From 0313023bf32122ee7ece94d4b08b83f8769a2792 Mon Sep 17 00:00:00 2001
From: Nils Lehmann <35272119+nilsleh@users.noreply.github.com>
Date: Wed, 19 Apr 2023 17:07:48 +0200
Subject: [PATCH] Add Western USA Live Fuel Moisture Dataset (#1262)
* basic working version
* format data.py
* add test for features variables
* pyupgrade
* add docs
* additional doc
* forgot pdb
* requested changes
* ignore pd return type
* fill coverage gap
* split dataset name for docs
* Add missing column
* Fix error list
---------
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
---
docs/api/datasets.rst | 5 +
docs/api/non_geo_datasets.csv | 1 +
.../western_usa_live_fuel_moisture/data.py | 223 +++++++++++
.../su_sar_moisture_content.tar.gz | Bin 0 -> 2152 bytes
.../su_sar_moisture_content_0/labels.geojson | 1 +
.../su_sar_moisture_content_0/stac.json | 1 +
.../su_sar_moisture_content_1/labels.geojson | 1 +
.../su_sar_moisture_content_1/stac.json | 1 +
.../su_sar_moisture_content_2/labels.geojson | 1 +
.../su_sar_moisture_content_2/stac.json | 1 +
.../test_western_usa_live_fuel_moisture.py | 100 +++++
torchgeo/datasets/__init__.py | 2 +
.../western_usa_live_fuel_moisture.py | 354 ++++++++++++++++++
13 files changed, 691 insertions(+)
create mode 100644 tests/data/western_usa_live_fuel_moisture/data.py
create mode 100644 tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content.tar.gz
create mode 100644 tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_0/labels.geojson
create mode 100644 tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_0/stac.json
create mode 100644 tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_1/labels.geojson
create mode 100644 tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_1/stac.json
create mode 100644 tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_2/labels.geojson
create mode 100644 tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_2/stac.json
create mode 100644 tests/datasets/test_western_usa_live_fuel_moisture.py
create mode 100644 torchgeo/datasets/western_usa_live_fuel_moisture.py
diff --git a/docs/api/datasets.rst b/docs/api/datasets.rst
index 775bbc2cd4e..de65151f74e 100644
--- a/docs/api/datasets.rst
+++ b/docs/api/datasets.rst
@@ -344,6 +344,11 @@ VHR-10
.. autoclass:: VHR10
+Western USA Live Fuel Moisture
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. autoclass:: WesternUSALiveFuelMoisture
+
xView2
^^^^^^
diff --git a/docs/api/non_geo_datasets.csv b/docs/api/non_geo_datasets.csv
index f73f0547165..1f6ed308256 100644
--- a/docs/api/non_geo_datasets.csv
+++ b/docs/api/non_geo_datasets.csv
@@ -34,5 +34,6 @@ Dataset,Task,Source,# Samples,# Classes,Size (px),Resolution (m),Bands
`USAVars`_,R,NAIP Aerial,100K,-,-,4,"RGB, NIR"
`Vaihingen`_,S,Aerial,33,6,"1,281--3,816",0.09,RGB
`VHR-10`_,I,"Google Earth, Vaihingen",800,10,"358--1,728",0.08--2,RGB
+`Western USA Live Fuel Moisture`_,R,"Landsat8, Sentinel-1",2615,-,-,-,-
`xView2`_,CD,Maxar,"3,732",4,"1,024x1,024",0.8,RGB
`ZueriCrop`_,"I, T",Sentinel-2,116K,48,24x24,10,MSI
diff --git a/tests/data/western_usa_live_fuel_moisture/data.py b/tests/data/western_usa_live_fuel_moisture/data.py
new file mode 100644
index 00000000000..d64c445ed41
--- /dev/null
+++ b/tests/data/western_usa_live_fuel_moisture/data.py
@@ -0,0 +1,223 @@
+#!/usr/bin/env python3
+
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+import hashlib
+import json
+import os
+import shutil
+
+NUM_SAMPLES = 3
+
+
+data_dir = "su_sar_moisture_content"
+
+LABELS = {
+ "type": "Feature",
+ "properties": {
+ "percent(t)": 132.6666667,
+ "site": "Blackstone",
+ "date": "6/30/15",
+ "slope(t)": 0.599961042,
+ "elevation(t)": 1522.0,
+ "canopy_height(t)": 0.0,
+ "forest_cover(t)": 130.0,
+ "silt(t)": 36.0,
+ "sand(t)": 38.0,
+ "clay(t)": 26.0,
+ "vv(t)": -12.80108143,
+ "vh(t)": -20.86413967,
+ "red(t)": 2007.5,
+ "green(t)": 1669.5,
+ "blue(t)": 1234.5,
+ "swir(t)": 3226.5,
+ "nir(t)": 2764.5,
+ "ndvi(t)": 0.158611467,
+ "ndwi(t)": -0.07713057,
+ "nirv(t)": 438.5596345,
+ "vv_red(t)": -0.006376628,
+ "vv_green(t)": -0.007667614,
+ "vv_blue(t)": -0.010369446,
+ "vv_swir(t)": -0.003967482,
+ "vv_nir(t)": -0.004630523,
+ "vv_ndvi(t)": -80.70716267,
+ "vv_ndwi(t)": 165.9663796,
+ "vv_nirv(t)": -0.029188919,
+ "vh_red(t)": -0.010393096,
+ "vh_green(t)": -0.012497238,
+ "vh_blue(t)": -0.016900883,
+ "vh_swir(t)": -0.006466493,
+ "vh_nir(t)": -0.007547166,
+ "vh_ndvi(t)": -131.5424422,
+ "vh_ndwi(t)": 270.5041557,
+ "vh_nirv(t)": -0.047574236,
+ "vh_vv(t)": -8.063058239,
+ "slope(t-1)": 0.599961042,
+ "elevation(t-1)": 1522.0,
+ "canopy_height(t-1)": 0.0,
+ "forest_cover(t-1)": 130.0,
+ "silt(t-1)": 36.0,
+ "sand(t-1)": 38.0,
+ "clay(t-1)": 26.0,
+ "vv(t-1)": -12.93716855,
+ "vh(t-1)": -20.92368901,
+ "red(t-1)": 1792.0,
+ "green(t-1)": 1490.0,
+ "blue(t-1)": 1102.5,
+ "swir(t-1)": 3047.0,
+ "nir(t-1)": 2574.0,
+ "ndvi(t-1)": 0.179116009,
+ "ndwi(t-1)": -0.084146807,
+ "nirv(t-1)": 461.0691997,
+ "vv_red(t-1)": -0.007219402,
+ "vv_green(t-1)": -0.008682663,
+ "vv_blue(t-1)": -0.011734393,
+ "vv_swir(t-1)": -0.004245871,
