Wolfram Research

Function Repository Resource:

INaturalistSearch (1.0.0) current version: 1.1.0 »

Source Notebook

Search for iNaturalist observations using the iNaturalist API

Contributed by: Jofre Espigule-Pons  |  JofreEspigulePons

ResourceFunction["INaturalistSearch"][query]

gives a dataset with taxa occurrences of the specified query.

ResourceFunction["INaturalistSearch"][query,prop]

gives the property prop of the specified query.

Details and Options

ResourceFunction["INaturalistSearch"] utilizes iNaturalist's API to find observations of species and taxa.
The query can be specified using a taxon (as a string, Entity or an ExternalIdentifier for a Wikidata ID) or by All to include all possible taxa in the search.
ResourceFunction["INaturalistSearch"][query] is equivalent to ResourceFunction["INaturalistSearch"][query,"Dataset"].
Supported properties for ResourceFunction["INaturalistSearch"] include:
"Count"total count of taxa observations of the specified query
"Dataset"dataset with taxa observations of the specified query
"SimplifiedDataset"simplified dataset with taxa observations of the specified query
"RawData"raw data of taxa observations of the specified query
ResourceFunction["INaturalistSearch"] accepts the same options as Dataset for the "SimplifiedDataset" property.
Other options supported by ResourceFunction["INaturalistSearch"] include:
MaxItems200number of observations to return
Page1page of the observations to return
ObservationGeoRange{{-90, 90}, {-180, 180}}geographic range of the observations
ObservationDateRange{DateObject[{1700}],Today}date range of the observations
The following "QualityGrade" option specifications can be given:
"Research"observations with research grade
"NeedsID"observations that need identification
"Casual"casual observations
The following "HasImage" option specifications can be given:
Trueobservations with images
Falseobservations without images
The following "HasAudio" option specifications can be given:
Trueobservations with audio
Falseobservations without audio
The following "LifeStage" option specifications can be given:
"Egg"observations of eggs
"Adult"observations of adult specimens
"Teneral"observations of teneral specimens
"Pupa"observations of pupa specimens
"Nymph"observations of nymph specimens
"Larva"observations of larva specimens
"Subimago"observations of subimago specimens
"Juvenile"observations of juvenile specimens
The following "Sex" option specifications can be given:
"Male"observations of male specimens
"Female"observations of female specimens
The following "PlantPhenology" option specifications can be given:
"Flowering"observations of flowering plant specimens
"Fruiting"observations of fruiting plant specimens
"FlowerBudding"observations of flower budding plant specimens
"NoEvidenceOfFlowering"observations without evidence of flowering plant specimens
The following "Alive" option specifications can be given:
Trueobservations of alive specimens
Falseobservations of inert specimens
"CannotBeDetermined"observations of unconfirmed alive specimens
The following "Threatened" option specifications can be given:
Trueobservations of threatened taxa
Falseobservations without threatened taxa
The following "Endemic" option specifications can be given:
Trueobservations of endemic taxa
Falseobservations without endemic taxa
The following "Native" option specifications can be given:
Trueobservations of native taxa
Falseobservations without native taxa
The following "Introduced" option specifications can be given:
Trueobservations of introduced taxa
Falseobservations without introduced taxa
The following "Captive" option specifications can be given:
Trueobservations of captive taxa
Falseobservations without captive taxa
ResourceFunction["INaturalistSearch"] does not include observations with missing geographic coordinates.

Examples

Basic Examples (1) 

Obtain a Dataset of threatened species observed in Yellowstone National Park in a span of one week:

In[1]:=
data = ResourceFunction["INaturalistSearch"][All, "Threatened" -> True, "ObservationGeoRange" -> GeoBounds[Entity["Park", "YellowstoneNationalPark::zc6x9"]], "ObservationDateRange" -> {DateObject[{2020, 7, 19}], DateObject[{2020, 7, 26}]}]
Out[1]=

Scope (6) 

Obtain a Dataset of threatened species observed in Yellowstone National Park in a span of a day:

In[2]:=
data = ResourceFunction["INaturalistSearch"][All, "Threatened" -> True, "ObservationGeoRange" -> GeoBounds[Entity["Park", "YellowstoneNationalPark::zc6x9"]], "ObservationDateRange" -> {Yesterday, Today}]
Out[2]=

Get the total count of wolf observations in Yellowstone National Park:

In[3]:=
ResourceFunction["INaturalistSearch"][
 ExternalIdentifier["WikidataID", "Q18498", <|"Label" -> "wolf", "Description" -> "species of mammal"|>], "Count", "ObservationGeoRange" -> GeoBounds[Entity["Park", "YellowstoneNationalPark::zc6x9"]]]
Out[3]=

Obtain a Dataset of all observations of different types of eggs from a specific region:

In[4]:=
ResourceFunction["INaturalistSearch"][ All , "ObservationGeoRange" -> GeoBounds[Entity["AdministrativeDivision", {"Catalonia", "Spain"}]],
  "LifeStage" -> "Egg" ]
Out[4]=

Obtain observations of a specific user containing audio recordings:

In[5]:=
audioData = ResourceFunction["INaturalistSearch"][ All, "UserLogin" -> "jofree", "HasAudio" -> True  ]
Out[5]=

Import the audio file from the previous observation:

In[6]:=
Import[First@Normal@audioData[All, "AudioURL"]]
Out[6]=

Obtain a Dataset of observations from Canada containing audio recordings:

In[7]:=
ResourceFunction["INaturalistSearch"][ All, "ObservationGeoRange" -> GeoBounds[Entity["Country", "Canada"]], "ObservationDateRange" -> {DateObject[{2019, 7, 19}], DateObject[{2019, 7, 21}]}, "HasAudio" -> True  ]
Out[7]=

Obtain a Dataset of a specific taxon with observations of dead specimens only:

In[8]:=
ResourceFunction["INaturalistSearch"][ Entity["Species", "Species:NezaraViridula"] , "SimplifiedDataset" , "Alive" -> False]
Out[8]=

Options (1) 

Options from Dataset can be directly specified in INaturalistSearch for the "SimplifiedDataset" property:

In[9]:=
ResourceFunction["INaturalistSearch"][ Entity["Species", "Species:CanisLupus"], "SimplifiedDataset", "ObservationGeoRange" -> GeoBounds[Entity["Park", "YellowstoneNationalPark::zc6x9"]], "ObservationDateRange" -> {DateObject[{2020, 07, 20}], Today}, Background -> LightBrown ]
Out[9]=

Neat Examples (5) 

Create a classifier to automatically identify observations of nymphs and adults of brown marmorated stink bugs:

In[10]:=
classes = {"Nymph", "Adult"};

Import the images to create a training set and a test set:

In[11]:=
nymphImages = Flatten@Table[
     Map[Import, Normal[ResourceFunction["INaturalistSearch"][ "Halyomorpha halys", "SimplifiedDataset", "QualityGrade" -> "Research"  , "LifeStage" -> "Nymph", "Page" -> i][All, "SquareImageURL"]]], {i, 1, 3}] // Quiet;
In[12]:=
adultImages = Flatten@Table[
     Map[Import, Normal[ResourceFunction["INaturalistSearch"][ "Halyomorpha halys", "SimplifiedDataset", "QualityGrade" -> "Research"  , "LifeStage" -> "Adult", "Page" -> i][All, "SquareImageURL"]]], {i, 1, 3}] // Quiet;
In[13]:=
dataset = RandomSample@
   Flatten[Thread /@ Thread[{nymphImages, adultImages} -> classes]];
In[14]:=
trainingSet = dataset[[;; 700]];
testSet = dataset[[701 ;;]];
In[15]:=
c = Classify[trainingSet, PerformanceGoal -> "Quality"]
Out[15]=
In[16]:=
cm = ClassifierMeasurements[c, testSet, "ConfusionMatrixPlot"]
Out[16]=

