Data Set Information:

This big data set is a fused bi-temporal optical-radar data for cropland classification. The images were collected by RapidEye satellites (optical) and the Unmanned Aerial Vehicle Synthetic Aperture Radar (UAVSAR) system (Radar) over an agricultural region near Winnipeg, Manitoba, Canada on 2012.
There are 2 * 49 radar features and 2 * 38 optical features for two dates: 05 and 14 July 2012.
Seven crop type classes exist for this data set as follows: 1-Corn; 2-Peas; 3- Canola; 4-Soybeans; 5- Oats; 6- Wheat; and 7-Broadleaf.

Attribute Information:

175 attributes including:
     1- class;
     2- f1 to f49:Polarimetric features on 05 July 2012;
     3- f50 to f98:Polarimetric features on 14 July 2012;
     4- f99 to f136:Optical features on 05 July 2012;
     5- f137 to f174:Optical features on 14 July 2012;

Details:
label:crop type class
f1:sigHH_Rad05July
f2:sigHV_Rad05July
f3:sigVV_Rad05July
f4:sigRR_Rad05July
f5:sigRL_Rad05July
f6:sigLL_Rad05July
f7:Rhhvv_Rad05July
f8:Rhvhh_Rad05July
f9:Rhvvv_Rad05July
f10:Rrrll_Rad05July
f11:Rrlrr_Rad05July
f12:Rrlll_Rad05July
f13:Rhh_Rad05July
f14:Rhv_Rad05July
f15:Rvv_Rad05July
f16:Rrr_Rad05July
f17:Rrl_Rad05July
f18:Rll_Rad05July
f19:Ro12_Rad05July
f20:Ro13_Rad05July
f21:Ro23_Rad05July
f22:Ro12cir_Rad05July
f23:Ro13cir_Rad05July
f24:Ro23cir_Rad05July
f25:l1_Rad05July
f26:l2_Rad05July
f27:l3_Rad05July
f28:H_Rad05July
f29:A_Rad05July
f30:a_Rad05July
f31:HA_Rad05July
f32:H1mA_Rad05July
f33:1mHA_Rad05July
f34:1mH1mA_Rad05July
f35:PH_Rad05July
f36:rvi_Rad05July
f37:paulalpha_Rad05July
f38:paulbeta_Rad05July
f39:paulgamma_Rad05July
f40:krogks_Rad05July
f41:krogkd_Rad05July
f42:krogkh_Rad05July
f43:freeodd_Rad05July
f44:freedbl_Rad05July
f45:freevol_Rad05July
f46:yamodd_Rad05July
f47:yamdbl_Rad05July
f48:yamhlx_Rad05July
f49:yamvol_Rad05July
f50:sigHH_Rad14July
f51:sigHV_Rad14July
f52:sigVV_Rad14July
f53:sigRR_Rad14July
f54:sigRL_Rad14July
f55:sigLL_Rad14July
f56:Rhhvv_Rad14July
f57:Rhvhh_Rad14July
f58:Rhvvv_Rad14July
f59:Rrrll_Rad14July
f60:Rrlrr_Rad14July
f61:Rrlll_Rad14July
f62:Rhh_Rad14July
f63:Rhv_Rad14July
f64:Rvv_Rad14July
f65:Rrr_Rad14July
f66:Rrl_Rad14July
f67:Rll_Rad14July
f68:Ro12_Rad14July
f69:Ro13_Rad14July
f70:Ro23_Rad14July
f71:Ro12cir_Rad14July
f72:Ro13cir_Rad14July
f73:Ro23cir_Rad14July
f74:l1_Rad14July
f75:l2_Rad14July
f76:l3_Rad14July
f77:H_Rad14July
f78:A_Rad14July
f79:a_Rad14July
f80:HA_Rad14July
f81:H1mA_Rad14July
f82:1mHA_Rad14July
f83:1mH1mA_Rad14July
f84:PH_Rad14July
f85:rvi_Rad14July
f86:paulalpha_Rad14July
f87:paulbeta_Rad14July
f88:paulgamma_Rad14July
f89:krogks_Rad14July
f90:krogkd_Rad14July
f91:krogkh_Rad14July
f92:freeodd_Rad14July
f93:freedbl_Rad14July
f94:freevol_Rad14July