+ "vv_nir(t-1)": -0.005026095,
+ "vv_ndvi(t-1)": -72.22787422,
+ "vv_ndwi(t-1)": 153.7452097,
+ "vv_nirv(t-1)": -0.02805906,
+ "vh_red(t-1)": -0.011676166,
+ "vh_green(t-1)": -0.014042744,
+ "vh_blue(t-1)": -0.018978403,
+ "vh_swir(t-1)": -0.00686698,
+ "vh_nir(t-1)": -0.008128861,
+ "vh_ndvi(t-1)": -116.8164094,
+ "vh_ndwi(t-1)": 248.6569562,
+ "vh_nirv(t-1)": -0.0453808,
+ "vh_vv(t-1)": -7.986520458,
+ "slope(t-2)": 0.599961042,
+ "elevation(t-2)": 1522.0,
+ "canopy_height(t-2)": 0.0,
+ "forest_cover(t-2)": 130.0,
+ "silt(t-2)": 36.0,
+ "sand(t-2)": 38.0,
+ "clay(t-2)": 26.0,
+ "vv(t-2)": -13.07325567,
+ "vh(t-2)": -20.98323835,
+ "red(t-2)": 1721.5,
+ "green(t-2)": 1432.0,
+ "blue(t-2)": 1056.5,
+ "swir(t-2)": 2950.0,
+ "nir(t-2)": 2476.0,
+ "ndvi(t-2)": 0.179768568,
+ "ndwi(t-2)": -0.087357002,
+ "nirv(t-2)": 445.0984812,
+ "vv_red(t-2)": -0.007594107,
+ "vv_green(t-2)": -0.009129368,
+ "vv_blue(t-2)": -0.012374118,
+ "vv_swir(t-2)": -0.004431612,
+ "vv_nir(t-2)": -0.00527999,
+ "vv_ndvi(t-2)": -72.72270011,
+ "vv_ndwi(t-2)": 149.6532084,
+ "vv_nirv(t-2)": -0.029371603,
+ "vh_red(t-2)": -0.012188927,
+ "vh_green(t-2)": -0.014653099,
+ "vh_blue(t-2)": -0.019861087,
+ "vh_swir(t-2)": -0.007112962,
+ "vh_nir(t-2)": -0.008474652,
+ "vh_ndvi(t-2)": -116.7236217,
+ "vh_ndwi(t-2)": 240.2009889,
+ "vh_nirv(t-2)": -0.047142912,
+ "vh_vv(t-2)": -7.909982677,
+ "slope(t-3)": 0.599961042,
+ "elevation(t-3)": 1522.0,
+ "canopy_height(t-3)": 0.0,
+ "forest_cover(t-3)": 130.0,
+ "silt(t-3)": 36.0,
+ "sand(t-3)": 38.0,
+ "clay(t-3)": 26.0,
+ "vv(t-3)": -12.35794964,
+ "vh(t-3)": -20.25746909,
+ "red(t-3)": 1367.333333,
+ "green(t-3)": 1151.0,
+ "blue(t-3)": 827.3333333,
+ "swir(t-3)": 2349.333333,
+ "nir(t-3)": 2051.0,
+ "ndvi(t-3)": 0.216978329,
+ "ndwi(t-3)": -0.050717071,
+ "nirv(t-3)": 413.3885932,
+ "vv_red(t-3)": -0.009037993,
+ "vv_green(t-3)": -0.010736707,
+ "vv_blue(t-3)": -0.014937087,
+ "vv_swir(t-3)": -0.005260194,
+ "vv_nir(t-3)": -0.006025329,
+ "vv_ndvi(t-3)": -56.95476465,
+ "vv_ndwi(t-3)": 243.6644995,
+ "vv_nirv(t-3)": -0.029894269,
+ "vh_red(t-3)": -0.014815311,
+ "vh_green(t-3)": -0.017599886,
+ "vh_blue(t-3)": -0.024485257,
+ "vh_swir(t-3)": -0.008622646,
+ "vh_nir(t-3)": -0.009876874,
+ "vh_ndvi(t-3)": -93.36171601,
+ "vh_ndwi(t-3)": 399.4211186,
+ "vh_nirv(t-3)": -0.049003454,
+ "vh_vv(t-3)": -7.899519455,
+ },
+ "geometry": {"type": "Point", "coordinates": [-115.8855556, 42.44111111]},
+}
+
+STAC = {
+ "assets": {
+ "documentation": {
+ "href": "../_common/documentation.pdf",
+ "type": "application/pdf",
+ },
+ "labels": {"href": "labels.geojson", "type": "application/geo+json"},
+ "training_features_descriptions": {
+ "href": "../_common/training_features_descriptions.csv",
+ "title": "Training Features Descriptions",
+ "type": "text/csv",
+ },
+ },
+ "bbox": [-115.8855556, 42.44111111, -115.8855556, 42.44111111],
+ "collection": "su_sar_moisture_content",
+ "geometry": {"coordinates": [-115.8855556, 42.44111111], "type": "Point"},
+ "id": "su_sar_moisture_content_0001",
+ "links": [
+ {"href": "../collection.json", "rel": "collection"},
+ {"href": "../collection.json", "rel": "parent"},
+ ],
+ "properties": {
+ "datetime": "2015-06-30T00:00:00Z",
+ "label:description": "",
+ "label:properties": ["percent(t)"],
+ "label:type": "vector",
+ },
+ "stac_extensions": ["label"],
+ "stac_version": "1.0.0-beta.2",
+ "type": "Feature",
+}
+
+
+def create_file(path: str) -> None:
+ label_path = os.path.join(path, "labels.geojson")
+ with open(label_path, "w") as f:
+ json.dump(LABELS, f)
+
+ stac_path = os.path.join(path, "stac.json")
+ with open(stac_path, "w") as f:
+ json.dump(STAC, f)
+
+
+if __name__ == "__main__":
+ # Remove old data
+ if os.path.isdir(data_dir):
+ shutil.rmtree(data_dir)
+
+ os.makedirs(os.path.join(os.getcwd(), data_dir))
+
+ for i in range(NUM_SAMPLES):
+ sample_dir = os.path.join(data_dir, data_dir + f"_{i}")
+ os.makedirs(sample_dir)
+ create_file(sample_dir)
+
+ # Compress data
+ shutil.make_archive(data_dir, "gztar", ".", data_dir)
+
+ # Compute checksums
+ with open(data_dir + ".tar.gz", "rb") as f:
+ md5 = hashlib.md5(f.read()).hexdigest()
+ print(f"{data_dir}.tar.gz: {md5}")
diff --git a/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content.tar.gz b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fe38d993d677c7f7e38e9b8f8699f9cc591284b1
GIT binary patch
literal 2152
zcma)-X*kr67ROOEmTJn#s407lVv;37METpZw;1MXq^1~};ZKR7EM<#OVi?&Oq@wKe
z@2L#NzL$o^h_a2fG3)R0;=aB2p65KD7w7wY&zp0ea}<+6pf1mIeqsPV6ovQ2p#p<2
z_>fTC4HP;E8*&31q7&ka6Isfk2Qdu~{<HpoaPdc(NnLs;gDtiPmN?x{J-1Pj6vr6<
zmQs@%U}M*mqyj`FC_b|(`+KPHW^uFL6{V}G7jPY%y?=GP({6J}tT9Cjd2FJonM(mB
z;pR2amc10--@VbFMmDKr=?*LNDifG+o(8EMV_V@-K<*uyww}YA#5<+Mo<M^NXR(BE
zWpe==N(tgJUXd^7Mw$#S)$+-lGu9l^cg=i&m_6r;Q_TW{&M{pT@S)W@orH-+F1}BY
zFAUO>`$9+rsH-SUGLSP3$isk3b+5<Q`c{F2Y4c$8?j02Zz=attHCq&~snO;(t}_c5
zV@<qRdtGlT2kedK6>TBvEregyIe;Y-KqN7SUiq{%`tU#a@bY{fM7A1*@T};29qC2W
zFT{myA6tRB6$Bq4@BCXyg0z^c+`{j{wsI;I{{)5;np3Oq!^fYUm>Oo)(#Cg@Gx1LN
z<Dzn#HBrd@J#CKk6VZvjJb(J~ev)Tc=sE)nMQtRqc{R&>LOQ5TN6H`uk?-s;NgX{h