Test the trained classifier with two specific test examples:

In[17]:=
testSet[[8]]
Out[17]=
In[18]:=
trained["TrainedNet"][\!\(\*
GraphicsBox[
TagBox[RasterBox[CompressedData["
1:eJw1u3dQm2m+Lsh0O5CRQOScc84555xzFCBAgDJIIBAiSCAQIJSzQFnknG0M
Ns52u213nJmemXPnnKl7d7d2q7b27309Z9f1+iskY+l7fuEJwvbsQlX1fmdk
ZIQzBpeqztFMLLaTVA0BD2qHcf2I4Z7uwmF8D6IHm9D1PXiy+P/7/e3ryw+K
rVuW/sWa6HJ67WJc+mpGdDfBuSIsHwwefF7WvZhb28MKT8d1b5b3fpKq3y5L
ryc1L6aVd1OHn1e1b+ZF1xNLe1j2CVl0PSe/XTK8EWy+FZ5+Xb/+Xb3zjqd+
taz5yFV95MterMpumOJzuvb50vZLxvoVSX1L2X23cPqVf/GL5Or3jd0P3PWb
OeWLedVrmvrd4sFX6frzZfU96+Rn2daHNd4ZWfViGRz5HW3lhMC+xC+dDLMu
Ser3y6o7uu6esfuWtf165eidYPsF6/zT+tv/ODx4JzHccw8+SJ98UZ9/kquf
LYObpO9ils+Ia5ck9sXoxouZ7fdLex9WDz+x129mpc9m938Wbbxa3PywpHs1
t3FLEVyO8i+InFMC/xJgxKleMnc+CfVv2Ou3i/pXK/s/cMExvFvVfmTv/iTd
eMmWPVk6/ay4/mXd8Jy+92ZBc0dVPqMe/sg7AxDec46+SvZ+5B1+Fajf0A9+
4h3/JN37JDn7dePp37R7HznyG/rpL+tv/teR9tWK7HZWfEsR3VH2fxUZfmCr
7hcuf5Uef+bvvlvT3y/vvOVe/KQEZ+sV9/Cj7OyL8slPqud/bJ39tLH1kb96
Orl4NCZ/uaj/yFHdMw4+8TR3C9oXC5vvV7UfmIbPLNnLOdndFPsEu/GCuvtl
RflqZu0Uv/5iTvWKoXq1CIoAGn3xZ/nhZ87BjyvXfxHpXtHBbSufM3feifQv
OPuv+acfxbpn9IMPLP3LBfD6utdr/IvZ0z9rjn5bB2+6+5mrf8dQ3FHPfpZo
ni9f/aZS3S6B2z78JL7/H3unvyi33vP2v4g071a2vvDO/6bdeMXUvl46+Mrd
/mFV/3Z5/cX88S+y5/+1zTunyp7On/+sfPq7bucNf/stf+s9KB2Hdz3Pf8rY
+ixTveaCgj/7Y/PwB4Hkcmr9jrZ2PjKp75rd7WMeYVaPscIn41uflvlXJO27
hZ0f1+R3c5sfWaCV6peMqz+kYHp3f1g8+LzEP8Opns+BHqmeLcov5/dfcw/e
cq5/lT/5TXHyVfLkD8PJzzrtK7HyOV/6lLn1UWh4u6Z5wdh+x9p9x1M+Xdp9
K9Dere28EYLWg17sfRBtv+Vuf+Be/w0URK58vbr+cgm89dnvwou/SPXvmae/
S5/8Q/3m/9jf/MCRXM9e/qq8+KrYuGEIzqeFV7SVoynuJUN4w1K/lchv2E/+
sv/k903wytKrmcVdDHG9Gc4qQElrJjTdS4d4/pMJ/Q8rjH30+quFg58EBz8J
+ecT3NNx0fmE5GrC8Gr+4BNT84IiuR4RXJK0b5mgs/uf+Ze/yE6/iMDZfsfW
PF+VXDFXtunyC/4Ia3hBSV7SkAQHM4Z73pwCR2L3cnenV/UUyfHi+/+8uvpF
p3y6/PwfW6c/iW/+oXn6H5rtL9ydrzzp8xnpM6rynnb0M//gR/bJT3wwri//
qT/8gbf/nv38D93Fj7L12wXOKYVzPiN8sqh6I1w9XuCcLWlfST/+r9vddzL1
s1Xx+Qz7lMQ8wRKUTYOiqhFZ+8oxUXQzIwVtPRvf/oH39B+G679qlc9XlM+Y
mjum8mZ+69Xy7ttl1TOq7n5edTfPO52SXtKf/aFXXM+1k3Mq0bFDS9Vd0xUI
WhOc2oxiIpFzXST2YA+5THg4s6gZR8639FJrOsbLGnBFFf2ZVBH27T/Pfvt/
7n7+v6/AXr/9n7tP/tCAOXz/fx2C9oEd3HnP2n63evGr9O7v6tu/qfY+rO2/
Xzv/Kn7xd+3t7yrpDe2/AW7+IFG/4bNP6eKrlY1n3Od/P957KxMezzJ0WJph
aPEIyzhGT233zW4N03cIjL1R5uHYwtbIhBS5dkA9+qTUPOMJjxbFR0sbl6z1
syXRwbTsZNbwjC3ZW8TTEXX9hQtSYu1gRk57iOScuvdJYHjPld4uC69XuOeL
2pcCQL/CE7Lylr79Qbj7UXr9u/b4s1x5swZelqEm77+Tf/rfLzZfrY5y2siC
HuEJbeet+OAHydGPkpPP0sMfRPs/8O//uQWG5Ogn4f5nHlhMsJLHX4S3f1Ut
7xI3XjD3v0ie/H1z7Zgie7b45K9b+pdc8SlNfDorPJ6WX9PXjsfnNoepm4MI
VlXLbF79RFYmIiwDHlrYH5/aFJRcF1qKyJrmj9AlE+QVHGVthMrCD022IYh1
w5Od+KnBAUJPY09laXNmalkQUzVy/pNMcUvTvVvZ+SJcf8UW3iyCN938uHb1
Z7Hu7YLuLWv3q2T/q2D7E+fkJ9X1X3Zu/zg8+axW3y4JjieW9Dg4pawem5/d
Ft0/Vys5o3/419nTX/W656yDH0SAw/c+C8//2Nh4zVC/Xtz6wLr5ixLsguhy
Fqyh7jUgopW9j+yzn8Wyq6nlLfTmS+aMondwsWrBgIPPV5URMgrR8cWYmKbJ
jOG1WrK0l3dA2X8rm2AP2QaZFTZkLoroJBqhDdlU2lAQkx42t0oprMkZJY/0
DSGKqwvi0kOyq6L3Xog2nsyCfdG8YWjeL6nfs1TvVgGW/a987ctZ+e3kJmDg
P0u3f+IAxla9YYG52v0kP/6q3PvI4xwSlTeMuz929t8ousark2r8s5vCEJNV
uqfsw/cyIApHXzae/9fu+R+q3a+CrR+5oGiAsvZ/4MiuqSs72K23QLw4iqcz
8mvqtKJ7eLGyDBmZ1e7fPJZJEsGRy3UjEvjK8Zj8ORUooOwZFbDrxvW8YJcq
3mUMT8IDYj0XODTyzHhBeUF1U3VFfQUS3d8/3DdDp6EJmPKaUhsXM9x0z+V7
JVj//U+ryvtp8c2E5G5W+3718Ktw6+2q8tmM5vXC5meu9jPn8C9i9vWE/hN3
9ye58sXa7o+S7Y9scIc7b1mXv2xcftUdvJNvP+dhF1pDsxzjS3zHWAjNDXvr
leD487r6fgXI5caLxaNfxPf/2nr2D7b2JWA/nPo5defdKmef1EzKj6v2jqv2
rcJmLm6SgH8AAsc5Iy6foAU3JM07quyWuLo/uHEztX3PlB3NxeZ6RKV7dw+1
bB7q1AZVR09nXlEhgUSE93Sj8GgGi8HkMtBEZERKABxbvfWMZ7hbOv3KPfmJ
rXo5B5QdSIPhnn3wXqR5sgS2SfFymXMzp3rPYhyOyl4s7QNj8J5/9ruSc0KS
PaHsvmc9+X195zVHdDy9/46/90qwfSvsn6wPTLNtwxUozxdPPshe/rGtefZt
njUvl6//rrr7D/75r8u6l0BbOW/+tUXkt8VUufXN1zG2xnZ+AA6ENb9D4F5N
KF7OLuwjeU8IqjcT2ncU3il6/Ql568XS5pPV7WtBdmkUYrgNPTIokYnLKyti
YuOnqDMard6wpZerpL/97YtCI+ocaOwntKKnWhbX0axtrOLJpORqHDiZ5/9h