f95:yamodd_Rad14July
f96:yamdbl_Rad14July
f97:yamhlx_Rad14July
f98:yamvol_Rad14July
f99:B_Opt05July
f100:G_Opt05July
f101:R_Opt05July
f102:Redge_Opt05July
f103:NIR_Opt05July
f104:NDVI_Opt05July
f105:SR_Opt05July
f106:RGRI_Opt05July
f107:EVI_Opt05July
f108:ARVI_Opt05July
f109:SAVI_Opt05July
f110:NDGI_Opt05July
f111:gNDVI_Opt05July
f112:MTVI2_Opt05July
f113:NDVIre_Opt05July
f114:SRre_Opt05July
f115:NDGIre_Opt05July
f116:RTVIcore_Opt05July
f117:RNDVI_Opt05July
f118:TCARI_Opt05July
f119:TVI_Opt05July
f120:PRI2_Opt05July
f121:MeanPC1_Opt05July
f122:VarPC1_Opt05July
f123:HomPC1_Opt05July
f124:ConPC1_Opt05July
f125:DisPC1_Opt05July
f126:EntPC1_Opt05July
f127:SecMomPC1_Opt05July
f128:CorPC1_Opt05July
f129:MeanPC2_Opt05July
f130:VarPC2_Opt05July
f131:HomPC2_Opt05July
f132:ConPC2_Opt05July
f133:DisPC2_Opt05July
f134:EntPC2_Opt05July
f135:SecMomPC2_Opt05July
f136:CorPC2_Opt05July
f137:B_Opt14July
f138:G_Opt14July
f139:R_Opt14July
f140:Redge_Opt14July
f141:NIR_Opt14July
f142:NDVI_Opt14July
f143:SR_Opt14July
f144:RGRI_Opt14July
f145:EVI_Opt14July
f146:ARVI_Opt14July
f147:SAVI_Opt14July
f148:NDGI_Opt14July
f149:gNDVI_Opt14July
f150:MTVI2_Opt14July
f151:NDVIre_Opt14July
f152:SRre_Opt14July
f153:NDGIre_Opt14July
f154:RTVIcore_Opt14July
f155:RNDVI_Opt14July
f156:TCARI_Opt14July
f157:TVI_Opt14July
f158:PRI2_Opt14July
f159:MeanPC1_Opt14July
f160:VarPC1_Opt14July
f161:HomPC1_Opt14July
f162:ConPC1_Opt14July
f163:DisPC1_Opt14July
f164:EntPC1_Opt14July
f165:SecMomPC1_Opt14July
f166:CorPC1_Opt14July
f167:MeanPC2_Opt14July
f168:VarPC2_Opt14July
f169:HomPC2_Opt14July
f170:ConPC2_Opt14July
f171:DisPC2_Opt14July
f172:EntPC2_Opt14July
f173:SecMomPC2_Opt14July
f174:CorPC2_Opt14July

For more information about these attributes, please refer to relevant papers.

Relevant Papers:

1- Khosravi, I., & Alavipanah, S. K. (2019). A random forest-based framework for crop mapping using temporal, spectral, textural and polarimetric observations. International Journal of Remote Sensing, 40(18), 7221-7251.a€?
2- Khosravi, I., et al. (2018). MSMD: maximum separability and minimum dependency feature selection for cropland classification from optical and radar data. International Journal of Remote Sensing, 39(8), 2159-2176.a€?

These papers can be downloaded from [Web link]

Citation Request:

I'd like to present my acknowledgment to the JPL NASA for the PolSAR images, and the SMAPVEX 2012 team, the Agriculture and Agri-Food Canada, for providing the PolSAR and the optical images.
Please cite my relevant papers.

Dr. Iman Khosravi,
Postdoctoral researcher,
Department of Remote Sensing & GIS, Faculty of Geography, University of Tehran, Tehran, I.R. Iran, 1417853933
E-Mail: iman.khosravi '@' ut.ac.ir
Website: http://i-khosravi.ir