zx@2fDKK>gkfE!vom|oQtvg568tbTukl$v_*A}7Yf(_RNz`=0C;7VYB&58(8VY#QOK
zy>B(s&D89TK?*rsQm+1GQKPp(x2cCtojo^<Rm>f5uBn<u#=A@`^;HNYmh>fhJdXcK
z^G6JrmJkoQisyO`T@V~`kS;P9FYoe)WtN}Lp_LQMmP3h>OU1)3XC}at>-H+z7red7
z(|k%T)JFV9Qf_4V#@_+?i_>o@j8)<eYs_y9GnwDjjj+{Bod8G7QKv!4L#Sqx_o<IU
zBw|y#R2S;d-QODM)KQEnP;B2cc(zFGTUtA<iuv%e-NQ_gB5d708LnvtGA=U7%zxCj
zD0z2!6A^jPdlXSD&hU@MZe5Kn<U%emX??nOEIFkw@5M@nGe1FcPZO^{+S4V8)Fiu$
zX~Dtpg!XIHt;g<%=?z8;bx$fhnv5zMA}S8(eU_=x*G6`%_?dhVtqBN_K4PFFvhPcy
zf45_JNhibEQza~0(lPd8)-a5{E3*G(@*9o;A=$XIpx~sNSD@%o)470A95xo>G*f(o
zRd^YGC%pYysk@9mUaL$Sv)5guJ!d9eHK^$6W2ybfe-)WEzKJoWWunho>5yLUKim|n
z<7Q8Mn|_+AGj#1{m7jR{OS5m+mFgAlaa3@%P$>S7br`ehEz*A0&k40AhB;AP=XMw;
zoK4kTt?lmRr$}EhCf|J$ys0O~FpUX*Zee7r#FvO!AzFkxDZykxa3uyt*`fl9WgU;x
z=$Dd7vUJ?tJ}{85j@GWX6E%)`lMc_5h0gte&_Kz7gTIIt*&u!Bk-9v|*e4dMnZBYW
zbuQ=CODeP99n4eG0Ke^6RJ&QK7VK%V&*_#I7_@GyoILaW(C%KA9lT+dgLwg$gKor$
zSwKbgZInuzTSQK2ldZ}i(V}G{;909aYF~PWD%yBU_JD)!kE-Y62KXAK;L$=abPZZc
z>|N+ggR6p8+@Rf~NUInn2hg-HSvL;>cEJ9l)tv)#YO>gFk!Ei?tNaLT4H^K;<hT2Q
z6W76s@4$%};KZqDXVZk8gjs2}qrrJ!ZOeXwUO|;N5@e4nV;`PMsc}?)=%;2aciB`!
zSN|GRQC=_guA!KBz+m0Whb2*i!jer9hbJ-;@r&*d<{!-sDN;+1gM?gZdseNdvCApA
z|1aol2=k*SR5s(xqtVokS<j0a)?&|cog5NnOj7bs;*Z}f@h>P;*UNNCx=ZtwN>Iqx
zDo8$|Djr3*`CYopK+n(;leatXW+5k5`xu${!nyahj58=&r+^sod{E0-JyV6IxI#NW
z59<oZ(w1;jmDVg8We9IAGeL-g<YS9S^%(T{ka(sWH9JC=U!JCrsd65(Gxx0fYd+Ul
ztc6!R$T@lH{w@~V(PS%#(i1fmn0v@vO2D4+l7UoOlFonhRd?U|tvEv;lJ)NB7a-`s
zpa9WHZUrv-7>?M#jzZx8nw-#Q61aZQmQ9gw0=(IgW}lNLm!j5#pEkqZ{_4k#jj#k)
zeLU<#VtBmB=99-N_f4>cj}`m)n~d5!hUe=yv`Dbe=1>Sdi(q9mB3en2x<5thug-ms
zF|V4WM$AXmSMwalVEiIMMQ1*N{B7f@?~4C;+yKGmDXNUNBIHgyNDIif65PGQ9V78)
zut99azEVRJiqw1GGQMtNB)4upNp?{?Rkm7w&f{wf+I4pBdq7`u{Th-h8s^Az`_+17
z@?P6WLyULpdRO;B*i0Pa=xE*t)^GYc#ca!5eQUkbTmq_v&2BrexTk$GmSC=9y(c0g
zu!<1w2{CKy0diKc_x+Lie-VGQNiS@lEUB<YEN{j)i1~?8U+^WU{oLM!DL1+1#_EJn
z@kUZI!Q)=_OYNV8Ou$8e_(?$Y09z&V6txk83%_jZ(kf{t^a~(8LXhMNDcx-I?Xp1r
ze<5<&l1&K#?03Lh<4tYb2L!CRWkQ88X`WKP15Kca|8&i~3+SCA1Xpko7dKHmf6R@q
zanE}du-rsFYXcDLf=inycVJul?;th*XBFr`8(+xYwub-_uXw0Rppc8G1h}pX6r2Aq
Rgi&iJ{4QW@MG8bj{tcRvTG;>q
literal 0
HcmV?d00001
diff --git a/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_0/labels.geojson b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_0/labels.geojson
new file mode 100644
index 00000000000..9492503feae
--- /dev/null
+++ b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_0/labels.geojson
@@ -0,0 +1 @@
+{"type": "Feature", "properties": {"percent(t)": 132.6666667, "site": "Blackstone", "date": "6/30/15", "slope(t)": 0.599961042, "elevation(t)": 1522.0, "canopy_height(t)": 0.0, "forest_cover(t)": 130.0, "silt(t)": 36.0, "sand(t)": 38.0, "clay(t)": 26.0, "vv(t)": -12.80108143, "vh(t)": -20.86413967, "red(t)": 2007.5, "green(t)": 1669.5, "blue(t)": 1234.5, "swir(t)": 3226.5, "nir(t)": 2764.5, "ndvi(t)": 0.158611467, "ndwi(t)": -0.07713057, "nirv(t)": 438.5596345, "vv_red(t)": -0.006376628, "vv_green(t)": -0.007667614, "vv_blue(t)": -0.010369446, "vv_swir(t)": -0.003967482, "vv_nir(t)": -0.004630523, "vv_ndvi(t)": -80.70716267, "vv_ndwi(t)": 165.9663796, "vv_nirv(t)": -0.029188919, "vh_red(t)": -0.010393096, "vh_green(t)": -0.012497238, "vh_blue(t)": -0.016900883, "vh_swir(t)": -0.006466493, "vh_nir(t)": -0.007547166, "vh_ndvi(t)": -131.5424422, "vh_ndwi(t)": 270.5041557, "vh_nirv(t)": -0.047574236, "vh_vv(t)": -8.063058239, "slope(t-1)": 0.599961042, "elevation(t-1)": 1522.0, "canopy_height(t-1)": 0.0, "forest_cover(t-1)": 130.0, "silt(t-1)": 36.0, "sand(t-1)": 38.0, "clay(t-1)": 26.0, "vv(t-1)": -12.93716855, "vh(t-1)": -20.92368901, "red(t-1)": 1792.0, "green(t-1)": 1490.0, "blue(t-1)": 1102.5, "swir(t-1)": 3047.0, "nir(t-1)": 2574.0, "ndvi(t-1)": 0.179116009, "ndwi(t-1)": -0.084146807, "nirv(t-1)": 461.0691997, "vv_red(t-1)": -0.007219402, "vv_green(t-1)": -0.008682663, "vv_blue(t-1)": -0.011734393, "vv_swir(t-1)": -0.004245871, "vv_nir(t-1)": -0.005026095, "vv_ndvi(t-1)": -72.22787422, "vv_ndwi(t-1)": 153.7452097, "vv_nirv(t-1)": -0.02805906, "vh_red(t-1)": -0.011676166, "vh_green(t-1)": -0.014042744, "vh_blue(t-1)": -0.018978403, "vh_swir(t-1)": -0.00686698, "vh_nir(t-1)": -0.008128861, "vh_ndvi(t-1)": -116.8164094, "vh_ndwi(t-1)": 248.6569562, "vh_nirv(t-1)": -0.0453808, "vh_vv(t-1)": -7.986520458, "slope(t-2)": 0.599961042, "elevation(t-2)": 1522.0, "canopy_height(t-2)": 0.0, "forest_cover(t-2)": 130.0, "silt(t-2)": 36.0, "sand(t-2)": 38.0, "clay(t-2)": 26.0, "vv(t-2)": -13.07325567, "vh(t-2)": -20.98323835, "red(t-2)": 1721.5, "green(t-2)": 1432.0, "blue(t-2)": 1056.5, "swir(t-2)": 2950.0, "nir(t-2)": 2476.0, "ndvi(t-2)": 0.179768568, "ndwi(t-2)": -0.087357002, "nirv(t-2)": 445.0984812, "vv_red(t-2)": -0.007594107, "vv_green(t-2)": -0.009129368, "vv_blue(t-2)": -0.012374118, "vv_swir(t-2)": -0.004431612, "vv_nir(t-2)": -0.00527999, "vv_ndvi(t-2)": -72.72270011, "vv_ndwi(t-2)": 149.6532084, "vv_nirv(t-2)": -0.029371603, "vh_red(t-2)": -0.012188927, "vh_green(t-2)": -0.014653099, "vh_blue(t-2)": -0.019861087, "vh_swir(t-2)": -0.007112962, "vh_nir(t-2)": -0.008474652, "vh_ndvi(t-2)": -116.7236217, "vh_ndwi(t-2)": 