos
State
Acre ACRE 6802 3.44%
Alagoas ALAGOAS 232 0.12%
Amapá AMAPÁ 1277 0.65%
Amazonas AMAZONAS 12676 6.41%
Bahia BAHIA 7371 3.73%
Ceará CEARÁ 4304 2.18%
Distrito Federal DISTRITO FEDERAL 213 0.11%
Espírito Santo ESPÍRITO SANTO 622 0.31%
Goiás GOIÁS 7160 3.62%
Maranhão MARANHÃO 18521 9.37%
Mato Grosso MATO GROSSO 31169 15.77%
Mato Grosso do Sul MATO GROSSO DO SUL 11653 5.90%
Minas Gerais MINAS GERAIS 9999 5.06%
Paraná PARANÁ 3314 1.68%
Paraíba PARAÍBA 1184 0.60%
Pará PARÁ 30165 15.26%
Pernambuco PERNAMBUCO 840 0.43%
Piauí PIAUÍ 10894 5.51%
Rio de Janeiro RIO DE JANEIRO 712 0.36%
Rio Grande do Norte RIO GRANDE DO NORTE 730 0.37%
Rio Grande do Sul RIO GRANDE DO SUL 3196 1.62%
Rondônia RONDÔNIA 11230 5.68%
Roraima RORAIMA 4784 2.42%
Santa Catarina SANTA CATARINA 1804 0.91%
Sergipe SERGIPE 81 0.04%
São Paulo SÃO PAULO 3074 1.56%
Tocantins TOCANTINS 13625 6.89%

Wild fires in 2019 divided per state.

UsageError: Line magic function `%%capture` not found.
No handles with labels found to put in legend.
11                   Acre
24                Alagoas
18                  Amapá
4                Amazonas
9                   Bahia
13                  Ceará
25       Distrito Federal
23         Espírito Santo
10                  Goiás
2                Maranhão
0             Mato Grosso
5      Mato Grosso do Sul
8            Minas Gerais
14                 Paraná
19                Paraíba
1                    Pará
20             Pernambuco
7                   Piauí
22         Rio de Janeiro
21    Rio Grande do Norte
15      Rio Grande do Sul
6                Rondônia
12                Roraima
17         Santa Catarina
26                Sergipe
16              São Paulo
3               Tocantins
Name: State, dtype: object