2HzN3XzJ0d+x13bGNz8Jtr+I1e/YZ39otn4UgoeXf9Xs/igAZmPnE+v9/7b3
6j8NQAWA+gOAT3/Tbt1x1VerU3xkTnNodlMIYwMLarX9hnP527rsKY19Onb8
ib/zZkVwMnbyRXDzt/XVPRR5vW3GgGBdjAhvJ9lXY8Cgcq4mwSAp7hdXTkZ3
PjP172fkN+Ogg/w9Et8wIdTPTTEwQ/ju2ITwto7WvoH+9s4ONBbD5nJOT48v
Tg/+8suXHYO2ID87NT0mLM6zrC2poC308meJ+sWs4m7m6BcRkObn/9rkHJMF
F5Ob71mADIFJO/wiVb9avfkP/fP/NJz9JgNPKm7nbv+H7tnf1IAzT77ILn/W
XP2iXb9eWjaMAksAzBiW3Ybndoif0DSvWQe/SDXAMHzmzcpQXeSSWkwaRdIl
OCNxz/CgTYvH/fNHiJVr7Mx+38rVqPjFnPTFAvA5QBrW72fUb+aAfItOJ3Q3
y+jphor2tLHZwen5sdKKQkR/b28fYmZuFoVBA4BisXBTsyHjsZdotK6WNitL
85j4kIAoRyobefOLamUbQ9P3A6UGpCd9Pie8prCPSYaXK6dfZMC97L37Zs+A
Cb/8Ta55sXDyiwS4BcO7lZNfxOBoXzMPv8iv/6o/+1WhfLEADOHBVzHww8DI
SW7pu19Fx78rNoHVfMNMqPTPbY+aFPULT6lgzhUvphVvpkX343MniPHN9lFD
O/MKTz/CUPQDiwfja+dTSwcEYK1B9xEzFVTx8JJiPCDOxSfUqaWrobymrBPe
hQLNI+BROOzUHHV6lkKh4AQ8Bpe1XFlelZWRXVCUX1qXqz3hi/amccv1Bx+5
QKOBFZQ+nZFeTW08pW/escdXEVMc1IKc9OFfl9rbb8Ty7A/l7d81n/7PY+0b
huzZxPGv7K1PS8BBAfOpfLMA5m3j5eztf2p2P3FABXQvl4APVD5fVL1YAgki
sdaXoSHoX7JX98d4F2T5q1nWFX7xfHjxEjV12Dtz0r98TVg6xa6ckvjXs6yj
SZCqdt5zgIkVHc1VITKKm5KzyhL8wz2yCzLTslMzstLLK8vqmuv7hwcAhcJ7
2zG4PjQWUV1VVphfAO/splAmxqaw7359qthn9lEq998JtXerBx/EwPwrnyyy
DeQufJl3lE1BXUpiYQjg561bjv52ce/1ivLp3OEnruiCJLkmSm5GaIYuAEr3
bkkG5vzlLP9q9Pg3/s6nFfEl+eJXGbjDwy9isLns80nWPhZ4OcVzuuw5feEA
PX8yvHSFlr6nyj/OMK8xC6eDy2doyTPy8h5u48ki2N+916u6G9q8pH/jkK7Y
XKhoyPD2dwgO8w4I9omIDolNiExJT8jJz6ipL8vOS42OC09Iii0pKy4vL8Vh
0bMzlOnpMRSuW7DBSCwI7h9r2Hwm1lzxnn7d5xsY7eiKwoZknygHiNtD1yA7
z3C7kGSXOe7w7rMV1fkUbwdb3h+EnM/VvqCs34xtPJs4/1UEvL3gkrpxv6B+
vbD3dU3zdh44f/BQ95atecc+/F0uvJtVvqTc/tf6yW8iziUZBCLBHVn5aZ5z
S5K+ovJvyGsX+OVDNAi5iNmSvulq+Qnj+pNCtDOhPVm8uN+4emFgrIznF6ak
psVFxYb4BXqFRvj7B3l6+boEBHtFRgUFhfpFx0YlpSSXlBTBu9qGBno6Ohoa
mkoTM8Kc/CyzqmL1VzKOnlHdWxCV5e8daQ91fxSS4jUyN5xWHG/jYW7j/jgw
3o4w21gGDy7rDWgiRvXTMxcN3YaXc09/l118FkrPKdyTCe2bVcnNlO79vOEj
Y/sLa+18DLFSOX+A035hTe8j2efD2z8uMfcxC9uo+/9p0L1n8C5HAJPo3jAB
cd3+XcfeI7K2x0LznQLTnXvGmjHTHc2DJTQ2Sa5nPb0/GqdgAJDklJjouNCE
5Kj0rGTQyrDIoKAQ/7BwcA2MiokEc5uQGBMbE1FWlJ+ZllhYmBke7Wtua2Tt
8aiyMyci29s9GgLxMUqvCBld7N28k//wr/umwSoTh++hLuYwD/MaeBZ3e5wk
rKscDepfyZpStx995h+85+mv55//rnz1z03JEyrI3QCF7j2dcYBkXeBp+wMd
y7nUA/iIoWH5CElRtdENA7yz8dU9jAzkoJd07Ys5sNogF6ieLYhOqYIjanFf
gmXQA7swy9B035zqlKBYn/zyjJKqvKzclOiYsKTk2PCoYDCZZZVFYRHBkdFh
/oF+oaGhsfFxgcF+IeEBTs529nbWbk72/t4eAGNMbKixlRHMwzQ83cslwiIw
zZ7KQ779++H7fx5f/apXPeP2TjVDfU0sPYzdIm2xi90r26TcwUA4Mxvww/Ip
DljKzXvW+XvB9vMl2dWk6Hpc83pu7+vKzk8r/GejE/o2/Eb9oLSMdtHXJyti
HaP4p3jBCXF1Bys5G5dejCkuiTuv6LLLce4hQXg+BrADJp/SDZSPpEdU+kXn
h0A9LHwjPKKTwwLD/FPSEiMiQ5xd7N09XVzcHINDA8Ijw+IT46JiokNDw719
fXz8Pbz9XO0drF2c7V0dHZzt7UIC/IEmBgR7mMH+5BfjVNOTvagg8HbIV19l
2rsF8QVl55MQxO2u6cpSdFIpOiG7PyShw7NpJp/7jKb/UbD+agXIgfr5wsbT
uY2b6dOfORv3U9JbsvQFZeUMu3A0iJZV19GS+sRlYzvwltVc+cupw1/YQCC4
p2Mv/qkBhm1R16O/nxGdEdefUjlHBBDbVW/ndZ9WBtj1BYMpaXUxMTlB1m6m
1k5mvsGegFJcXZ0tLMygNhBbe5ibhys4Ti6ODk6O4Je7p5ubp4OtsxUACDro
5+UZHRqeFBdfmJsTHhFkCvmurCFDsbvM0U8urA8B+jr5kX/8RQDuZOdHDlnZ
XT+VkgB3yx4KJsg7mMdT0hesjdcc4VOa4QNr/QUdfJvu7eL6/dT2Z8bsVi9I
rBM6uOB+cvkJduYEgdc3U48HqKeDzBuc7BONdoyZ3h2WvpxbPSdQtJ2sExwI
krxjMv+Msn5HP/uzTHY7t3o4sbI7WT+cld8YHZXh/hhqFBzlVV1XmpWdZmcH
MzU3s4RYWUEhVlBLgNHHz9PD08Xbz93F3c7OBeLl7Qq6NtiHyMvKdHNwio2M
iIoMgcJMapoLm/tKukcqVrSjursl6cXU2Vex9p5B0/eU48NiWuyGuTWsk6mF
7Qn1PV/9gqO+Z4KN2/+yBryx6g1T/3FtdhsxpmyV3M+uPZ1k3ZAxyibZp2nG
06EhZTleX98vq1i4xo4YOuYvCDNHWObVCKiA+J4CqqF+uyy/nde/WwMKsvGc
ztzFCS9meEfTc+KBlHJPcycjCwejtNzo/KJvBNLR0VZUUuwX4O/m4e7h5e4f
6AP2Li4+Mi4+PDkttrQiv6W1vrqmLDI0yNPVycfNLT4yMtDXCwI18Q1xMTIz
Km1LufikVVwwZBf053/d3XzB7Z3Oj6mCJdY7D87XCg8Wt55vqK55khO65nae
c4Dd+4G5/cOy8iXgTC5J1drDLubcUWTvFif3kK0reQAXcaeBtNvYI87tERWs
XRIYhyjm6ejcLop7M674QGM/GaUfDC0dETbeLIFXAKlt5QjFOsGAiDSr7KPw
uiZWu5r7c10DTKOT/eISwzy9XMPDQ1PT0zq6Oru6O0vKClPTk4AmxsSG+/i6
JiTH5Bdlo9ADAKObs52TvbW/l3ugj6edjaW1tamDMwTi+Ag92aM4ZLMMM+Nc