240.2009889, "vh_nirv(t-2)": -0.047142912, "vh_vv(t-2)": -7.909982677, "slope(t-3)": 0.599961042, "elevation(t-3)": 1522.0, "canopy_height(t-3)": 0.0, "forest_cover(t-3)": 130.0, "silt(t-3)": 36.0, "sand(t-3)": 38.0, "clay(t-3)": 26.0, "vv(t-3)": -12.35794964, "vh(t-3)": -20.25746909, "red(t-3)": 1367.333333, "green(t-3)": 1151.0, "blue(t-3)": 827.3333333, "swir(t-3)": 2349.333333, "nir(t-3)": 2051.0, "ndvi(t-3)": 0.216978329, "ndwi(t-3)": -0.050717071, "nirv(t-3)": 413.3885932, "vv_red(t-3)": -0.009037993, "vv_green(t-3)": -0.010736707, "vv_blue(t-3)": -0.014937087, "vv_swir(t-3)": -0.005260194, "vv_nir(t-3)": -0.006025329, "vv_ndvi(t-3)": -56.95476465, "vv_ndwi(t-3)": 243.6644995, "vv_nirv(t-3)": -0.029894269, "vh_red(t-3)": -0.014815311, "vh_green(t-3)": -0.017599886, "vh_blue(t-3)": -0.024485257, "vh_swir(t-3)": -0.008622646, "vh_nir(t-3)": -0.009876874, "vh_ndvi(t-3)": -93.36171601, "vh_ndwi(t-3)": 399.4211186, "vh_nirv(t-3)": -0.049003454, "vh_vv(t-3)": -7.899519455}, "geometry": {"type": "Point", "coordinates": [-115.8855556, 42.44111111]}}
\ No newline at end of file
diff --git a/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_0/stac.json b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_0/stac.json
new file mode 100644
index 00000000000..469f98574d9
--- /dev/null
+++ b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_0/stac.json
@@ -0,0 +1 @@
+{"assets": {"documentation": {"href": "../_common/documentation.pdf", "type": "application/pdf"}, "labels": {"href": "labels.geojson", "type": "application/geo+json"}, "training_features_descriptions": {"href": "../_common/training_features_descriptions.csv", "title": "Training Features Descriptions", "type": "text/csv"}}, "bbox": [-115.8855556, 42.44111111, -115.8855556, 42.44111111], "collection": "su_sar_moisture_content", "geometry": {"coordinates": [-115.8855556, 42.44111111], "type": "Point"}, "id": "su_sar_moisture_content_0001", "links": [{"href": "../collection.json", "rel": "collection"}, {"href": "../collection.json", "rel": "parent"}], "properties": {"datetime": "2015-06-30T00:00:00Z", "label:description": "", "label:properties": ["percent(t)"], "label:type": "vector"}, "stac_extensions": ["label"], "stac_version": "1.0.0-beta.2", "type": "Feature"}
\ No newline at end of file
diff --git a/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_1/labels.geojson b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_1/labels.geojson
new file mode 100644
index 00000000000..9492503feae
--- /dev/null
+++ b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_1/labels.geojson
@@ -0,0 +1 @@
+{"type": "Feature", "properties": {"percent(t)": 132.6666667, "site": "Blackstone", "date": "6/30/15", "slope(t)": 0.599961042, "elevation(t)": 1522.0, "canopy_height(t)": 0.0, "forest_cover(t)": 130.0, "silt(t)": 36.0, "sand(t)": 38.0, "clay(t)": 26.0, "vv(t)": -12.80108143, "vh(t)": -20.86413967, "red(t)": 2007.5, "green(t)": 1669.5, "blue(t)": 1234.5, "swir(t)": 3226.5, "nir(t)": 2764.5, "ndvi(t)": 0.158611467, "ndwi(t)": -0.07713057, "nirv(t)": 438.5596345, "vv_red(t)": -0.006376628, "vv_green(t)": -0.007667614, "vv_blue(t)": -0.010369446, "vv_swir(t)": -0.003967482, "vv_nir(t)": -0.004630523, "vv_ndvi(t)": -80.70716267, "vv_ndwi(t)": 165.9663796, "vv_nirv(t)": -0.029188919, "vh_red(t)": -0.010393096, "vh_green(t)": -0.012497238, "vh_blue(t)": -0.016900883, "vh_swir(t)": -0.006466493, "vh_nir(t)": -0.007547166, "vh_ndvi(t)": -131.5424422, "vh_ndwi(t)": 270.5041557, "vh_nirv(t)": -0.047574236, "vh_vv(t)": -8.063058239, "slope(t-1)": 0.599961042, "elevation(t-1)": 1522.0, "canopy_height(t-1)": 0.0, "forest_cover(t-1)": 130.0, "silt(t-1)": 36.0, "sand(t-1)": 38.0, "clay(t-1)": 26.0, "vv(t-1)": -12.93716855, "vh(t-1)": -20.92368901, "red(t-1)": 1792.0, "green(t-1)": 1490.0, "blue(t-1)": 1102.5, "swir(t-1)": 3047.0, "nir(t-1)": 2574.0, "ndvi(t-1)": 0.179116009, "ndwi(t-1)": -0.084146807, "nirv(t-1)": 461.0691997, "vv_red(t-1)": -0.007219402, "vv_green(t-1)": -0.008682663, "vv_blue(t-1)": -0.011734393, "vv_swir(t-1)": -0.004245871, "vv_nir(t-1)": -0.005026095, "vv_ndvi(t-1)": -72.22787422, "vv_ndwi(t-1)": 153.7452097, "vv_nirv(t-1)": -0.02805906, "vh_red(t-1)": -0.011676166, "vh_green(t-1)": -0.014042744, "vh_blue(t-1)": -0.018978403, "vh_swir(t-1)": -0.00686698, "vh_nir(t-1)": -0.008128861, "vh_ndvi(t-1)": -116.8164094, "vh_ndwi(t-1)": 248.6569562, "vh_nirv(t-1)": -0.0453808, "vh_vv(t-1)": -7.986520458, "slope(t-2)": 0.599961042, "elevation(t-2)": 1522.0, "canopy_height(t-2)": 0.0, "forest_cover(t-2)": 130.0, "silt(t-2)": 36.0, "sand(t-2)": 38.0, "clay(t-2)": 26.0, "vv(t-2)": -13.07325567, "vh(t-2)": -20.98323835, "red(t-2)": 1721.5, "green(t-2)": 1432.0, "blue(t-2)": 1056.5, "swir(t-2)": 2950.0, "nir(t-2)": 2476.0, "ndvi(t-2)": 0.179768568, "ndwi(t-2)": -0.087357002, "nirv(t-2)": 445.0984812, "vv_red(t-2)": -0.007594107, "vv_green(t-2)": -0.009129368, "vv_blue(t-2)": -0.012374118, "vv_swir(t-2)": -0.004431612, "vv_nir(t-2)": -0.00527999, "vv_ndvi(t-2)": -72.72270011, "vv_ndwi(t-2)": 