Appending the 2019 numbers to the 2017 data for comparison

<class 'pandas.core.frame.DataFrame'>
Int64Index: 27 entries, 11 to 3
Data columns (total 16 columns):
 #   Column                         Non-Null Count  Dtype  
---  ------                         --------------  -----  
 0   Campo                          27 non-null     object 
 1   Valor                          27 non-null     int64  
 2   Porcentagem do Total de Focos  27 non-null     object 
 3   State                          27 non-null     object 
 4   Number2019                     27 non-null     int64  
 5   Unnamed: 0                     27 non-null     int64  
 6   Lat                            27 non-null     object 
 7   Long                           27 non-null     object 
 8   Country                        27 non-null     object 
 9   Latitude                       27 non-null     float64
 10  Longitude                      27 non-null     float64
 11  Area                           27 non-null     float64
 12  Número                         27 non-null     int64  
 13  density                        27 non-null     float64
 14  densityMax                     27 non-null     float64
 15  geometry                       27 non-null     object 
dtypes: float64(5), int64(4), object(7)
memory usage: 3.6+ KB
Campo Valor Porcentagem do Total de Focos Number2019 Unnamed: 0 Lat Long Country Latitude Longitude Area Número density densityMax geometry Nettodiff Diff2Y
State
Acre ACRE 6802 3.44% 6802 0 9°1'25.666"S 70°48'43.182"W Brazil -9.023796 -70.811995 164123.0 7042 0.042907 46.068011 POINT (-70.811995 -9.023796111111112) -240 -3.408123
Alagoas ALAGOAS 232 0.12% 232 1 9°34'16.702"S 36°46'55.024"W Brazil -9.571306 -36.781951 27778.5 159 0.005724 6.145557 POINT (-36.78195111111111 -9.571306111111113) 73 45.911950
Amapá AMAPÁ 1277 0.65% 1277 2 1°11'4.999"N 51°43'47.327"W Brazil 1.184722 -51.729813 142828.5 1465 0.010257 11.012746 POINT (-51.72981305555556 1.184721944444445) -188 -12.832765
Amazonas AMAZONAS 12676 6.41% 12676 3 3°25'0.635"S 65°51'21.834"W Brazil -3.416843 -65.856065 1559159.1 14798 0.009491 10.190265 POINT (-65.856065 -3.416843055555556) -2122 -14.339776
Bahia BAHIA 7371 3.73% 7371 4 12°34'47.057"S 41°42'2.617"W Brazil -12.579738 -41.700727 564733.2 8249 0.014607 15.683062 POINT (-41.70072694444445 -12.57973805555556) -878 -10.643714
Ceará CEARÁ 4304 2.18% 4304 26 5°29'54.233"S 39°19'14.246"W Brazil -5.498398 -39.320624 148920.5 2555 0.017157 18.420835 POINT (-39.32062388888889 -5.498398055555557) 1749 68.454012
Distrito Federal DISTRITO FEDERAL 213 0.11% 213 5 15°38'16.494"S 48°0'54.216"W Brazil -15.637915 -48.015060 5780.0 410 0.070934 76.160346 POINT (-48.01506 -15.637915) -197 -48.048780
Espírito Santo ESPÍRITO SANTO 622 0.31% 622 6 19°11'0.323"S 40°18'31.907"W Brazil -19.183423 -40.308863 46095.6 234 0.005076 5.450411 POINT (-40.30886305555556 -19.18342305555555) 388 165.811966
Goiás GOIÁS 7160 3.62% 7160 7 15°49'37.333"S 49°50'10.406"W Brazil -15.827037 -49.836224 340111.8 8705 0.025595 27.480205 POINT (-49.8362238888889 -15.82703694444444) -1545 -17.748420
Maranhão MARANHÃO 18521 9.37% 18521 8 4°48'3.823"S 45°22'58.098"W Brazil -4.801062 -45.382805 331937.4 30916 0.093138 100.000000 POINT (-45.382805 -4.801061944444443) -12395 -40.092509
Mato Grosso MATO GROSSO 31169 15.77% 31169 9 12°40'29.73"S 56°48'47.596"W Brazil -12.674925 -56.813221 903366.2 43607 0.048272 51.828097 POINT (-56.8132211111111 -12.674925) -12438 -28.522944
Mato Grosso do Sul MATO GROSSO DO SUL 11653 5.90% 11653 10 20°46'20"S 54°47'6.6"W"W Brazil -20.772222 -54.785167 357145.5 7336 0.020541 22.053983 POINT (-54.78516666666666 -20.77222222222223) 4317 58.846783
Minas Gerais MINAS GERAIS 9999 5.06% 9999 11 18°30'43.841"S 44°33'18.112"W Brazil -18.512178 -44.555031 586522.1 11473 0.019561 21.002234 POINT (-44.55503111111111 -18.51217805555556) -1474 -12.847555
Paraná PARANÁ 3314 1.68% 3314 13 25°15'53."S 52°05'50."W Brazil -25.252000 -52.022000 199307.9 4463 0.022392 24.042259 POINT (-52.022 -25.252) -1149 -25.745015
Paraíba PARAÍBA 1184 0.60% 1184 14 7°14'23.86"S 36°46'55.024"W Brazil -7.239961 -36.781951 56469.8 294 0.005206 5.589899 POINT (-36.78195111111111 -7.239961111111112) 890 302.721088
Pará PARÁ 30165 15.26% 30165 12 1°59'53.257"S 54°55'50.214"W Brazil -1.998127 -54.930615 1247954.7 59771 0.047895 51.423850 POINT (-54.930615 -1.998126944444444) -29606 -49.532382
Pernambuco PERNAMBUCO 840 0.43% 840 15 8°48'49.381"S 36°57'14.785"W Brazil -8.813717 -36.954107 98148.3 522 0.005318 5.710322 POINT (-36.95410694444445 -8.813716944444446) 318 60.919540
Piauí PIAUÍ 10894 5.51% 10894 16 21°30'19.372"S 43°18'58.212"W Brazil -5.322220 -41.552502 251577.7 9478 0.037674 40.449900 POINT (-41.55250170000001 -5.3222198) 1416 14.939861
Rio de Janeiro RIO DE JANEIRO 712 0.36% 712 17 22°30'31.504"S 42°45'41.53"W Brazil -22.508751 -42.761536 43780.2 1397 0.031909 34.260331 POINT (-42.76153611111111 -22.50875111111111) -685 -49.033644
Rio Grande do Norte RIO GRANDE DO NORTE 730 0.37% 730 18 5°24'9.3"S 36°57'14.8"W Brazil -5.402583 -36.954111 52811.0 299 0.005662 6.078826 POINT (-36.95411111111111 -5.402583333333332) 431 144.147157
Rio Grande do Sul RIO GRANDE DO SUL 3196 1.62% 3196 19 30°2'4.7"S 51°13'3.7"W Brazil -30.034639 -51.217694 281730.2 2575 0.009140 9.813337 POINT (-51.21769444444445 -30.03463888888889) 621 24.116505
Rondônia RONDÔNIA 11230 5.68% 11230 20 11°30'20.642"S 63°34'50.2"W Brazil -11.505734 -63.580611 237590.5 14084 0.059278 63.645812 POINT (-63.58061111111112 -11.50573388888888) -2854 -20.264130
Roraima RORAIMA 4784 2.42% 4784 21 2°44'15.349"N 62°4'30.36"W Brazil 2.737597 -62.075100 224300.5 1101 0.004909 5.270235 POINT (-62.07510000000001 2.737596944444444) 3683 334.514078
Santa Catarina SANTA CATARINA 1804 0.91% 1804 22 27°14'32.4"S 50°13'7.9"W Brazil -27.242333 -50.218861 95736.2 2354 0.024588 26.399954 POINT (-50.21886111111111 -27.24233333333333) -550 -23.364486
Sergipe SERGIPE 81 0.04% 81 24 10°54'40"S 37°4'18"W Brazil -10.911111 -37.071667 21915.1 75 0.003422 3.674436 POINT (-37.07166666666667 -10.91111111111111) 6 8.000000
São Paulo SÃO PAULO 3074 1.56% 3074 23 23°33'1.9"S 46°37'59.9"W Brazil -23.550528 -46.633306 248222.8 5406 0.021779 23.383379 POINT (-46.63330555555557 -23.55052777777777) -2332 -43.137255
Tocantins TOCANTINS 13625 6.89% 13625 25 21°10'30"S 43°1'4.01"W Brazil -10.175280 -48.298247 277720.5 22317 0.080358 86.278138 POINT (-48.2982474 -10.17528) -8692 -38.947887