NI4x3IFvzG+IKW2JTcrzyiwK5UrnhRsrJNqA9px1+GZt88Ws5m5KdD5i+PZR
3vz0HqJPXDF3ipZ8WJg8GBhU1A6rKqbPOnC6snZOSr+0iH2Gpe/2M/axvCcU
YK0Zx+jp7b7lMyL7giq9XZbeMLgnFMk5Rfecwd0bX1jHrKhI7ZjijNJwV39L
Vx9YWKSfL5hGDzcfP+/c/JzePnhBcU5giK+Ht0toWEBwiJ+Hl2taRnJlVUlE
ZLCTk7Wnm72jHRRiYWxtZWplaQKFmdk4W9a0l6GoiGpEsVeiq0ukh4mzGcTd
2MHXxNbZyMXjYXVdJhLdkleREJrsNMbsOHrPE56McI8A4Y9TNR2zR31IRVXt
QvrkQR9G3QQXFKBVlU0r8T38tAFJNu8VjnOFWzwemt1Gyu7p7Esy4wC3fDIm
u1uRXK7NK6e7RprQU/CZVSyZ3j+7gJ1dIpS1ZNt4mRmZGJlaf+/gBgOq5+bu
BFjUycU+NCKwuq48IzvF08fVydXOP8ALqIO1tbWDg52fvxdYQw9PR2NjowcP
jLw9nL3cnRwdYJlZqVA7q8rGkjkO1SvGzcjC6DsHM2M3qIm76SNHI1t/I5+Y
x/l1wdmVoQGxzkEJnh5RDoVdyZOS3j5mUTU5omoyPJfkX0SNaFrJzCYGVc3F
ta1l9IlyJ/cau7kpjMuu9U8TC7u9Gy+n//2hokz6bIZ1TJRc05Z3KJXIgtTK
hOAkX5cgm4AoJ98gmJevdUCIc3hSkH+sn52Hra0LDOZoY2Flam5hbO9gY2ML
gdlDnN3sgY0B6Fw9HKNjwkFn3d3dfXx8AoN87eytLK0eOzhZBQZ5xcdFenm6
gnCRlZkO9CUmObq8uTSpMKZ5uAEzj5+TzefBc93TbIMKYOktXkw9ii4f6hqp
dIuw803wcgi38ct1TO8Jiu9yioLD4vpdInrs0zA+aRivlCGX0skQorpqTFsl
fYvb/JWycNouOBnZ+7B69Il/9EmoekZX3tAuf1pnqAi2wY+dwyABye4uoRYw
3z/BfIxsvI0g7t+5BDvE5yZ4BntB7CEOro5AGuztbc3MHwOkAKCtA9TL1w18
YWVtBjoLFMTV2cUFIHZzBHQKsCelRkVEB8FsAd1a2tva+fv6+fp6e/q7Wjqa
ZJYnnH/Y3bqXCy8WM/siXQrMfKttAhtgCFZ5L7MMxazPagmH+j22DrRwiIaZ
hT3wKbVN7g8IarT1b7SO73VrW8rMx/lNGBrxshLiRtn2L5TJzbLZw2r9y0XN
3YLqKUN9swh8u+Fu6elPioGpSktvI+Cg5iWkpY1x8cHsJK97+yUfx+hIKIpo
HqjPKk0PjwtLz0kDVhMwTGRkeECQv4OTrbmlibmVsZnlYxs7K1s7KAAIs4E6
OtiBPU1KjQuLCXJ0twV/ag2zgkAg5qZmgf4BkVGhdo4QGxeTmKyAVRVldXu0
n1me0uPtXmbqWGLiXGEei/AqHYvvZZRgV5sqB7I84+xNPB55JrvZx0Kj6wOx
op5OZgWcWdw6nznIKcZJKoRP8Yv73XNbzWPqkomtkv2vAg0II89XgB9j6jCr
eqzqci6tytPczSgyz11zubb3RrykxyhvaUAZu6aKMusjUkpD/aKcvIKdgiL8
fP29YDCYm5ubh5enp7cXsDFAI9w8nUArXd0cwN4FBvglJsQBrSwsyc0pygiL
C7ZztjWzMLW0hNhAYdGRUVHRYXZO5ha2RmHJrsPUmo7JtIxut6AyS7c8U/di
SHJfaCkppYqcilgux7ObMIvNk+zB2NwAS+fHPuGedv6wvN7UsfXBDlpxxWgC
VdUlfkKWP51Cr5bXjsVixeWDwjzB0ynxs1nNW+76sxXhybcPynRPFzzjHz1w
NirsSli/XNp+wwF+BijvILsisdndPw0C8TDyj3GKSg6wsjX5hsXWBgKxBFrv
5eOZlpZSUJRbXVOel59ZW1eWlh6fnpaYnBKfnZMO2BUcoBopqfEpqQkR4aGh
IUGI3u7snDQgFrYuppXNWcT5zt6p7LrRqJAyqE8R1C3XMh+dMK4axAo7Bler
iaI2PKuZsznBUVMTc0Pt3KDuwa42QRZRZb7t48W41SYSr6USFRlbbWsdZQSL
N6qnxC2fD6yeDAlvJrhXwKxuGF7xZOe0eTnSyt/IPNCoe65JcEFfPRhZ3R9c
PhioIsWFlMLsQ743sTMKjvcMifF383axc7AxMX1gYvqdgyM0LNw/LjayvKI4
LTUxLzejrq6oq7u+vau+vqmaSMKDMDhHnVykTY+NDNGmR4eQ7cHBnnX15akZ
iS7uDk4edtYO5l4hsOV1HHuX4F9g5V9q7Zr7uIlawL9emtzAal6zQNbee8+f
lg4s64hToqHAbA9ogLlnqH1gtHMXunxwssY75aF7ilFsHbQU4982F4cR5I9I
i+RPxgUXE8wDivperLvjgfpUIuLMfYzMg/9EVuCBXrCB5Xs9yz3HZCD8Aktg
CaV+bsFQGxez8NjgiKjQkLBAF1dbX3+X1NTo1tbqrs6Wpsbanu4O4ii2r69l
dW0WPza4tDZv2NScHOzv67UKHmdLKdrWCgcQDRWVmYPD8LzCrMDggLDocFt7
a0vYIySpQXW+HFfhHVnuGl3jSlUNr+3TuUcM6ZMF6dMZ4SWFpkOuHY1Oa/ra
5kqia72hXka23kYu4d9FFFoX9vvhReUj6+W9nBQ4K3FQlDUsyr14K+NtTslP
uScfdsS7S5uXPDS13srHyDHWoo1av7Azvrw/StMjhtllobX23rnWxe0p6LGu
mKSQ0KjgrJz07NyM3LwMNLp3YgLX1FRVkJ9VVJhbW1OBQSMxGARhdGB6njxO
HVVr1j+9f/fHz1+vDvZ0ch51fAjeUVlbV9De0VBRXZKQFA/ilRXEzDfAvamr
lDDdm1Mdl1galNccRVjqWFifkJ6uii5pstvZUXnj9FYHTl7VvpzWzc7FKmop
2jasuLRxNqp9NR4hT2vmRhbPe5Yx/ArnfBs5CcOa8rLWmKgs18Sy0N7xpmpE
VvNQbk59kLG7kXs6ZGC5TfZieXEfP789MLbeFlxrG1XvnVQaWliV3tRRExkX
7untkZaeBLYsLS2OzV4YHu7NykxJSY6vrirrhreRSBgOb5FEwVHmxmn06UU6
TSkWLs9Oj2OR3W1VibGBEWFevr6uQE2cnBwsIRaPjb8HEgNK5xfuFhLjm5oX
nVed2NhXnF+fEl3gT1PiZrT9mk/TtJOOZmZc/VIMTldBu+yU/oBnvewf2Slu
FUXXcoLLWb6V7MCylcAuRTpcnovfaUypcM9rCS7sie2aKitDxvpnm/hmP45t
cGidzRXcTtH2B5lnGNYlpowY4VtlEd/ma+Ji5OgFzS3OLK0qqW+sq66uLC7K
AwDRQ93ZGYkR4UHhYUFpqcmNDTV9/fBBVC+OhFpmLy2vLi4y5ulUKrqvd7in
ozQvJTs9prggvay0ID09NSwsDDCVpZUpsAdufs52bjaBYUG+QX4gRIdE+UUk
BzcPVBNZAzhu47AwH68tIO/Xzj/p3f+vFcmPY/PXPQhJVu1SZO1yRD07upYV
Wb8WAxdnoNTlwIgSNLWZLb4VqJjOuQKMoJEoaYHPZ7fNpPWzioBLx603okTV
eGkjRlCb1uPjU2aZ2ByQWBjm5GUTEhkUlxyblJQQFhbi6eESFhqQkRqXlhwT
HRUKAIaHhQBxzM3LbO1onGVMAYAjRFx2VkZaQkJiZHhiVEhxTkpBDiDXyMzU
