Purpose

This vignette documents the workflow to create the training dataset which is extracted from the target dataset at selected labelled locations. Alternatively, if there is no need for a target dataset, for example, when prototype which spatial resolution to use for predictions, the workflow described for making the target dataset is wholly valid for creating a training dataset only.

Libraries

library(RiverML)
library(magrittr)

Loading target data

Here we use the example of the South Fork Eel (SFE) river catchment (California, USA) and load the target streamlines for this region. Notice that using as.df = FALSE, get_target_points() now returns a SpatialPointsDataFrame which is projected on latitude/longitude.

region <- "SFE"
target_streamlines <- target_streamlines_SFE
target_points <- get_target_points(target_streamlines, as.df = FALSE)
#> Warning in proj4string(sldf): CRS object has comment, which is lost in output
target_points
#> class       : SpatialPointsDataFrame 
#> features    : 8022 
#> extent      : -124.0731, -123.4309, 39.60465, 40.37879  (xmin, xmax, ymin, ymax)
#> crs         : +proj=longlat +datum=WGS84 +no_defs 
#> variables   : 59
#> names       :   COMID_FID,         LENGTH, Rowid_,  COMID_FI_1,   COMID,      AREA,         SLOPE, CONFINEMEN,         RUSLE, CONFINEM_1,     RUSLEBINS, REGION, CSBIN, KMEANS_ID,     RTLBIN, ... 
#> min values  : 8283534_280, 0.886343917158,      0, 8283534_280, 8283534,    0.0036, 2.1034561e-08,          0,   0.148176916,   Confined, High Sediment,  North,    CH,         1, North_CH_1, ... 
#> max values  :  8290162_92,  200.000000006,  15660,   8290160_7, 8290162, 1785.0888, 1.57441710441,        994, 693.464281156, Unconfined,  Low Sediment,  North,    UL,         5, North_UL_5, ...

SFE_all_data_df is included in the package and contains the target data for the SFE region.