149.6532084, "vv_nirv(t-2)": -0.029371603, "vh_red(t-2)": -0.012188927, "vh_green(t-2)": -0.014653099, "vh_blue(t-2)": -0.019861087, "vh_swir(t-2)": -0.007112962, "vh_nir(t-2)": -0.008474652, "vh_ndvi(t-2)": -116.7236217, "vh_ndwi(t-2)": 240.2009889, "vh_nirv(t-2)": -0.047142912, "vh_vv(t-2)": -7.909982677, "slope(t-3)": 0.599961042, "elevation(t-3)": 1522.0, "canopy_height(t-3)": 0.0, "forest_cover(t-3)": 130.0, "silt(t-3)": 36.0, "sand(t-3)": 38.0, "clay(t-3)": 26.0, "vv(t-3)": -12.35794964, "vh(t-3)": -20.25746909, "red(t-3)": 1367.333333, "green(t-3)": 1151.0, "blue(t-3)": 827.3333333, "swir(t-3)": 2349.333333, "nir(t-3)": 2051.0, "ndvi(t-3)": 0.216978329, "ndwi(t-3)": -0.050717071, "nirv(t-3)": 413.3885932, "vv_red(t-3)": -0.009037993, "vv_green(t-3)": -0.010736707, "vv_blue(t-3)": -0.014937087, "vv_swir(t-3)": -0.005260194, "vv_nir(t-3)": -0.006025329, "vv_ndvi(t-3)": -56.95476465, "vv_ndwi(t-3)": 243.6644995, "vv_nirv(t-3)": -0.029894269, "vh_red(t-3)": -0.014815311, "vh_green(t-3)": -0.017599886, "vh_blue(t-3)": -0.024485257, "vh_swir(t-3)": -0.008622646, "vh_nir(t-3)": -0.009876874, "vh_ndvi(t-3)": -93.36171601, "vh_ndwi(t-3)": 399.4211186, "vh_nirv(t-3)": -0.049003454, "vh_vv(t-3)": -7.899519455}, "geometry": {"type": "Point", "coordinates": [-115.8855556, 42.44111111]}}
\ No newline at end of file
diff --git a/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_1/stac.json b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_1/stac.json
new file mode 100644
index 00000000000..469f98574d9
--- /dev/null
+++ b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_1/stac.json
@@ -0,0 +1 @@
+{"assets": {"documentation": {"href": "../_common/documentation.pdf", "type": "application/pdf"}, "labels": {"href": "labels.geojson", "type": "application/geo+json"}, "training_features_descriptions": {"href": "../_common/training_features_descriptions.csv", "title": "Training Features Descriptions", "type": "text/csv"}}, "bbox": [-115.8855556, 42.44111111, -115.8855556, 42.44111111], "collection": "su_sar_moisture_content", "geometry": {"coordinates": [-115.8855556, 42.44111111], "type": "Point"}, "id": "su_sar_moisture_content_0001", "links": [{"href": "../collection.json", "rel": "collection"}, {"href": "../collection.json", "rel": "parent"}], "properties": {"datetime": "2015-06-30T00:00:00Z", "label:description": "", "label:properties": ["percent(t)"], "label:type": "vector"}, "stac_extensions": ["label"], "stac_version": "1.0.0-beta.2", "type": "Feature"}
\ No newline at end of file
diff --git a/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_2/labels.geojson b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_2/labels.geojson
new file mode 100644
index 00000000000..9492503feae
--- /dev/null
+++ b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_2/labels.geojson
@@ -0,0 +1 @@
+{"type": "Feature", "properties": {"percent(t)": 132.6666667, "site": "Blackstone", "date": "6/30/15", "slope(t)": 0.599961042, "elevation(t)": 1522.0, "canopy_height(t)": 0.0, "forest_cover(t)": 130.0, "silt(t)": 36.0, "sand(t)": 38.0, "clay(t)": 26.0, "vv(t)": -12.80108143, "vh(t)": -20.86413967, "red(t)": 2007.5, "green(t)": 1669.5, "blue(t)": 1234.5, "swir(t)": 3226.5, "nir(t)": 2764.5, "ndvi(t)": 0.158611467, "ndwi(t)": -0.07713057, "nirv(t)": 438.5596345, "vv_red(t)": -0.006376628, "vv_green(t)": -0.007667614, "vv_blue(t)": -0.010369446, "vv_swir(t)": -0.003967482, "vv_nir(t)": -0.004630523, "vv_ndvi(t)": -80.70716267, "vv_ndwi(t)": 165.9663796, "vv_nirv(t)": -0.029188919, "vh_red(t)": -0.010393096, "vh_green(t)": -0.012497238, "vh_blue(t)": -0.016900883, "vh_swir(t)": -0.006466493, "vh_nir(t)": -0.007547166, "vh_ndvi(t)": -131.5424422, "vh_ndwi(t)": 270.5041557, "vh_nirv(t)": -0.047574236, "vh_vv(t)": -8.063058239, "slope(t-1)": 0.599961042, "elevation(t-1)": 1522.0, "canopy_height(t-1)": 0.0, "forest_cover(t-1)": 130.0, "silt(t-1)": 36.0, "sand(t-1)": 38.0, "clay(t-1)": 26.0, "vv(t-1)": -12.93716855, "vh(t-1)": -20.92368901, "red(t-1)": 1792.0, "green(t-1)": 1490.0, "blue(t-1)": 1102.5, "swir(t-1)": 3047.0, "nir(t-1)": 2574.0, "ndvi(t-1)": 0.179116009, "ndwi(t-1)": -0.084146807, "nirv(t-1)": 461.0691997, "vv_red(t-1)": -0.007219402, "vv_green(t-1)": -0.008682663, "vv_blue(t-1)": -0.011734393, "vv_swir(t-1)": -0.004245871, "vv_nir(t-1)": -0.005026095, "vv_ndvi(t-1)": -72.22787422, "vv_ndwi(t-1)": 153.7452097, "vv_nirv(t-1)": -0.02805906, "vh_red(t-1)": -0.011676166, "vh_green(t-1)": -0.014042744, "vh_blue(t-1)": -0.018978403, "vh_swir(t-1)": -0.00686698, "vh_nir(t-1)": -0.008128861, "vh_ndvi(t-1)": -116.8164094, "vh_ndwi(t-1)": 248.6569562, "vh_nirv(t-1)": -0.0453808, "vh_vv(t-1)": -7.986520458, "slope(t-2)": 0.599961042, "elevation(t-2)": 1522.0, "canopy_height(t-2)": 0.0, "forest_cover(t-2)": 130.0, "silt(t-2)": 36.0, "sand(t-2)": 38.0, "clay(t-2)": 26.0, "vv(t-2)": -13.07325567, "vh(t-2)": -20.98323835, "red(t-2)": 1721.5, "green(t-2)": 1432.0, "blue(t-2)": 1056.5, "swir(t-2)": 2950.0, "nir(t-2)": 2476.0, "ndvi(t-2)": 0.179768568, "ndwi(t-2)": -0.087357002, "nirv(t-2)": 