pPy8nKKioqioCGcXOxcvO/cQJxCooc6QR5bfw5zMwbK7BdnV9ZY0o8txKy1I
Tu64vnztJWrrH0vMZ4Pju0390oLWtaRKenjjSjzWUDl10ja4UQLn58wcdM3u
wZmnSLecx4GV1vHd7tmYwMLRsJgux7BGaArCI3s4MGMgoGA4sgAZW4fLjqv2
jan2rx4qSC+Nc/V1+A5YSpPvzcxMrKwsPNydfbzdgAAmxIZ5ebq4ujgAfXd3
d01IiKuqKS+rLoH3dS6vMtNT0xxgNu5O9g4QC38PpwBvV2BUwTM2UGBXITYw
KwvIw4BIl5iSgMgS7/Bc96z6iOA0aGV3XFKJl1eMZV1vYUFbPHa1SnRD0H1e
pJ0MDIgLq+fCGpfjUOrSAUUBCEed/OwBRQlSUjwkKVs6GVw47J/St+ZjosJb
nIMbbJL6PRP73RP7PNIH/f0rLKManPH8dskpA7vYjaEhhqa6kRPwso4CqBsQ
5UfWThbfmxgB0+LoZOvi6uDm6ujv4w6DmjvYW9tYW4AnU1OTwyJCnV0dXDyd
AkL92jpagSMFrsbJzgbg8vVwcneCge+3sbIEnu3hoz+ZWjyAwB6WNGUAn+mW
DSkaSKSp0KOcJtkldVmPz2uNTCoISyoMGV9r2bil8G/IfbzS2tnownGv5rVY
pLKgnZvaI81rXcvol5V9+7xa3TK60Ty3i6DqO9iXFLykrYdZxjjCcp9OsC7H
JzV9/kXW8dXerbgS3HQPdrIPgeqoaSnPKEj1CXF/aG1kYvedmd1DV18770BX
Tx9n4LStbSwd7G3s7aAgAVmYP3b3cI6JiQIAnVwcvQO8YI7WpuYm5uam1lAr
O2srEJfcnGHgCrKhLRRiZws1tXhkYvUnOw/j/KakwsGsmskK+HxLz0Lz2vns
jAE3LutrI5WFJHmn5IUOT5UpLkh4SW0bMx2vKe8UJLdw45p4cZWMkHZRBnKj
HK1pwGqaQa6f2OqlHQ4TNW3zm5jVQxL/cnJ+Fz27NSR/uYBkNYQWOyaWB4Sn
uWcURVU0FiRmRvmHe8GcLIOivLOrkqt7i3yjnWzcTcxg31vYPDY2ewCzhUCt
LWysQTvMzMwfmZg+NDV7ZG5pYQW1fGz+yNTKGJAkBEBztPf2cgNj7OJo7epk
6+gAamJtaWUCsTM1hhk5B5nltSdMaUYpm8Tq8Xy0sHNyC9m5WtK3VtVLq4lI
880vT+hC5RCY1Z0LWY2MhOa1eIAOrS8Y0uQ3sxMGVaXE3bYBRU23oIyg7cAo
mgiqNgSnfGETxTsjsw9GabpB+g5qYReL5TZHV7pH5LoV1CdEpHrbeptCPR9Z
ej5Mr4qjrOG5m3TeDqMBWZxQEPwIZgSCoa0z1BJqCpoIhMwKYmoFMTYHlG/6
0MLK0t7RAWpjCSYZIHVwsgcTa+9gDbO1cHCwBOEXVMMGZmkKeWRq+wDi8TC1
KnhwvgEj6KyfyRniVUzom4qnfJrXYvqkuUOcyqBEp6yi2K6h8raRPKKyBSEv
aBLEw+WpGF3xxG7D6GYDVl3XL60a3+6mHg52s0vx6y1juo6R9UbeMUl4Rl7Z
wgpOJ8flXfM7GKp2uBiZBPX/PijJ1T0c1jBUNkhrJ/KR46LhGSX+9ItmUTfG
3pnpGCm39n1o5vidqfVDc6gp8CGAKAA6EPqsrE0ALqiNNQhF/50vLKzM/31M
QSmsrB9DbYxt7c2tbcxAjrCyNwY51z0WWo/JGhN3j210Zw0FtM8noaTZVQs+
g5r0uau2cXVzYJJdZKJPdUde90Q1nFU4etCA2i3vVeZ08pKGFfkg5PYI8wfl
VeS9HtoZalTbipLWjKqbJvQthz/xxBeTrB2i7GpedENfOQG+lF44kArxN33k
YISkdB9/2iTJBymb6NUrquAZXf2OzdwjbtwtE1idYTmuVu4PQBOt7EA4MAMh
yAZmbgl5aGrx3be1MjN+ZPxtVk3NQDfNrWFQiK2VhY2Jhc1DmIOptZ0xuJrD
Hpo5PLDxM85rjyXwWpcO8czT0Y7FnJqJyGZ61Oxp08JN1/RpO9XQHZ7pGJ8Z
UNNVWDWU08MtRm1WYrYaeuRFQ6p8wmYx6OPARmGXKLtbnD+61TSy1dAryket
l4wZakRPiOLLsZUt/PrTRe7l9IwBM6lG5/elGrt8/8j+wQgDIzpZpRrQ04cY
1u2U+A1t8YxA0fU2kNPqiZkZzWEByc4ugfZGpn8CuwYaBJpiY2sKCN/Y7DtA
LGAyQSq0sAQjag7m08HVztza2BTyna2LOdA4qIPx95ZGMB/ThLKgkoGE9plc
vLyhX1CFFFW10hLImirW8z6coRyjruhdKYzItotM80gri6kcyulgZSE28uqX
0pCySuJ2LVyQ0ilIHVKXIDfKEOslhK2GblHe6GbdiK5ycrdO8gTDP8MY7hdB
6JM+mQNNXNoZ75qss/Y0t3a1qu8p23oho+1gJ7a6xw1d8LWigpGwlAGviEbb
0EqYTxYkIM3JM8IZ5mYDtYNYWJtbQh9BYI+sbB6aWT78xpyWgHMef1tMqDmY
VTOIiaUdOI8BOz20NLL3sHILtk8oDk9rjIhr9I5ptc/C+rVxChtXsvHyctpe
04A0o4UVWzkT0k5PK4GHOwc+yqpMqhzKbWOm9IhT0fLKqc1ucF24QM6c9A9v
1GO0zaPbneR9OFJWDjwMfr2CutUkf4bnHaOEx2Orm3jBxeTCNlp4RaOtEyEu
xjaOFgHRXgzpxIiotYwUmdbvBfxAeKttYB00tA7mmvHIKx3qmWjrGGzj4GMH
/JWNI5jAh6bQP5lBv7GrqZWJidkj0D4Ly0ff8AIysX5oAntgYvsnYzsjvxjX
2p7iHlJrN7nJN8fBvxQWXAcNarIsno4c220dM9S1M2NzRp1Kp7zLqL597JyC
dn+faPO8mtSs+jiAF68uQQlLaXt9tP1+oq5tWFqLlNbgtO2jm53TJ0iMqp6o
bRxT1y2f9gvPCLIr8qIGpbieY+7jFg9wwqezVAnKPdgG3K2rrxPwuumdvjFt
dqG1dj6l0Nh2j3pKdhe9Mg+R4BwPdYiAAIA2XhZ2nhA7d0sbFxOo02Mrh8fA
DJjZGJtAH8HszS2tHzi4QSCOxlA3U+cgG2tfE9dY20J4BlmA7aO3VmBy0uAR
7nlWPiWQoFpI4Yh3CzOmlBJQPOGXS3Tu4sb1ClMQaxn1+Bi30AdpWZHJOeGj
a60T6rZ+fsnUfhdlpwOtqJk+6J2/HB7RtwBoCFEpSd+KkVaRlI0Eac3KNmrn
3arm2RL/iLx2PkZcb6dvo2VXjKhMH2tHE3CHgQme2V2BQZXA27jWTeQR5b3T
WsyEDJXRHucUbeMSbe8e6WjvZ2Xva2nvbWHnZQ7zMIW5fvOQEGcLayczAA3m
bObsAwXP2/tbuEXagpp4pzoEFbpndkXnIROap4pqxjJDax1Dqx2iW+ziO80q
KN7V9KjaxVjyTu3wem7zchR+vYzIr/GJNY6J90tOD+seK5nW9A5KKvC6umF5
GWajcsTQQNDXAyJFq6rI220A9ZCwZFzVQN6on9ciVc/op18k2nvmpLp3UtvD
Oh2jypER6W7Wzo9snCFgxUDQGObWjSkQk8ohLL9zYKmxe67BK9MBGmTqEG4D
Omjh8tjOx+K/Adp6msFAK90sYO5QmLsVzMXC2hU8aQF1NwZ84hBsYRdm7hJn
5ZpkGVnpEVXtktjqUTQcVktO7GPmD7BzS4ieTYsRpVRgMlNqaTElE8GlkyGl