Difference in numbers of fires over a period of 2 years: 2017-2019 (netto).

State Acre Alagoas Amapá Amazonas Bahia Ceará Distrito Federal Espírito Santo Goiás Maranhão ... Piauí Rio Grande do Norte Rio Grande do Sul Rio de Janeiro Rondônia Roraima Santa Catarina Sergipe São Paulo Tocantins
Nettodiff -240 73 -188 -2122 -878 1749 -197 388 -1545 -12395 ... 1416 431 621 -685 -2854 3683 -550 6 -2332 -8692

1 rows × 27 columns

Let's look at the impact of new fire numbers weighted to the area of the state.

No handles with labels found to put in legend.

firesBrazil1719

Lat Long Country Latitude Longitude Area Número density densityMax geometry
State
Acre 9°1'25.666"S 70°48'43.182"W Brazil -9.023796 -70.811995 164123.0 7042 0.042907 46.068011 POINT (-70.811995 -9.023796111111112)
Alagoas 9°34'16.702"S 36°46'55.024"W Brazil -9.571306 -36.781951 27778.5 159 0.005724 6.145557 POINT (-36.78195111111111 -9.571306111111113)
Amapá 1°11'4.999"N 51°43'47.327"W Brazil 1.184722 -51.729813 142828.5 1465 0.010257 11.012746 POINT (-51.72981305555556 1.184721944444445)
Amazonas 3°25'0.635"S 65°51'21.834"W Brazil -3.416843 -65.856065 1559159.1 14798 0.009491 10.190265 POINT (-65.856065 -3.416843055555556)
Bahia 12°34'47.057"S 41°42'2.617"W Brazil -12.579738 -41.700727 564733.2 8249 0.014607 15.683062 POINT (-41.70072694444445 -12.57973805555556)
Ceará 5°29'54.233"S 39°19'14.246"W Brazil -5.498398 -39.320624 148920.5 2555 0.017157 18.420835 POINT (-39.32062388888889 -5.498398055555557)
Distrito Federal 15°38'16.494"S 48°0'54.216"W Brazil -15.637915 -48.015060 5780.0 410 0.070934 76.160346 POINT (-48.01506 -15.637915)
Espírito Santo 19°11'0.323"S 40°18'31.907"W Brazil -19.183423 -40.308863 46095.6 234 0.005076 5.450411 POINT (-40.30886305555556 -19.18342305555555)
Goiás 15°49'37.333"S 49°50'10.406"W Brazil -15.827037 -49.836224 340111.8 8705 0.025595 27.480205 POINT (-49.8362238888889 -15.82703694444444)
Maranhão 4°48'3.823"S 45°22'58.098"W Brazil -4.801062 -45.382805 331937.4 30916 0.093138 100.000000 POINT (-45.382805 -4.801061944444443)
Mato Grosso 12°40'29.73"S 56°48'47.596"W Brazil -12.674925 -56.813221 903366.2 43607 0.048272 51.828097 POINT (-56.8132211111111 -12.674925)
Mato Grosso do Sul 20°46'20"S 54°47'6.6"W"W Brazil -20.772222 -54.785167 357145.5 7336 0.020541 22.053983 POINT (-54.78516666666666 -20.77222222222223)
Minas Gerais 18°30'43.841"S 44°33'18.112"W Brazil -18.512178 -44.555031 586522.1 11473 0.019561 21.002234 POINT (-44.55503111111111 -18.51217805555556)
Paraná 25°15'53."S 52°05'50."W Brazil -25.252000 -52.022000 199307.9 4463 0.022392 24.042259 POINT (-52.022 -25.252)
Paraíba 7°14'23.86"S 36°46'55.024"W Brazil -7.239961 -36.781951 56469.8 294 0.005206 5.589899 POINT (-36.78195111111111 -7.239961111111112)
Pará 1°59'53.257"S 54°55'50.214"W Brazil -1.998127 -54.930615 1247954.7 59771 0.047895 51.423850 POINT (-54.930615 -1.998126944444444)
Pernambuco 8°48'49.381"S 36°57'14.785"W Brazil -8.813717 -36.954107 98148.3 522 0.005318 5.710322 POINT (-36.95410694444445 -8.813716944444446)
Piauí 21°30'19.372"S 43°18'58.212"W Brazil -5.322220 -41.552502 251577.7 9478 0.037674 40.449900 POINT (-41.55250170000001 -5.3222198)
Rio Grande do Norte 5°24'9.3"S 36°57'14.8"W Brazil -5.402583 -36.954111 52811.0 299 0.005662 6.078826 POINT (-36.95411111111111 -5.402583333333332)
Rio Grande do Sul 30°2'4.7"S 51°13'3.7"W Brazil -30.034639 -51.217694 281730.2 2575 0.009140 9.813337 POINT (-51.21769444444445 -30.03463888888889)
Rio de Janeiro 22°30'31.504"S 42°45'41.53"W Brazil -22.508751 -42.761536 43780.2 1397 0.031909 34.260331 POINT (-42.76153611111111 -22.50875111111111)
Rondônia 11°30'20.642"S 63°34'50.2"W Brazil -11.505734 -63.580611 237590.5 14084 0.059278 63.645812 POINT (-63.58061111111112 -11.50573388888888)
Roraima 2°44'15.349"N 62°4'30.36"W Brazil 2.737597 -62.075100 224300.5 1101 0.004909 5.270235 POINT (-62.07510000000001 2.737596944444444)
Santa Catarina 27°14'32.4"S 50°13'7.9"W Brazil -27.242333 -50.218861 95736.2 2354 0.024588 26.399954 POINT (-50.21886111111111 -27.24233333333333)
Sergipe 10°54'40"S 37°4'18"W Brazil -10.911111 -37.071667 21915.1 75 0.003422 3.674436 POINT (-37.07166666666667 -10.91111111111111)
São Paulo 23°33'1.9"S 46°37'59.9"W Brazil -23.550528 -46.633306 248222.8 5406 0.021779 23.383379 POINT (-46.63330555555557 -23.55052777777777)
Tocantins 21°10'30"S 43°1'4.01"W Brazil -10.175280 -48.298247 277720.5 22317 0.080358 86.278138 POINT (-48.2982474 -10.17528)
261085