445.0984812, "vv_red(t-2)": -0.007594107, "vv_green(t-2)": -0.009129368, "vv_blue(t-2)": -0.012374118, "vv_swir(t-2)": -0.004431612, "vv_nir(t-2)": -0.00527999, "vv_ndvi(t-2)": -72.72270011, "vv_ndwi(t-2)": 149.6532084, "vv_nirv(t-2)": -0.029371603, "vh_red(t-2)": -0.012188927, "vh_green(t-2)": -0.014653099, "vh_blue(t-2)": -0.019861087, "vh_swir(t-2)": -0.007112962, "vh_nir(t-2)": -0.008474652, "vh_ndvi(t-2)": -116.7236217, "vh_ndwi(t-2)": 240.2009889, "vh_nirv(t-2)": -0.047142912, "vh_vv(t-2)": -7.909982677, "slope(t-3)": 0.599961042, "elevation(t-3)": 1522.0, "canopy_height(t-3)": 0.0, "forest_cover(t-3)": 130.0, "silt(t-3)": 36.0, "sand(t-3)": 38.0, "clay(t-3)": 26.0, "vv(t-3)": -12.35794964, "vh(t-3)": -20.25746909, "red(t-3)": 1367.333333, "green(t-3)": 1151.0, "blue(t-3)": 827.3333333, "swir(t-3)": 2349.333333, "nir(t-3)": 2051.0, "ndvi(t-3)": 0.216978329, "ndwi(t-3)": -0.050717071, "nirv(t-3)": 413.3885932, "vv_red(t-3)": -0.009037993, "vv_green(t-3)": -0.010736707, "vv_blue(t-3)": -0.014937087, "vv_swir(t-3)": -0.005260194, "vv_nir(t-3)": -0.006025329, "vv_ndvi(t-3)": -56.95476465, "vv_ndwi(t-3)": 243.6644995, "vv_nirv(t-3)": -0.029894269, "vh_red(t-3)": -0.014815311, "vh_green(t-3)": -0.017599886, "vh_blue(t-3)": -0.024485257, "vh_swir(t-3)": -0.008622646, "vh_nir(t-3)": -0.009876874, "vh_ndvi(t-3)": -93.36171601, "vh_ndwi(t-3)": 399.4211186, "vh_nirv(t-3)": -0.049003454, "vh_vv(t-3)": -7.899519455}, "geometry": {"type": "Point", "coordinates": [-115.8855556, 42.44111111]}}
\ No newline at end of file
diff --git a/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_2/stac.json b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_2/stac.json
new file mode 100644
index 00000000000..469f98574d9
--- /dev/null
+++ b/tests/data/western_usa_live_fuel_moisture/su_sar_moisture_content/su_sar_moisture_content_2/stac.json
@@ -0,0 +1 @@
+{"assets": {"documentation": {"href": "../_common/documentation.pdf", "type": "application/pdf"}, "labels": {"href": "labels.geojson", "type": "application/geo+json"}, "training_features_descriptions": {"href": "../_common/training_features_descriptions.csv", "title": "Training Features Descriptions", "type": "text/csv"}}, "bbox": [-115.8855556, 42.44111111, -115.8855556, 42.44111111], "collection": "su_sar_moisture_content", "geometry": {"coordinates": [-115.8855556, 42.44111111], "type": "Point"}, "id": "su_sar_moisture_content_0001", "links": [{"href": "../collection.json", "rel": "collection"}, {"href": "../collection.json", "rel": "parent"}], "properties": {"datetime": "2015-06-30T00:00:00Z", "label:description": "", "label:properties": ["percent(t)"], "label:type": "vector"}, "stac_extensions": ["label"], "stac_version": "1.0.0-beta.2", "type": "Feature"}
\ No newline at end of file
diff --git a/tests/datasets/test_western_usa_live_fuel_moisture.py b/tests/datasets/test_western_usa_live_fuel_moisture.py
new file mode 100644
index 00000000000..ad79ca7937c
--- /dev/null
+++ b/tests/datasets/test_western_usa_live_fuel_moisture.py
@@ -0,0 +1,100 @@
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+import builtins
+import os
+import shutil
+from pathlib import Path
+from typing import Any
+
+import pytest
+import torch
+import torch.nn as nn
+from _pytest.fixtures import SubRequest
+from _pytest.monkeypatch import MonkeyPatch
+
+from torchgeo.datasets import WesternUSALiveFuelMoisture
+
+
+class Collection:
+ def download(self, output_dir: str, **kwargs: str) -> None:
+ tarball_path = os.path.join(
+ "tests",
+ "data",
+ "western_usa_live_fuel_moisture",
+ "su_sar_moisture_content.tar.gz",
+ )
+ shutil.copy(tarball_path, output_dir)
+
+
+def fetch(collection_id: str, **kwargs: str) -> Collection:
+ return Collection()
+
+
+class TestWesternUSALiveFuelMoisture:
+ @pytest.fixture
+ def dataset(
+ self, monkeypatch: MonkeyPatch, tmp_path: Path
+ ) -> WesternUSALiveFuelMoisture:
+ radiant_mlhub = pytest.importorskip("radiant_mlhub", minversion="0.2.1")
+ monkeypatch.setattr(radiant_mlhub.Collection, "fetch", fetch)
+ md5 = "ecbc9269dd27c4efe7aa887960054351"
+ monkeypatch.setattr(WesternUSALiveFuelMoisture, "md5", md5)
+ root = str(tmp_path)
+ transforms = nn.Identity()
+ return WesternUSALiveFuelMoisture(
+ root, transforms=transforms, download=True, api_key="", checksum=True
+ )
+
+ @pytest.mark.parametrize("index", [0, 1, 2])
+ def test_getitem(self, dataset: WesternUSALiveFuelMoisture, index: int) -> None:
+ x = dataset[index]
+ assert isinstance(x, dict)
+ assert isinstance(x["input"], torch.Tensor)
+ assert isinstance(x["label"], torch.Tensor)
+
+ def test_len(self, dataset: WesternUSALiveFuelMoisture) -> None:
+ assert len(dataset) == 3
+
+ def test_already_downloaded(self, tmp_path: Path) -> None:
+ pathname = os.path.join(
+ "tests",
+ "data",
+ "western_usa_live_fuel_moisture",
+ "su_sar_moisture_content.tar.gz",
+ )
+ root = str(tmp_path)
+ shutil.copy(pathname, root)
+ WesternUSALiveFuelMoisture(root)
+
+ def test_not_downloaded(self, tmp_path: Path) -> None:
+ with pytest.raises(RuntimeError, match="Dataset not found in"):