pJCmsUTfROOYRO/49IC6oXQAkLrfM77bgldXY1XlA7JC4lY9oCO0qpxoqO0X
5mLlJRR9PVVXv/thTf5kRv9qRfNymaofGFf3LB7i+ceU/vFqK5fvrOxNQ1MC
5xS4hS38/CZu5YDcNVceW+sTWOBiE/7YOdrGNtAS5mdp7we18TQF3sbazdja
zRSg+/8BQq1dLWy9IDYelt9Yy8cc5mduF2xuH27mlghxTzEPyIOEVcDy+v1J
sgbaVmcdJaKGGpKBdU5CucYOOKVjfVOHPIPboNGdDkVDwZ7xj0JiXOra8vg7
Uyh2NVZZ08XLHNuqHZDktrGTRzarJw+byfuNsyftIxrgE2pmd5rmt1v552T9
2xWKAjHMqidudGElLcq3S6wDEk0y5BlpYeHw2DHAlszD8E9pVNXwrBaTDY/0
y7Z1SbCyjzS3C7O08HwE9TYDIwrztLB2N/v2YzU3U9DBfzcRAnjY2g1i7wuD
eUFtva1t/WC2fjb2wda2IVYOEZaOMWaeqRbBRdCEZufCwYBSXFAW0j220zqT
4J2AcgnrgQW32QQ3Q71qzIIabZLbPX3SLD2DrTOKIjvGildOCAheHlJRgFUV
D8pyQSTsl+WAhyhVCU5dMSgsoOgaqdqmhc1O1vHo8gGeuTeCF7XiZe0z20OM
Axwwb5ztkZA0GLDWZi6mdUMVc+vErumKkqEE/xyYe4qlS7ylU5SlfYiFQwjE
KcTaztfS1ssSYIR5fPuhs62HFTg2bpYQF0tLFwuYl42Np/W34wOD+drY+cPs
gqD2YVBzHyOH6EdBBbCAIouwasuUTuf4TvvamaSFK0zOeEDGqE/OaFAWNiC+
3yOo0TaowgZUw9HXIj47OLMpop9Z3sPJbl+L6xNlDsnzRoDua8pAE4H8EdSV
hI3KpWPE/HYHc7dH93F19ZQ4t4kmKromdf2yV/Ok9a5JBVx2MZHfGvLI7hvA
iPzQ4fmeSkxGWLmTTyYUFv7ALvyxQ4S5c4SVY5iVrb8FGDyYt7mtj4WdtxU4
ME8ra3cLqNu3A3Gz+NY7b2trDyvQRzt/WwDQIdjW0tfEM9HePcnKLcU0oMQq
rtWplBDeRs8cFNYNSGrbOVmNK4l19NhSclj5dHwOLjy8ztUx1tzexzo2KyKy
yBsk9O6V1A5W7KAsf0heBFYPpSwjbYMoUYmSF5M01dNbTZPK6jldA2BO5hFB
fEen6AdQkmb29QT3epJuGJBdj8HJuQ/svwF0jXDJb8sMLXLxy4G4J1kkVAc0
4YqTqkOAgXSJhNgGfgMI9TYBg+oYAHX0swZLBwCC8w2pJ8BuaedrDXE3h3qA
YYZ+29lgCOBSrxRbp/jH3nmWKXCvInxIw2xi21Jmw1xO/UIWoNDG5ZjaucjG
+YSWlawGenZyd5Brio1nhKtHqLNztFUzORvOTB6SZCD4mcOKYtR6EZhP0D6k
vAgwDGBdgryUKC2d32zmP6FMqHsZh6MkdS9GBkLiEPtiXHQ9wdzqx6/WWXl9
98D2O1B230SPsEK3jH9/esPdmV3VU/h7860jZX7pDm5xMNsgM/tgq28EEgAB
rQQobH2sLF2NHfytYV5mMC8TcCBuD629Htv7m9oGGDuGm7jEm7unmvkWmse0
OnYyMzpWU5qWYuvmo0GOG5LU1C9FdXLiO5gJveysXn5By2JuHirWNcXaLcLB
KdDaNRbaOp47o2tG8lLRshysuhBMKWq9YHC9sF9agBTnkzS1Y8raGW3rzsf5
5eORKV0/Wd0/vYOaP8ayrkZnDEiaDsk5wpBFbb7JtuZuxhBPK7cIp9S6sA5y
8RinR3KygF1qJ/MHKIJhwioirjzAJQZiH27lHG7jEAK1D4RaeX7rFDhWbo+B
PgJ0IHMBdDY+D2z8v7MJ/M4x9qFr8sOAEsvUXo/2xZQefkafNLONEwOiwfzl
4PhWa8taDHm3YlRZNrrxjS0HhJWlown+hfZOEeZOoRaRRR6DC9VYdglOlI+W
ZJMMQArzMKoCcHDqEvJW3Zi2BiMqxgqK1476iPIOoAuThqHZPQxAx7km8S7I
yhfzrCN0FzXXJdbCzPV7MF1RmUFoWgdqoWmUDRcez1KlgzhWu/B4jiIZRjHa
k+tC3RNhwJ9A/M1cImwBh/xbESzBVtoAzvECI2oJ9TG2DTJxjjF3invknPIN
XT01EckvACTfzIquWQps40VWMfxbWIld/HSUOhcpywReiyCvHQLGUt3YPJ+b
0OYNiNQrwSS0wDa1yaOPlkdZrx9RFI1qCoiG4iFFJlKWPijP6OEldbFiR5QF
aHEmRVvG2McuHhII693j2r6FoyGiogkk38VtzNBqWQEixC3ewtz9T6aODyIz
/RmKsWkJin84vbZHxrFaB5l1GzdLJFEPXYXHrnR6pMCcYqD2EdYe8c72YdZQ
X1O7AEsbXzMwqza+gIisIAHG1iEPHWIfu2eZhtbY1k0ltC6l9ImyW9figHNu
58dULvh1CuMQssxhdcGwKgetzJ/bhU9o2+vn4/skRZ2s/BxUUFKDU26nT163
n3fm9/lwv+n11lFZMWEjt2MlEiFMGtUX9UtS+8UpneyYEXU+Vp5FUOQs7WFX
jomLp2OSVwuK1zPzewPLe3iisKOWlBxb5+qZYmUT+NDG09glCDIw2ai4YB5+
kjM28dSNfroBTRK3rx6SqBtDyzsTjcSygBw3O8A5YRBYsKVdKARMrLWfKeim
lZ+5daA5LMLUNu6xW7ZFIty7bSm7lhbfK8hu56QACeviJ/eI0moWQpvXYrul
6eNHtd2S5G5eKlnTMrvTjddVt6wl9UlL+wQltaTwcpRfBTagcMDXPdWokRgr
v8fN7td1rsbUz4cQNEUkQ3mvMBVYccp2LXW3nrJZN781zLmYEN0vGH7isy5x
s3q48IwiuaYVICMjqp0Dsu3sQx87BZoHJbp0EqoAvWier85qh1jHxFndwKi4
Vf2OObmOGBH0LBjG4dON8bWRACPoIxhX4FgAVUIDH0NDH9vGmDomm/iX26QP
+jcupKJVlcBytHGT+hXZKE0xWl08ddyK3igd2ijC71YjNQX9G9m94kzgJ5H8
Iqy+pEOc2rdRCqwmSVmJE+YVolzqxsOiKi2hEUY4QdG4uryJFt61mjCqA8Nc
jpQWgJfCKMrJm01AEHd+YMue0xdPySuX5CldO5pbTlUgdPdrBHFXMTrJI9Ui
MN3BPczCyd9keLr96L2Spv323yjm9EiMoH7pEMs8wRNlnZMqJJbfTdOSBxnd
Wa1JbvH27vH2wAY4RpnBIr93STfxKbIIAFI+4F4zH93KiW8XxCMU6Z3ibz9N
AA/B0o1oa4WviNMn3UPaiiZRSgs/ES5Kb6YnANVuE8Q08qPg8vx+RSlOUTwq
z+9iRBWiXVPb7GNrINWjoRhBIRFI3kHn7GHX9H4nQpCPlBQDB07Za0fJymj6
fvYpibFPnFAjBNej3HPcvHpoUYsncOGL2+M57VFV/em59ZEBibbEJQR7hwr6
NSrvANRE3xkiyFqWTwnM4xHwdwmSng5adQO5YmChIzDbxSnGwjXBwinhkVPm
d55FD6LbYTkEnyp6ePNaTJcoHqXPblgLq18Nb2JFo1TAbpUOSouJ2nqUorxf
WdYoSK3nxA9s5BO0VYD861aDWiUxjdxkuDhnSJaLV+TDV2PrqcFpcNt8pGc3
I50gqxgWFpHUdf2CApSsYkBcgl6vYlwOCN+QqHtddG0v72R0ZqMf+E/2ycjW