Difference in numbers of fires over a time span of 2 years: 2017-2019 (percentage).

State Acre Alagoas Amapá Amazonas Bahia Ceará Distrito Federal Espírito Santo Goiás Maranhão ... Piauí Rio Grande do Norte Rio Grande do Sul Rio de Janeiro Rondônia Roraima Santa Catarina Sergipe São Paulo Tocantins
Diff2Y -3.408123 45.91195 -12.832765 -14.339776 -10.643714 68.454012 -48.04878 165.811966 -17.74842 -40.092509 ... 14.939861 144.147157 24.116505 -49.033644 -20.26413 334.514078 -23.364486 8.0 -43.137255 -38.947887

1 rows × 27 columns

[Text(0, 0.5, 'Federal State'),
 Text(0.5, 0, 'Difference in numbers of fires: 2017-2019 (percentage)')]

Wild fires spotted inside the 5 km protective corridor around Federal Conservation Units in 2019.

States Valor Porcentagem do Total de Focos
Campo
FLOREX RIO PRETO-JACUNDÁ RONDÔNIA 256 0.13%
RESEX JACI-PARANÁ RONDÔNIA 249 0.13%
APA RIO PARDO RONDÔNIA 247 0.12%
RESEX GUARIBA-ROOSEVELT MATO GROSSO 247 0.12%
PES DE MIRADOR MARANHÃO 243 0.12%
... ... ... ...
RPPN VOVÓ DINDINHA ESPÍRITO SANTO 1 0.00%
RVS MATA DA USINA SÃO JOSÉ PERNAMBUCO 1 0.00%
RVS MATA DO CONTRA-AÇUDE PERNAMBUCO 1 0.00%
RVS MATA DO JUNCO SERGIPE 1 0.00%
RVS MATA DOS MURIQUIS MINAS GERAIS 1 0.00%

577 rows × 3 columns

States ACRE ACRE - AMAZONAS ALAGOAS AMAPÁ AMAPÁ - PARÁ AMAZONAS AMAZONAS - MATO GROSSO AMAZONAS - RONDÔNIA AMAZONAS - RORAIMA BAHIA ... PIAUÍ RIO DE JANEIRO RIO GRANDE DO NORTE RIO GRANDE DO SUL RIO GRANDE DO SUL - SANTA CATARINA RONDÔNIA SANTA CATARINA SERGIPE SÃO PAULO TOCANTINS
Valor 119 380 24 222 19 328 62 154 4 334 ... 13 265 14 146 15 1704 26 2 510 579

1 rows × 52 columns

A. I can split the values up according to the weight that state had in the data of 2017.
B. I might search for the Coordinates of the border locations for a more accurate plot.