target_data_df <- SFE_all_data_df
dim(target_data_df)
#> [1] 8022  287

SFE target data
CatAreaSqKm	WsAreaSqKm	CHYD	CCHEM	CSED	CCONN	CTEMP	CHABT	ICI	WHYD	WCHEM	WSED	WCONN	WTEMP	WHABT	IWI	PctSilicicCat	PctWaterCat	PctSilicicWs	PctWaterWs	PctOw2011Cat	PctUrbOp2011Cat	PctUrbLo2011Cat	PctBl2011Cat	PctConif2011Cat	PctMxFst2011Cat	PctShrb2011Cat	PctGrs2011Cat	PctWdWet2011Cat	PctHbWet2011Cat	PctOw2011Ws	PctIce2011Ws	PctUrbOp2011Ws	PctUrbLo2011Ws	PctBl2011Ws	PctConif2011Ws	PctMxFst2011Ws	PctShrb2011Ws	PctGrs2011Ws	PctWdWet2011Ws	PctHbWet2011Ws	PctOw2011CatRp100	PctBl2011CatRp100	PctConif2011CatRp100	PctShrb2011CatRp100	PctGrs2011CatRp100	PctHbWet2011CatRp100	PctOw2011WsRp100	PctBl2011WsRp100	PctConif2011WsRp100	PctShrb2011WsRp100	PctGrs2011WsRp100	PctHbWet2011WsRp100	Precip8110Cat	Tmax8110Cat	Tmean8110Cat	Tmin8110Cat	Precip8110Ws	Tmax8110Ws	Tmean8110Ws	Tmin8110Ws	RunoffCat	RunoffWs	ClayCat	SandCat	ClayWs	SandWs	OmCat	PermCat	RckDepCat	WtDepCat	OmWs	PermWs	RckDepWs	WtDepWs	SLOPE	CONFINEMEN	RUSLE	SO	LDD	aspect_max.rstr	aspect_mean.rstr	aspect_median.rstr	aspect_min.rstr	aspect_sd.rstr	aspect_skew.rstr	curvplan_max.rstr	curvplan_mean.rstr	curvplan_median.rstr	curvplan_min.rstr	curvplan_sd.rstr	curvplan_skew.rstr	curvprof_max.rstr	curvprof_mean.rstr	curvprof_median.rstr	curvprof_min.rstr	curvprof_sd.rstr	curvprof_skew.rstr	flowdir_max.rstr	flowdir_mean.rstr	flowdir_median.rstr	flowdir_min.rstr	flowdir_sd.rstr	flowdir_skew.rstr	layer_max.rstr	layer_mean.rstr	layer_median.rstr	layer_min.rstr	layer_sd.rstr	layer_skew.rstr	roughness_max.rstr	roughness_mean.rstr	roughness_median.rstr	roughness_min.rstr	roughness_sd.rstr	roughness_skew.rstr	slope_max.rstr	slope_mean.rstr	slope_median.rstr	slope_min.rstr	slope_sd.rstr	slope_skew.rstr	tpi_max.rstr	tpi_mean.rstr	tpi_median.rstr	tpi_min.rstr	tpi_sd.rstr	tpi_skew.rstr	tri_max.rstr	tri_mean.rstr	tri_median.rstr	tri_min.rstr	tri_sd.rstr	tri_skew.rstr	aspect_max.nrch	aspect_mean.nrch	aspect_median.nrch	aspect_min.nrch	aspect_sd.nrch	aspect_skew.nrch	curvplan_max.nrch	curvplan_mean.nrch	curvplan_median.nrch	curvplan_min.nrch	curvplan_sd.nrch	curvplan_skew.nrch	curvprof_max.nrch	curvprof_mean.nrch	curvprof_median.nrch	curvprof_min.nrch	curvprof_sd.nrch	curvprof_skew.nrch	flowdir_max.nrch	flowdir_mean.nrch	flowdir_median.nrch	flowdir_min.nrch	flowdir_sd.nrch	flowdir_skew.nrch	layer_max.nrch	layer_mean.nrch	layer_median.nrch	layer_min.nrch	layer_sd.nrch	layer_skew.nrch	roughness_max.nrch	roughness_mean.nrch	roughness_median.nrch	roughness_min.nrch	roughness_sd.nrch	roughness_skew.nrch	slope_max.nrch	slope_mean.nrch	slope_median.nrch	slope_min.nrch	slope_sd.nrch	slope_skew.nrch	tpi_max.nrch	tpi_mean.nrch	tpi_median.nrch	tpi_min.nrch	tpi_sd.nrch	tpi_skew.nrch	tri_max.nrch	tri_mean.nrch	tri_median.nrch	tri_min.nrch	tri_sd.nrch	tri_skew.nrch	H.640	H.960	H.1280	H.1600	H.1920	H.2240	H.2560	H.2880	H.3200	H.3840	H.4480	H.5120	H.5760	H.6400	H.7680	H.8960	H.10240	H.11520	H.12800	H.15360	H.17920	H.20480	H.23040	H.25600	H.30720	H.35840	H.40960	H.46080	H.51200	H.61440	H.71680	H.81920
3.586	5.681	0.950	0.954	0.955	0.957	0.942	0.945	0.738	0.963	0.960	0.962	0.969	0.958	0.952	0.786	100.000	0.000	100.000	0.000	0.000	0.000	0.000	0.000	87.025	0.000	8.302	0.000	3.657	1.016	0.000	0.000	0.000	0.000	0.000	87.025	0.000	8.302	0.000	3.657	1.016	0.000	0.000	63.636	36.364	0.000	0.000	0.000	29.630	33.333	28.889	8.148	0.000	1210.073	13.646	7.371	1.092	1210.073	13.646	7.371	1.092	293	293.000	13.877	56.248	13.877	56.248	0.714	10.486	125.433	182.880	0.714	10.486	125.433	182.880	0.060	14	5.806	1	0.553	6.282	2.531	3.426	0.001	2.096	0.124	0.040	0.000	0.000	-0.047	0.006	-0.812	0.036	-0.001	-0.001	-0.046	0.008	-0.764	128	9.464	16	1	10.094	3.627	794.441	710.960	705.982	648.451	31.922	0.448	18.264	9.234	