O+a8HLGixhPZvQNzLSU9qSHZjo7RD+KrvWckWJqGMCxq7maXr50QBRcTBGnb
wiFuXA2nHaLR0pY2Rmk/q6WHUV+OTPJMM/bIeexTbuxT/X0qygm4fbBuFfRA
QCMYfd6gKhMuSm1dSwAzid4ontyrH9VXAYwgHQxsFLcK0+vX4jolaShdUa88
o4kX1SVLqmVF9sgyBuXZKEXu5FZVGyO6eiIQyc3GyspH1DWDkrwmRkwXK6OX
mzuirp856B7RVGHWS2d2O+bUXbInE3TVAAi83KNv/ySPvYmhCrrn5YQGTFFY
vrtLnAkwMJWoZIZmZHlvQvSKzrmbIEraeMdj8zuYMVU3/Qg1sQlHiqpmDgbJ
hgGCrKuVnJnX61szFVtMDqqghzSxYnCG8vGD+urFoF5ZcqcgumE5rJOXBswV
MMZ4DQg4lSD6YZRlg4pitK6yiZvcwklsEyVVr4T2rKfitgsHVBm9stQOfiLl
oK5PmNHLSelaTiQpywmKslFN7cxR14Ake1Rf0bWWNiguRssrl69R07stJE3l
iLKKd4xhbg8Kz8j6V8xpRTfvgMA/HNHeLtKkKOco4+A8x5yuiPKheLCYE2LE
hKKPc0sd1/VQ1nuI/BY0r3HK0EfStg+JK6b2unsEpV2cUqSguoeRO7fZMbnT
VLMYUbsU1sCKQsiy23lgxpIAQLg4oUMQ3yPKGjHUD2+UUk/aRvSlQ4oc4Crx
+speadaAMhdnKBnS5DZzI5u54R2C6CF11pAyGyFKpezVoyT5OEUpkpfDPO3B
y8sJqhqSoWFYUQgUp20lFeTfUU0DUlQC/AwITQD+9ttFzT19/Y4uOCULj8fF
p2T+yRhDi4ordXeNMU1pDG6dKOEeTkguZvlnM8tH4xhp2/TWIEM/zN4bGZd3
IjkVbQuZbSsZSHlpv6ykeTVjeL1qQtdI1tYCc9K3ntHCjcEYiglblZ2CVED+
bbzouuVg0As4P4u41YjVVAP+HFbmD0gzQOrB6crggpQhdQ5CnlK/HNjBjwLt
7hXF0S4a+K8HcKrCQWFONyttarN5QteAl5YvniCYV8Pd3By8phLUB6usBNyy
dD08sdP6bT6P28Y367X3i4LzqaXtEdnT+RlZ/5IWvbZP7Jgssgo0AvOZ251A
4PYqn63IbxZ5Z3OCp/Osi8lpwyDncIyzPwoGdUzZPrJR28XObOemVsyHY/QV
tKtu4JeG13N65ImNvDC4NLFXnoZQZIENGlDm9G9kdgoT2rjxPeLcYVXFkLIc
oy0H4t4rSWvnJLVzEgYUGRht7th+CZwf1SuKHZAlDitSMcoslCyLdtSEkRaA
sUSJikmqWrSobOV8CLdR07GSObndQj+FE/X1JEMjTlWN09YQDd9KByRj/TlD
fstY3CIQeR2yyxlwxkWdvfSKxDq/4AKnjI7IOTV+ZW+cezbNf0LHS+ELByO0
nW9FoKkHJtY7JS8ow6LittXEFnYcXJLKej80dd4wrMke2SnsUSaAQz6pGFBm
NbCiO0UpuK1S/HYJaBDOUDq210LaaSHtNqPUpX3yzP71DEA73aKUPllKrzRh
fLeoX5rQI4gclCeQ9HmUnTKcIndMU07dbli5GAAGlXdLAAAxUpDc2/r4hShZ
KQBI2WsDp5WVBmLF0EYBaa8Wqy0HKjat6WcfjIpOJ2Y2eteOCSu76M6ZvAx4
YHZvGDAtk/LeKRWCou1fPiOtXowvHOK51xTO2ThZ0UXbHuhcygF62rQSO6jM
nX3SNHZS1adOG9Zl9q7Hd8iiG3jB/cqUYV1ODTMcqcrrEqcgVbngSr/pwupr
J446x/ZbO4UZjWvRSFU26G87L6FbBPobgZQnAYAD0jjURvKgJHHcULR03oaV
5YMRnd3vwCsq8cpq+EoGgp1DWK9BiUuw6xVAMRcue1l3wwBdjzi7W5wG3hG4
vindIG0LAxZw5y1LfD2F4dTAZ3J66EW1E+njSsTSNp5/Mg68HEXfj1O0j+sQ
kwYk/9n0wj4WI2pAC6uZ58MgjmE0RTOXTaP7xaitHPRONkKd1CmJ6hBHNnFC
G9mhrfxoMKLk43r8djlKV4jdLBk7qMdv1hO2GlGaqiF1CfAtgCqHtXlwSXIr
N6ZXkkTaLiRtF/QKYzCq9D5RPFGbT1AVoGV5+PWSHm7muKFxDlgCSTGCl0vZ
bBkSFRLVVSR9Lf28a+KgiXrW2gWcz3oWqGSHMIm2Qxpaa6OrMUefxPPaYQKv
laYdxnKbl84m2FfT/DMq54BM3uinHRBGVL3k7UEEt5ak7cXKW7CKBqyifkBc
NKID0944uls2rMsa0qW1iiMwuznUyxog6ED1GllhjWuRgBiBqKH1xYBwABwg
4kPaqh55MRzEN03R6GElbre4W5HSLU0Bk9AtTu2VpAxuZHQL4pDyZIw6G6PM
GdEWT+03jGorQT2nj9ox6gogMZT9FsCoQ6L8UVX55E4DkBuEJAOMAZiHDmFC
uzi+bi1sXIkCAOXXdJoSiVttmNMMLWxh+1ZrAFvObA8z90ZAE/GizjFN/4ge
MX2M7Rc1DMmb2tmFCHEFcbNlYqcF8Dz1pAmpzMBt53XLY9tFEe2SmHZhLEaV
P7lfCxeldIqSUdoSrAG0r2hYWwC0GzS0b6O4W1bYIy+Ay7LAnbSJY4Cao7eK
lu56e6UZdUthyPVMkCn65akDshS8tgCvLR7RlY/oKkFyB+IyslndLczsFWQC
1aAdtLJvkCRDZTc/6ZtLlyXBFYlweTJCldohj8dJurCiNs3rhUlJi/iMyD0e
GeBU4ZWtU5vdY8rWQXYFQdJMVnbT91E4fVsbrxgpr29nF5fOxDevZRIMDdMn
8JmzDgKInPo8jCG7dtUPTGaXPAF0DVQbSCFyI79/I4ewXYPbrBrSFIBFA3MI
GLVXUdghyoXLcoCRrmeHN3DDQAexOyWAf1o5ibVL4QhZRve/J7ZblEQ+qAGi
A3IHwIVWlw7I89mv0IBA+kSZ0zv1zPMu5kUPcHGdnHjAbz3yhKoV/9q14BZx
dKMg4v8F4JtUzA==
"], {{0, 75.}, {75., 0}}, {0, 255},
ColorFunction->RGBColor],
BoxForm`ImageTag["Byte", ColorSpace -> "RGB", Interleaving -> True],
Selectable->False],
DefaultBaseStyle->"ImageGraphics",
ImageSizeRaw->{75., 75.},
PlotRange->{{0, 75.}, {0, 75.}}]\)]
Out[18]=
In[19]:=
testSet[[2]]
Out[19]=
In[20]:=
trained["TrainedNet"][\!\(\*
GraphicsBox[
TagBox[RasterBox[CompressedData["
1:eJx1nId/3FS6983uZRdYuCy79+4GeNlLJ7DUkBCThJA4pJM4xU6xE/fYjh2X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"], {{0, 75.}, {75., 0}}, {0, 255},
ColorFunction->RGBColor],
BoxForm`ImageTag["Byte", ColorSpace -> "RGB", Interleaving -> True],
Selectable->False],
DefaultBaseStyle->"ImageGraphics",
ImageSizeRaw->{75., 75.},
PlotRange->{{0, 75.}, {0, 75.}}]\)]
Out[20]=