<class 'pandas.core.frame.DataFrame'>
Index: 1 entries, Valor to Valor
Data columns (total 52 columns):
 #   Column                              Non-Null Count  Dtype
---  ------                              --------------  -----
 0   ACRE                                1 non-null      int64
 1   ACRE - AMAZONAS                     1 non-null      int64
 2   ALAGOAS                             1 non-null      int64
 3   AMAPÁ                               1 non-null      int64
 4   AMAPÁ - PARÁ                        1 non-null      int64
 5   AMAZONAS                            1 non-null      int64
 6   AMAZONAS - MATO GROSSO              1 non-null      int64
 7   AMAZONAS - RONDÔNIA                 1 non-null      int64
 8   AMAZONAS - RORAIMA                  1 non-null      int64
 9   BAHIA                               1 non-null      int64
 10  BAHIA - GOIÁS                       1 non-null      int64
 11  BAHIA - MARANHÃO - PIAUÍ            1 non-null      int64
 12  BAHIA - MINAS GERAIS                1 non-null      int64
 13  BAHIA - PIAUÍ                       1 non-null      int64
 14  BAHIA - PIAUÍ - TOCANTINS           1 non-null      int64
 15  BAHIA - TOCANTINS                   1 non-null      int64
 16  CEARÁ                               1 non-null      int64
 17  DISTRITO FEDERAL                    1 non-null      int64
 18  DISTRITO FEDERAL - GOIÁS            1 non-null      int64
 19  ESPÍRITO SANTO                      1 non-null      int64
 20  GOIÁS                               1 non-null      int64
 21  GOIÁS - MATO GROSSO                 1 non-null      int64
 22  GOIÁS - TOCANTINS                   1 non-null      int64
 23  MARANHÃO                            1 non-null      int64
 24  MARANHÃO - PARÁ                     1 non-null      int64
 25  MARANHÃO - PIAUÍ                    1 non-null      int64
 26  MARANHÃO - TOCANTINS                1 non-null      int64
 27  MATO GROSSO                         1 non-null      int64
 28  MATO GROSSO - MATO GROSSO DO SUL    1 non-null      int64
 29  MATO GROSSO - PARÁ                  1 non-null      int64
 30  MATO GROSSO - TOCANTINS             1 non-null      int64
 31  MATO GROSSO DO SUL                  1 non-null      int64
 32  MINAS GERAIS                        1 non-null      int64
 33  MINAS GERAIS - SÃO PAULO            1 non-null      int64
 34  PARANÁ                              1 non-null      int64
 35  PARANÁ - SANTA CATARINA             1 non-null      int64
 36  PARANÁ - SÃO PAULO                  1 non-null      int64
 37  PARAÍBA                             1 non-null      int64
 38  PARAÍBA - PERNAMBUCO                1 non-null      int64
 39  PARÁ                                1 non-null      int64
 40  PARÁ - TOCANTINS                    1 non-null      int64
 41  PERNAMBUCO                          1 non-null      int64
 42  PIAUÍ                               1 non-null      int64
 43  RIO DE JANEIRO                      1 non-null      int64
 44  RIO GRANDE DO NORTE                 1 non-null      int64
 45  RIO GRANDE DO SUL                   1 non-null      int64
 46  RIO GRANDE DO SUL - SANTA CATARINA  1 non-null      int64
 47  RONDÔNIA                            1 non-null      int64
 48  SANTA CATARINA                      1 non-null      int64
 49  SERGIPE                             1 non-null      int64
 50  SÃO PAULO                           1 non-null      int64
 51  TOCANTINS                           1 non-null      int64
dtypes: int64(52)
memory usage: 424.0+ bytes

Barplot of states which had wild fires inside the 5 km protective buffer zone

[Text(0, 0, 'RONDÔNIA')]

Fires located inside the 5 km buffer zones surrounding labelled "Indigenous Territorium" forest territory