9.455	1.076	3.321	-0.133	0.764	0.384	0.389	0.026	0.133	-0.249	2.626	-0.068	-0.024	-1.847	0.447	-0.085	6.010	2.869	2.896	0.255	1.069	-0.032	6.270	1.566	0.346	0.013	2.202	1.165	0.003	-0.003	0.000	-0.036	0.009	-2.255	0.000	-0.014	-0.012	-0.037	0.011	-0.731	32	6.067	1	1	9.288	1.577	682.511	673.280	671.432	668.006	3.962	0.739	11.544	5.276	4.775	2.553	2.016	1.057	0.441	0.199	0.185	0.060	0.088	0.707	0.033	-0.685	-0.562	-1.846	0.568	-0.558	3.318	1.663	1.636	0.899	0.573	0.948	0.910	0.962	0.918	0.894	0.839	0.852	0.839	0.816	0.806	0.743	0.695	0.707	0.768	0.712	0.680	0.637	0.597	0.578	0.611	0.527	0.524	0.481	0.487	0.395	0.443	0.362	0.454	0.398	0.449	0.404	0.368	0.366
2.855	4.098	1.000	0.986	0.994	1.000	1.000	0.994	0.974	0.995	0.983	0.991	0.996	0.995	0.991	0.953	100.000	0.000	100.000	0.000	0.820	0.000	0.000	41.803	9.016	0.000	28.689	19.672	0.000	0.000	0.816	0.000	0.000	0.000	75.184	2.204	0.000	12.000	9.796	0.000	0.000	0.000	0.000	90.390	8.312	1.299	0.000	1.791	0.000	87.910	8.806	1.493	0.000	710.003	7.348	1.348	-4.660	742.730	6.808	0.896	-5.018	293	293.000	5.710	69.130	5.710	69.130	1.450	23.220	152.400	163.830	1.450	23.220	152.400	163.830	0.041	0	52.215	1	0.802	6.277	2.765	2.109	0.000	1.855	0.171	0.042	0.001	0.002	-0.063	0.009	-1.089	0.057	-0.002	0.000	-0.068	0.013	-1.126	128	10.273	16	1	14.654	4.839	248.074	177.737	175.381	120.033	30.005	0.263	32.795	11.026	9.515	0.692	6.060	1.200	1.333	0.483	0.419	0.007	0.269	1.002	2.672	-0.010	0.067	-3.748	0.716	-0.754	8.824	3.261	2.848	0.225	1.706	1.012	6.116	3.262	4.527	0.212	2.066	-0.435	0.010	-0.010	-0.004	-0.054	0.016	-1.461	-0.002	-0.027	-0.020	-0.068	0.017	-0.589	64	25.259	16	1	20.538	0.996	139.348	134.755	134.129	130.633	3.001	0.232	8.451	4.609	4.017	2.040	1.824	0.538	0.419	0.166	0.149	0.024	0.113	0.765	-0.285	-0.932	-0.752	-1.972	0.464	-0.583	2.513	1.371	1.287	0.460	0.578	0.332	0.858	0.792	0.706	0.793	0.695	0.644	0.772	0.753	0.674	0.653	0.656	0.640	0.709	0.589	0.650	0.692	0.504	0.613	0.560	0.601	0.537	0.459	0.416	0.508	0.390	0.485	0.394	0.385	0.449	0.368	0.368	0.474
3.994	4.843	0.994	0.981	0.990	0.996	0.995	0.993	0.949	0.993	0.980	0.986	0.993	0.991	0.987	0.932	100.000	0.000	100.000	0.000	6.091	0.000	0.000	75.127	0.000	0.000	13.706	5.076	0.000	0.000	0.711	1.665	0.000	0.000	83.764	0.000	0.000	3.629	10.232	0.000	0.000	0.000	2.899	0.000	66.667	30.435	0.000	0.000	35.836	0.000	31.367	32.797	0.000	834.400	6.771	1.236	-4.305	927.973	5.398	-0.443	-6.283	293	304.963	5.710	69.130	5.710	69.130	1.450	23.220	152.400	163.830	1.450	23.220	152.400	163.830	0.291	0	308.980	1	0.663	5.895	3.613	3.727	1.478	1.234	0.059	0.044	0.000	0.002	-0.081	0.014	-1.764	0.023	-0.001	0.000	-0.073	0.009	-2.209	16	9.325	16	1	7.366	-0.212	455.246	349.543	352.887	249.622	44.744	-0.162	27.273	13.526	13.358	2.836	4.193	0.315	1.146	0.595	0.598	0.064	0.194	-0.020	3.093	-0.039	0.086	-4.022	0.794	-1.289	8.454	4.047	3.982	0.974	1.242	0.283	4.652	3.545	3.625	2.564	0.550	0.213	-0.007	-0.036	-0.034	-0.065	0.020	-0.040	0.007	-0.008	-0.005	-0.048	0.011	-1.616	16	8.464	8	1	5.809	0.225	327.129	296.531	295.940	268.134	18.875	0.044	15.034	9.594	8.873	4.949	2.626	0.426	0.610	0.360	0.326	0.185	0.113	0.681	-0.113	-1.309	-1.120	-3.021	0.670	-0.840	4.886	3.090	3.088	1.826	0.860	0.470	0.922	0.877	0.843	0.814	0.866	0.835	0.815	0.793	0.786	0.787	0.764	0.700	0.706	0.724	0.633	0.677	0.631	0.617	0.620	0.584	0.553	0.616	0.497	0.545	0.390	0.485	0.472	0.385	0.366	0.368	0.368	0.366