Check unconfirmed observations:

In[21]:=
nymphUnconfirmedImages = Map[Import, Normal[ResourceFunction["INaturalistSearch"][ "Halyomorpha halys", "SimplifiedDataset", "QualityGrade" -> "NeedsID"  , "Page" -> 1,
       MaxItems -> 5][All, "SquareImageURL"]]] // Quiet
Out[21]=
In[22]:=
trained["TrainedNet"][\!\(\*
GraphicsBox[
TagBox[RasterBox[CompressedData["
1:eJxNm3d0FdmW3scza9kee43t8bx5780L9KMDTdPQ5CiCAJHVBJFzzrRoRM5C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"], {{0, 75.}, {75., 0}}, {0, 255},
ColorFunction->RGBColor],
BoxForm`ImageTag["Byte", ColorSpace -> "RGB", Interleaving -> True],
Selectable->False],
DefaultBaseStyle->"ImageGraphics",
ImageSizeRaw->{75., 75.},
PlotRange->{{0, 75.}, {0, 75.}}]\)]
Out[22]=

Get the observation link in order to annotate the "LifeStage" of the specimen and hence contribute to a research-grade observation:

In[23]:=
Normal[ResourceFunction["INaturalistSearch"][ "Halyomorpha halys", "SimplifiedDataset", "QualityGrade" -> "NeedsID"  , "Page" -> 1, MaxItems -> 1][All, "ObservationURL"]] // Quiet
Out[23]=

Version History

  • 1.1.0 – 13 June 2022
  • 1.0.0 – 17 August 2020

Related Resources

License Information