Date of the observation: 2020-03-02

latGms lngGms longitude latitude data_hora_ satelite municipio estado pais precipitac ... risco_fogo bioma grade_wrs path_row continente vegetacao id_area_in frp id_tipo_ar geometry
0 N 4 15 36 W 60 3 0 -60.050 4.260 2020-03-02 GOES-16 NORMANDIA RORAIMA Brasil 0.00 ... 0.81 Amazônia 232/57 232_057 8 Savana arbórea; Caatinga fechada 0 NaN None POINT (-60.05000 4.26000)
1 N 4 15 36 W 60 1 48 -60.030 4.260 2020-03-02 GOES-16 NORMANDIA RORAIMA Brasil 0.00 ... 0.81 Amazônia 232/57 232_057 8 Savana arbórea; Caatinga fechada 0 NaN None POINT (-60.03000 4.26000)
2 N 4 15 36 W 60 1 48 -60.030 4.260 2020-03-02 GOES-16 NORMANDIA RORAIMA Brasil 0.00 ... 0.81 Amazônia 232/57 232_057 8 Savana arbórea; Caatinga fechada 0 NaN None POINT (-60.03000 4.26000)
3 N 4 15 36 W 60 3 0 -60.050 4.260 2020-03-02 GOES-16 NORMANDIA RORAIMA Brasil 0.00 ... 0.81 Amazônia 232/57 232_057 8 Savana arbórea; Caatinga fechada 0 NaN None POINT (-60.05000 4.26000)
4 N 4 15 36 W 60 3 0 -60.050 4.260 2020-03-02 GOES-16 NORMANDIA RORAIMA Brasil 0.00 ... 0.81 Amazônia 232/57 232_057 8 Savana arbórea; Caatinga fechada 0 NaN None POINT (-60.05000 4.26000)
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
182 N 3 36 36 W 60 6 29 -60.108 3.610 2020-03-02 AQUA_M-T NORMANDIA RORAIMA Brasil 0.00 ... 0.81 Amazônia 232/57 232_057 8 Savana arbórea; Caatinga fechada 0 31.1 None POINT (-60.10800 3.61000)
183 N 3 11 6 W 60 29 38 -60.494 3.185 2020-03-02 AQUA_M-T BOA VISTA RORAIMA Brasil 0.00 ... 0.42 Amazônia 232/58 232_058 8 Savana arbórea; Caatinga fechada 0 78.4 None POINT (-60.49400 3.18500)
184 N 3 10 55 W 60 28 41 -60.478 3.182 2020-03-02 AQUA_M-T BOA VISTA RORAIMA Brasil 0.00 ... 0.42 Amazônia 232/58 232_058 8 Savana arbórea; Caatinga fechada 0 27.9 None POINT (-60.47800 3.18200)
185 N 2 54 11 W 60 0 11 -60.003 2.903 2020-03-02 AQUA_M-T BONFIM RORAIMA Brasil 0.00 ... 0.41 Amazônia 231/58 231_058 8 Floresta Ombrófila densa 0 50.7 None POINT (-60.00300 2.90300)
186 S 12 1 1 W 64 48 11 -64.803 -12.017 2020-03-02 AQUA_M-T GUAJARÁ-MIRIM RONDÔNIA Brasil 1.96 ... 0.01 Amazônia 232/68 232_068 8 Floresta Ombrófila densa 0 9.2 None POINT (-64.80300 -12.01700)

187 rows × 21 columns

Random Forest Regressor

Unnamed: 0 Date Ano Estado Mês Número Período Year Month Day Month2 month_cat
5259 5259 1998-01-15 1998 Roraima 1 0 01/01/1998 1998 1 15 1 0
5260 5260 1999-01-15 1999 Roraima 1 15 01/01/1999 1999 1 15 1 0
5261 5261 2000-01-15 2000 Roraima 1 18 01/01/2000 2000 1 15 1 0
5262 5262 2001-01-15 2001 Roraima 1 101 01/01/2001 2001 1 15 1 0
5263 5263 2002-01-15 2002 Roraima 1 302 01/01/2002 2002 1 15 1 0
... ... ... ... ... ... ... ... ... ... ... ... ...
5493 5493 2012-12-15 2012 Roraima 12 78 01/01/2012 2012 12 15 12 11
5494 5494 2013-12-15 2013 Roraima 12 65 01/01/2013 2013 12 15 12 11
5495 5495 2014-12-15 2014 Roraima 12 277 01/01/2014 2014 12 15 12 11
5496 5496 2015-12-15 2015 Roraima 12 304 01/01/2015 2015 12 15 12 11
5497 5497 2016-12-15 2016 Roraima 12 136 01/01/2016 2016 12 15 12 11

239 rows × 12 columns

Unnamed: 0 Ano Estado Mês Número Período Year Month Day Month2
Date
1998-01-15 0 1998 Acre 1 0 01/01/1998 1998 1 15 1
1999-01-15 1 1999 Acre 1 0 01/01/1999 1999 1 15 1
2000-01-15 2 2000 Acre 1 0 01/01/2000 2000 1 15 1
2001-01-15 3 2001 Acre 1 0 01/01/2001 2001 1 15 1
2002-01-15 4 2002 Acre 1 0 01/01/2002 2002 1 15 1
Mean Absolute Error:  8.090909090909092
   Predicted  Actual
0         17      31
1         22      18
2         31      16
3         20       8
4          8       1
Mean Absolute Error:  3139.7272727272725
   Predicted  Actual
0        982     219
1        368      14
2        159      42
3         90      45
4        151     114

%whos

Markdown and LaTeX: 𝛼2

Maps of Brazil

Agriculture map

  1. Brazil agriculture map
  1. Legal Amazon Map 2017 Zebende IBGE 2018

Public forests of Brazil map

  1. Map with the states and public forests of Brazil

Major biomes and federal protected areas map

  1. Brazil major biomes and federal protected areas (reserves that responded)

Types of protected area

Protected areas, also called conservation units, are divided into different categories according to their goals. These are defined by Law No. 9.985 of 18 July 2000, which established the National System of Conservation Units (SNUC).
Objectives include conservation of nature, sustainable development, scientific research, education and eco-tourism.
Fully protected units are expected to maintain the natural ecosystem without human interference.
Sustainable use units allow sustained use of renewable environmental resources while maintaining biodiversity and other ecological attributes.