3.856	746.815	0.997	0.978	0.978	0.993	0.990	0.965	0.904	0.984	0.971	0.976	0.975	0.970	0.969	0.855	100.000	0.000	100.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	100.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	100.000	0.000	0.000	0.000	0.000	0.000	31.642	62.164	4.925	1.269	0.000	0.000	31.642	62.164	4.925	1.269	280.990	20.029	13.628	7.228	280.990	20.029	13.628	7.228	106	106.000	4.960	76.570	4.960	76.570	0.240	43.470	85.440	182.880	0.240	43.470	85.440	182.880	0.001	42	289.641	5	0.873	5.905	2.734	1.629	0.747	1.553	0.192	0.013	0.000	0.000	-0.023	0.003	-2.323	0.044	-0.002	-0.002	-0.044	0.008	0.211	64	7.998	1	1	8.477	1.446	277.513	200.941	195.291	163.743	31.948	0.468	26.282	9.189	10.201	0.311	5.143	-0.249	1.234	0.461	0.507	0.000	0.271	-0.026	1.870	-0.048	-0.055	-1.838	0.352	-0.043	7.967	2.904	3.225	0.129	1.681	-0.091	1.779	1.389	1.355	1.149	0.177	0.474	0.002	0.000	0.000	-0.003	0.001	-0.169	0.002	-0.005	-0.007	-0.008	0.004	0.938	2	1.042	1	1	0.204	4.304	165.333	164.504	164.495	163.915	0.401	0.265	3.588	1.680	1.530	0.542	0.929	0.427	0.155	0.081	0.074	0.030	0.040	0.311	0.147	-0.124	-0.148	-0.308	0.114	0.562	1.012	0.521	0.476	0.195	0.256	0.316	0.919	0.925	0.835	0.768	0.880	0.795	0.790	0.776	0.755	0.734	0.688	0.711	0.640	0.535	0.435	0.493	0.498	0.551	0.465	0.470	0.367	0.334	0.417	0.395	0.466	0.362	0.394	0.513	0.449	0.404	0.368	0.474
4.895	4.895	1.000	0.977	0.988	0.991	0.988	0.984	0.931	1.000	0.977	0.986	0.990	0.988	0.981	0.926	98.517	1.483	98.517	1.483	0.000	3.377	1.188	0.000	6.361	3.404	71.235	14.168	0.000	0.268	0.000	0.000	3.377	1.188	0.000	6.361	3.404	71.235	14.168	0.000	0.268	0.000	1.711	22.368	46.184	25.789	3.947	0.000	1.711	22.368	46.184	25.789	3.947	417.362	20.607	13.517	6.421	417.362	20.607	13.517	6.421	293	293.000	14.204	56.572	14.204	56.572	0.626	7.282	86.530	181.455	0.626	7.282	86.530	181.455	0.102	9	6.452	1	0.623	6.282	3.501	3.964	0.001	2.163	-0.447	0.033	0.000	0.000	-0.060	0.008	-1.670	0.036	-0.001	0.000	-0.051	0.010	-0.978	128	12.922	16	1	11.387	4.437	428.525	378.313	378.780	330.742	21.190	0.048	17.571	6.649	6.103	1.645	2.655	1.065	0.707	0.279	0.259	0.008	0.112	0.905	2.459	-0.051	0.005	-3.086	0.555	-1.015	5.462	2.096	1.922	0.414	0.829	0.977	6.212	2.358	0.811	0.121	2.246	0.401	0.005	-0.011	-0.004	-0.060	0.016	-1.368	0.010	-0.018	-0.021	-0.033	0.012	0.955	64	15.938	16	1	15.020	0.972	358.031	348.184	350.932	340.357	5.211	-0.210	10.845	5.691	5.260	1.702	2.350	0.485	0.469	0.191	0.193	0.016	0.119	0.529	-0.069	-0.974	-0.907	-2.902	0.683	-1.210	4.109	1.669	1.581	0.414	0.892	0.842	0.847	0.917	0.865	0.828	0.839	0.799	0.754	0.752	0.767	0.762	0.713	0.713	0.636	0.657	0.591	0.573	0.580	0.649	0.600	0.546	0.538	0.500	0.448	0.468	0.581	0.438	0.397	0.385	0.366	0.464	0.812	0.474
0.860	18.095	0.988	0.972	0.978	0.986	0.981	0.974	0.884	0.998	0.980	0.988	0.986	0.983	0.982	0.919	100.000	0.000	100.000	0.000	0.000	0.000	0.000	24.715	28.517	0.000	46.008	0.760	0.000	0.000	0.659	0.088	0.000	0.000	77.920	2.512	0.000	11.739	7.082	0.000	0.000	14.062	0.000	10.938	53.125	21.875	0.000	14.062	0.000	10.938	53.125	21.875	0.000	671.741	9.725	3.010	-3.713	943.536	6.541	0.480	-5.583	293	293.000	5.710	69.130	5.710	69.130	1.450	23.220	152.400	163.830	1.450	23.220	152.400	163.830	0.015	148	4.515	2	0.864	6.278	3.713	4.567	0.004	1.778	-0.309	0.024	0.001	0.000	-0.024	0.005	0.032	0.032	-0.002	0.000	-0.046	0.008	-1.426	128	11.021	16	1	13.912	4.940	254.109	186.173	180.822	169.393	17.459	1.544	18.335	4.515	3.628	0.155	3.231	1.072	0.790	0.200	0.158	0.001	0.148	1.107	2.067	-0.027	-0.012	-2.588	0.387	-0.757	5.383	1.364	1.088	0.024	0.983	1.067	5.489	4.736	4.846	4.023	0.427	-0.193	0.014	0.002	0.003	-0.015	0.006	-0.635	0.006	-0.016	-0.011	-0.046	0.018	-0.486	16	15.520	16	4	2.400	-4.416	176.251	171.978	171.122	170.226	1.647	1.140	13.452	5.784	6.345	0.770	4.373	0.339	0.697	0.254	0.216	0.030	0.204	0.507	0.192	-0.530	-0.161	-2.588	0.836	-1.269	4.591	1.629	1.462	0.223	1.306	0.569	0.727	0.889	0.848	0.751	0.749	0.717	0.705	0.666	0.799	0.749	0.628	0.606	0.601	0.608	0.537	0.461	0.421	0.394	0.577	0.458	0.388	0.459	0.535	0.377	0.390	0.438	0.394	0.385	0.449	0.368	0.812	0.474