+ WesternUSALiveFuelMoisture(str(tmp_path))
+
+ def test_invalid_features(self, dataset: WesternUSALiveFuelMoisture) -> None:
+ with pytest.raises(AssertionError, match="Invalid input variable name."):
+ WesternUSALiveFuelMoisture(dataset.root, input_features=["foo"])
+
+ @pytest.fixture(params=["pandas"])
+ def mock_missing_module(self, monkeypatch: MonkeyPatch, request: SubRequest) -> str:
+ import_orig = builtins.__import__
+ package = str(request.param)
+
+ def mocked_import(name: str, *args: Any, **kwargs: Any) -> Any:
+ if name == package:
+ raise ImportError()
+ return import_orig(name, *args, **kwargs)
+
+ monkeypatch.setattr(builtins, "__import__", mocked_import)
+ return package
+
+ def test_mock_missing_module(
+ self, dataset: WesternUSALiveFuelMoisture, mock_missing_module: str
+ ) -> None:
+ package = mock_missing_module
+ if package == "pandas":
+ with pytest.raises(
+ ImportError,
+ match=f"{package} is not installed and is required to use this dataset",
+ ):
+ WesternUSALiveFuelMoisture(dataset.root)
diff --git a/torchgeo/datasets/__init__.py b/torchgeo/datasets/__init__.py
index 334601853d5..c0ad168bafd 100644
--- a/torchgeo/datasets/__init__.py
+++ b/torchgeo/datasets/__init__.py
@@ -114,6 +114,7 @@
)
from .vaihingen import Vaihingen2D
from .vhr10 import VHR10
+from .western_usa_live_fuel_moisture import WesternUSALiveFuelMoisture
from .xview import XView2
from .zuericrop import ZueriCrop
@@ -209,6 +210,7 @@
"USAVars",
"Vaihingen2D",
"VHR10",
+ "WesternUSALiveFuelMoisture",
"XView2",
"ZueriCrop",
# Base classes
diff --git a/torchgeo/datasets/western_usa_live_fuel_moisture.py b/torchgeo/datasets/western_usa_live_fuel_moisture.py
new file mode 100644
index 00000000000..63fd8fbeccc
--- /dev/null
+++ b/torchgeo/datasets/western_usa_live_fuel_moisture.py
@@ -0,0 +1,354 @@
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+"""Western USA Live Fuel Moisture Dataset."""
+
+import glob
+import json
+import os
+from typing import Any, Callable, Optional
+
+import torch
+from torch import Tensor
+
+from .geo import NonGeoDataset
+from .utils import download_radiant_mlhub_collection, extract_archive
+
+
+class WesternUSALiveFuelMoisture(NonGeoDataset):
+ """Western USA Live Fuel Moisture Dataset.
+
+ This tabular style dataset contains fuel moisture
+ (mass of water in vegetation) and remotely sensed variables
+ in the western United States. It contains 2615 datapoints and 138
+ variables. For more details see the
+ `dataset page <https://mlhub.earth/data/su_sar_moisture_content_main>`_.
+
+ Dataset Format:
+
+ * .geojson file for each datapoint
+
+ Dataset Features:
+
+ * 138 remote sensing derived variables, some with a time dependency
+ * 2615 datapoints with regression target of predicting fuel moisture
+
+ If you use this dataset in your research, please cite the following paper:
+
+ * https://doi.org/10.1016/j.rse.2020.111797
+
+ .. note::
+
+ This dataset requires the following additional library to be installed:
+
+ * `radiant-mlhub <https://pypi.org/project/radiant-mlhub/>`_ to download the
+ imagery and labels from the Radiant Earth MLHub
+
+ .. versionadded:: 0.5
+ """
+
+ collection_id = "su_sar_moisture_content"
+
+ md5 = "a6c0721f06a3a0110b7d1243b18614f0"
+
+ label_name = "percent(t)"
+
+ all_variable_names = [
+ # "date",
+ "slope(t)",
+ "elevation(t)",
+ "canopy_height(t)",
+ "forest_cover(t)",
+ "silt(t)",
+ "sand(t)",
+ "clay(t)",
+ "vv(t)",
+ "vh(t)",
+ "red(t)",
+ "green(t)",
+ "blue(t)",
+ "swir(t)",
+ "nir(t)",
+ "ndvi(t)",
+ "ndwi(t)",
+ "nirv(t)",
+ "vv_red(t)",
+ "vv_green(t)",
+ "vv_blue(t)",
+ "vv_swir(t)",
+ "vv_nir(t)",
+ "vv_ndvi(t)",
+ "vv_ndwi(t)",
+ "vv_nirv(t)",
+ "vh_red(t)",
+ "vh_green(t)",
+ "vh_blue(t)",
+ "vh_swir(t)",
+ "vh_nir(t)",
+ "vh_ndvi(t)",
+ "vh_ndwi(t)",
+ "vh_nirv(t)",
+ "vh_vv(t)",
+ "slope(t-1)",
+ "elevation(t-1)",
+ "canopy_height(t-1)",
+ "forest_cover(t-1)",
+ "silt(t-1)",
+ "sand(t-1)",
+ "clay(t-1)",
+ "vv(t-1)",
+ "vh(t-1)",
+ "red(t-1)",
+ "green(t-1)",
+ "blue(t-1)",
+ "swir(t-1)",
+ "nir(t-1)",
+ "ndvi(t-1)",
+ "ndwi(t-1)",
+ "nirv(t-1)",
+ "vv_red(t-1)",
+ "vv_green(t-1)",
+ "vv_blue(t-1)",
+ "vv_swir(t-1)",
+ "vv_nir(t-1)",
+ "vv_ndvi(t-1)",
+ "vv_ndwi(t-1)",
+ "vv_nirv(t-1)",
+ "vh_red(t-1)",
+ "vh_green(t-1)",
+ "vh_blue(t-1)",
+ "vh_swir(t-1)",
+ "vh_nir(t-1)",
+ "vh_ndvi(t-1)",
+ "vh_ndwi(t-1)",
+ "vh_nirv(t-1)",
+ "vh_vv(t-1)",
+ "slope(t-2)",
+ "elevation(t-2)",
+ "canopy_height(t-2)",
+ "forest_cover(t-2)",
+ "silt(t-2)",
+ "sand(t-2)",
+ "clay(t-2)",
+ "vv(t-2)",
+ "vh(t-2)",
+ "red(t-2)",
+ "green(t-2)",
+ "blue(t-2)",
+ "swir(t-2)",
+ "nir(t-2)",
+ "ndvi(t-2)",
+ "ndwi(t-2)",
+ "nirv(t-2)",
+ "vv_red(t-2)",
+ "vv_green(t-2)",
+ "vv_blue(t-2)",
+ "vv_swir(t-2)",
+ "vv_nir(t-2)",
+ "vv_ndvi(t-2)",
+ "vv_ndwi(t-2)",
+ "vv_nirv(t-2)",
+ "vh_red(t-2)",
+ "vh_green(t-2)",
+ "vh_blue(t-2)",
+ "vh_swir(t-2)",
+ "vh_nir(t-2)",
+ "vh_ndvi(t-2)",
+ "vh_ndwi(t-2)",
+ "vh_nirv(t-2)",
+ "vh_vv(t-2)",
+ "slope(t-3)",
+ "elevation(t-3)",
+ "canopy_height(t-3)",
+ "forest_cover(t-3)",
+ "silt(t-3)",
+ "sand(t-3)",