The Chico Mendes Institute for Biodiversity Conservation, which administers Federal units, defines the classes of unit as:

Fully protected (proteção integral)

  • Ecological stations (Portuguese: Estações Ecológicas)
  • Biological reserves (Portuguese: Reservas Biológicas)
  • National parks (Portuguese: Parques nacionais), State parks (Portuguese: Parques estaduais) and Municipal nature parks (Portuguese: Parques naturais municipais)
  • Natural monuments (Portuguese: Monumentos Naturais)
  • Wildlife refuges (Portuguese: Refúgios de Vida Silvestre)

The sustainable use units are:

  • Environmental protection areas (Portuguese: Áreas de Proteção Ambiental)
  • Areas of relevant ecological interest (Portuguese: Áreas de Relevante Interesse Ecológico)
  • National forests (Portuguese: Florestas Nacionais) and State forests (Portuguese: Florestas Estaduais)
  • Extractive reserves (Portuguese: Reservas Extrativistas)
  • Wildlife reserves (Portuguese: Reservas de Fauna)
  • Sustainable development reserves (Portuguese: Reservas de Desenvolvimento Sustentável)
  • Private natural heritage reserves (Portuguese: Reservas Particular do Patrimônio Natural)

In addition, some states designate areas as ecological reserve (Portuguese: Reserva Ecológica).


satelite pais estado municipio bioma diasemchuva precipitacao riscofogo latitude longitude frp
datahora
2018-02-01 17:06:00 NPP-375 Brasil RORAIMA UIRAMUTA Amazonia 0 0.00 0.35 4.35564 -60.20242 NaN
2018-03-12 05:30:00 NPP-375 Brasil RORAIMA CANTA Amazonia 0 0.00 0.41 2.18465 -60.81395 NaN
2018-03-24 17:36:00 NPP-375 Brasil SANTA CATARINA SANTA CECILIA Mata Atlantica 0 27.85 0.00 -27.06369 -50.48926 NaN
2018-03-13 05:12:00 NPP-375 Brasil RORAIMA CARACARAI Amazonia 0 0.00 0.34 1.71623 -60.99483 NaN
2018-02-27 17:18:00 NPP-375 Brasil RORAIMA CARACARAI Amazonia 0 1.15 0.85 1.96740 -60.78246 NaN
... ... ... ... ... ... ... ... ... ... ... ...
2018-03-19 15:54:00 NPP-375 Brasil MINAS GERAIS ALMENARA Mata Atlantica 0 0.00 0.13 -15.96370 -40.59505 NaN
2018-02-18 04:06:00 NPP-375 Brasil BAHIA RIACHAO DAS NEVES Cerrado 0 0.55 0.23 -11.49848 -44.87274 NaN
2018-03-31 17:12:00 NPP-375 Brasil MINAS GERAIS ARINOS Cerrado 0 0.00 0.51 -15.63578 -45.77114 NaN
2018-03-09 04:48:00 NPP-375 Brasil RORAIMA BONFIM Amazonia 0 0.00 0.34 3.19729 -60.01252 NaN
2018-03-12 05:30:00 NPP-375 Brasil RORAIMA CANTA Amazonia 0 0.00 0.24 2.61829 -60.60953 NaN

894841 rows × 11 columns

satelite pais estado municipio bioma diasemchuva precipitacao riscofogo latitude longitude frp Tel
datahora
2018-01-01 04:06:00 NPP-375 Brasil Pará DOM ELISEU Amazonia 0 0.00 0.00 -4.13374 -47.74136 NaN 146071
2018-01-01 04:06:00 NPP-375 Brasil Maranhão CURURUPU Amazonia 0 0.68 0.03 -1.87060 -44.79064 NaN 96061
2018-01-01 04:06:00 NPP-375 Brasil Maranhão BURITICUPU Amazonia 0 0.28 0.05 -4.57812 -46.39031 NaN 96061
2018-01-01 04:06:00 NPP-375 Brasil Maranhão AMAPA DO MARANHAO Amazonia 0 0.00 0.77 -1.63951 -45.92559 NaN 96061
2018-01-01 04:06:00 NPP-375 Brasil Maranhão ITINGA DO MARANHAO Amazonia 0 0.32 0.01 -4.12603 -47.14958 NaN 96061
... ... ... ... ... ... ... ... ... ... ... ... ...
2018-12-31 18:00:00 NPP-375 Brasil Roraima PACARAIMA Amazonia 11 0.00 0.07 3.65606 -60.45773 7.6 26019
2018-12-31 18:00:00 NPP-375 Brasil Roraima PACARAIMA Amazonia 11 0.00 0.07 3.64490 -60.57117 6.3 26019
2018-12-31 18:00:00 NPP-375 Brasil Roraima PACARAIMA Amazonia 11 0.00 0.07 3.64252 -60.57256 6.5 26019
2018-12-31 18:00:00 NPP-375 Brasil Roraima BOA VISTA Amazonia 19 0.00 0.74 3.33945 -60.41800 5.6 26019
2018-12-31 18:00:00 NPP-375 Brasil AMAZONAS SAO GABRIEL DA CACHOEIRA Amazonia 5 0.00 0.20 1.29423 -68.98925 4.9 62402

894841 rows × 12 columns

The fire risk index versus the power in Watts emitted by wild fires.