Loading labelled locations

We now use get_input_data() to load and sort an input .csv file and convert the information herein as a SpatialPoints object with get_points_from_input_data().

input_dir <- system.file("extdata/input_data", package = "RiverML")
fname <- paste0(region,"_input.csv")
input_data <- get_input_data(file.path(input_dir, fname))
head(input_data)
#>   Name ward.grp      long      lat year
#> 1    3        5 -123.6740 39.68902 2017
#> 2   10        4 -123.5543 39.80925 2017
#> 3   17        6 -123.5150 39.73622 2017
#> 4   18        4 -124.0260 40.33604 2017
#> 5   24        4 -123.6221 39.64763 2017
#> 6   25        4 -123.8076 40.13879 2017
labelled_points <- get_points_from_input_data(input_data)
labelled_points
#> class       : SpatialPoints 
#> features    : 96 
#> extent      : -124.0401, -123.4844, 39.64582, 40.36147  (xmin, xmax, ymin, ymax)
#> crs         : +proj=longlat +datum=WGS84 +no_defs

Snapping labelled locations to target locations

Using snap_points_to_points() we extract the indices of target_points corresponding to the minimum distances between the labelled_points and the target_points.

snap <- snap_points_to_points(labelled_points, target_points)
length(snap)
#> [1] 96
head(snap)
#> [1] 6292 2887 3779 1792 7514 3769

From the snap indices, we can easily retrieve the training data, the corresponding groups and save.

training_data_df <- target_data_df[snap, ]
groups <- input_data$ward.grp
# write.csv(training_data_df, # saving 
#   file = file.path(out_dir, paste0(region,'_data_df.csv')), 
#   row.names = FALSE)
# write.csv(groups, # saving
#   file = file.path(out_dir, paste0(region,'_groups.csv')), 
#   row.names = FALSE)

Make training dataset

Purpose

Libraries

Loading target data

Loading labelled locations

Snapping labelled locations to target locations