+ "clay(t-3)",
+ "vv(t-3)",
+ "vh(t-3)",
+ "red(t-3)",
+ "green(t-3)",
+ "blue(t-3)",
+ "swir(t-3)",
+ "nir(t-3)",
+ "ndvi(t-3)",
+ "ndwi(t-3)",
+ "nirv(t-3)",
+ "vv_red(t-3)",
+ "vv_green(t-3)",
+ "vv_blue(t-3)",
+ "vv_swir(t-3)",
+ "vv_nir(t-3)",
+ "vv_ndvi(t-3)",
+ "vv_ndwi(t-3)",
+ "vv_nirv(t-3)",
+ "vh_red(t-3)",
+ "vh_green(t-3)",
+ "vh_blue(t-3)",
+ "vh_swir(t-3)",
+ "vh_nir(t-3)",
+ "vh_ndvi(t-3)",
+ "vh_ndwi(t-3)",
+ "vh_nirv(t-3)",
+ "vh_vv(t-3)",
+ "lat",
+ "lon",
+ ]
+
+ def __init__(
+ self,
+ root: str = "data",
+ input_features: list[str] = all_variable_names,
+ transforms: Optional[Callable[[dict[str, Any]], dict[str, Any]]] = None,
+ download: bool = False,
+ api_key: Optional[str] = None,
+ checksum: bool = False,
+ ) -> None:
+ """Initialize a new Western USA Live Fuel Moisture Dataset.
+
+ Args:
+ root: root directory where dataset can be found
+ input_features: which input features to include
+ transforms: a function/transform that takes input sample and its target as
+ entry and returns a transformed version
+ download: if True, download dataset and store it in the root directory
+ api_key: a RadiantEarth MLHub API key to use for downloading the dataset
+ checksum: if True, check the MD5 of the downloaded files (may be slow)
+
+ Raises:
+ AssertionError: if ``input_features`` contains invalid variable names
+ ImportError: if pandas is not installed
+ RuntimeError: if ``download=False`` but dataset is missing or checksum fails
+ """
+ super().__init__()
+
+ self.root = root
+ self.transforms = transforms
+ self.checksum = checksum
+ self.download = download
+ self.api_key = api_key
+
+ self._verify()
+
+ try:
+ import pandas as pd # noqa: F401
+ except ImportError:
+ raise ImportError(
+ "pandas is not installed and is required to use this dataset"
+ )
+
+ assert all(
+ input in self.all_variable_names for input in input_features
+ ), "Invalid input variable name."
+ self.input_features = input_features
+
+ self.collection = self._retrieve_collection()
+
+ self.dataframe = self._load_data()
+
+ def _retrieve_collection(self) -> list[str]:
+ """Retrieve dataset collection that maps samples to paths.
+
+ Returns:
+ list of sample paths
+ """
+ return glob.glob(
+ os.path.join(self.root, self.collection_id, "**", "labels.geojson")
+ )
+
+ def __len__(self) -> int:
+ """Return the number of data points in the dataset.
+
+ Returns:
+ length of the dataset
+ """
+ return len(self.dataframe)
+
+ def __getitem__(self, index: int) -> dict[str, Any]:
+ """Return an index within the dataset.
+
+ Args:
+ index: index to return
+
+ Returns:
+ input features and target at that index
+ """
+ data = self.dataframe.iloc[index, :]
+
+ sample: dict[str, Tensor] = {
+ "input": torch.tensor(data.drop([self.label_name]), dtype=torch.float32),
+ "label": torch.tensor(data[self.label_name], dtype=torch.float32),
+ }
+
+ if self.transforms is not None:
+ sample = self.transforms(sample)
+
+ return sample
+
+ def _load_data(self) -> "pd.DataFrame": # type: ignore[name-defined] # noqa: F821
+ """Load data from individual files into pandas dataframe.
+
+ Returns:
+ the features and label
+ """
+ import pandas as pd
+
+ data_rows = []
+ for path in self.collection:
+ with open(path) as f:
+ content = json.load(f)
+ data_dict = content["properties"]
+ data_dict["lat"] = content["geometry"]["coordinates"][0]
+ data_dict["lon"] = content["geometry"]["coordinates"][1]
+ data_rows.append(data_dict)
+
+ df: pd.DataFrame = pd.DataFrame(data_rows)
+ df = df[self.input_features + [self.label_name]]
+ return df
+
+ def _verify(self) -> None:
+ """Verify the integrity of the dataset.
+
+ Raises:
+ RuntimeError: if ``download=False`` but dataset is missing or checksum fails
+ """
+ # Check if the extracted files already exist
+ pathname = os.path.join(self.root, self.collection_id)
+ if os.path.exists(pathname):
+ return
+
+ # Check if the zip files have already been downloaded
+ pathname = os.path.join(self.root, self.collection_id) + ".tar.gz"
+ if os.path.exists(pathname):
+ self._extract()
+ return
+
+ # Check if the user requested to download the dataset
+ if not self.download:
+ raise RuntimeError(
+ f"Dataset not found in `root={self.root}` and `download=False`, "
+ "either specify a different `root` directory or use `download=True` "
+ "to automatically download the dataset."
+ )
+
+ # Download the dataset
+ self._download()
+ self._extract()
+
+ def _extract(self) -> None:
+ """Extract the dataset."""
+ pathname = os.path.join(self.root, self.collection_id) + ".tar.gz"
+ extract_archive(pathname, self.root)
+
+ def _download(self, api_key: Optional[str] = None) -> None:
+ """Download the dataset and extract it.
+
+ Args:
+ api_key: a RadiantEarth MLHub API key to use for downloading the dataset
+
+ Raises:
+ RuntimeError: if download doesn't work correctly or checksums don't match
+ """
+ download_radiant_mlhub_collection(self.collection_id, self.root, api_key)
+ filename = os.path.join(self.root, self.collection_id) + ".tar.gz"
+ extract_archive(filename, self.root)