It has been known that the presence of lots of smoke can have a mitigating affect on the amount of fires. see the report of Mr Dias Alexandre of the INPE

Plot of fire risk index , power emitted by wild fires and amount of precipitation.

diasemchuva precipitacao riscofogo latitude longitude frp Tel 7d d7 Prep10
datahora
2018-01-01 0.000000 4.726857 0.284286 -8.554291 -45.667726 NaN 60703.342857 67677.835597 NaN 47.268571
2018-01-02 0.000000 1.908403 0.288244 -5.485300 -44.740374 NaN 74368.886151 67677.835597 NaN 19.084027
2018-01-03 0.023585 2.135915 0.299535 -4.894919 -46.258911 NaN 71054.132075 67677.835597 NaN 21.359151
2018-01-04 0.000000 2.280958 0.258852 -6.563095 -49.214242 NaN 81773.965358 67677.835597 NaN 22.809584
2018-01-05 0.000000 3.424190 0.214359 -6.264962 -52.064192 NaN 85238.827935 67677.835597 NaN 34.241903
diasemchuva precipitacao riscofogo latitude longitude frp Tel 7d d7 Prep10
datahora
2018-12-27 3.069288 0.344698 0.243917 -5.105968 -48.564982 10.793889 107157.606072 NaN 72565.925161 3.446983
2018-12-28 4.037851 0.226860 0.170280 -3.882601 -49.667922 10.829548 119944.864957 NaN 81693.680235 2.268596
2018-12-29 4.690727 0.604553 0.286570 -4.296227 -45.920646 11.078512 79268.877846 NaN 83494.767940 6.045530
2018-12-30 4.791297 1.509654 0.319095 -4.561789 -44.871554 11.798630 75260.501209 NaN 82979.993070 15.096535
2018-12-31 5.841420 0.635787 0.444301 -6.107027 -43.861548 11.677988 46149.123077 NaN 79929.248747 6.357870

Plot of fire risk index and power emitted by wild fires.

The fire risk index for a particular day is determined beforehand, and is a value between 0 and 1. The maximum likelyhood of a fire occuring in the area is 1.
The FPR (in MegaWatts) is only known after the satellite data has been received and processed.
From August on, the divergence of these 2 curves is clear and persistent.

estado satelite
0 ACRE 27194
1 ALAGOAS 2486
2 Amapá 7483
3 Amazonas 62402
4 BAHIA 39022
5 CEARA 18130
6 DISTRITO FEDERAL 645
7 ESPIRITO SANTO 1523
8 GOIAS 24846
9 MATO GROSSO DO SUL 16078
10 MINAS GERAIS 33212
11 Maranhão 96061
12 Mato Grosso 117939
13 PARANA 13346
14 PERNAMBUCO 6978
15 PIAUI 78502
16 Paraíba 6326
17 Pará 146071
18 RIO DE JANEIRO 2259
19 RIO GRANDE DO NORTE 3227
20 RIO GRANDE DO SUL 10215
21 Rondônia 63534
22 Roraima 26019
23 SANTA CATARINA 7289
24 SAO PAULO 18532
25 SERGIPE 1496
26 TOCANTINS 64026

Unnamed: 0 Ano Estado Mês Número Período Year Month Day Month2
Date
1998-01-15 0 1998 Acre 1 0 01/01/1998 1998 1 15 1
1999-01-15 1 1999 Acre 1 0 01/01/1999 1999 1 15 1
2000-01-15 2 2000 Acre 1 0 01/01/2000 2000 1 15 1
2001-01-15 3 2001 Acre 1 0 01/01/2001 2001 1 15 1
2002-01-15 4 2002 Acre 1 0 01/01/2002 2002 1 15 1

Group of lineplots

Unnamed: 0 Ano Estado Mês Número Período Year Month Day Month2
Date
1998-01-15 3347 1998 Paraíba 1 0 01/01/1998 1998 1 15 1
1999-01-15 3348 1999 Paraíba 1 26 01/01/1999 1999 1 15 1
2000-01-15 3349 2000 Paraíba 1 0 01/01/2000 2000 1 15 1
2001-01-15 3350 2001 Paraíba 1 11 01/01/2001 2001 1 15 1
2002-01-15 3351 2002 Paraíba 1 5 01/01/2002 2002 1 15 1
... ... ... ... ... ... ... ... ... ... ...
2012-12-15 3581 2012 Paraíba 12 62 01/01/2012 2012 12 15 12
2013-12-15 3582 2013 Paraíba 12 78 01/01/2013 2013 12 15 12
2014-12-15 3583 2014 Paraíba 12 62 01/01/2014 2014 12 15 12
2015-12-15 3584 2015 Paraíba 12 122 01/01/2015 2015 12 15 12
2016-12-15 3585 2016 Paraíba 12 8 01/01/2016 2016 12 15 12

239 rows × 10 columns

Poisson