Landsat:LiDAR-AGB v0.0.5 Map Accuracy - Holdout Plots Only

Map accuracy/agreement assessment following the Riemann et. al. framework.

Lucas Johnson
2021-07-29

Description

Map accuracy assessment for the v0.0.5 model-weighted-ensemble Landsat model trained on LiDAR-AGB surfaces. FIA data inventoried between 2013 and 2019 were considered for this assessment.

Model Document

Riemann et. al.

Branch used to produce this document: lj_landsat-lidar-0.0.5-holdout

FIA plot inclusion criteria

Masking

No masking applied.

Agreement Statistics (SI corrected)

Table 1: Plot:Pixel Pooled x LCPRI
LCPRI Group n PPH Mean FIA MBE RMSE MAE R2 KS AC ACs ACu
1 pooled 405 NA 6.03 52.86 61.04 54.68 0.05 0.91 0.21 0.40 0.81
2 pooled 967 NA 9.43 25.01 34.50 29.85 0.24 0.81 0.28 0.58 0.70
3 pooled 75 NA 29.73 24.55 39.26 33.92 0.49 0.56 0.47 0.71 0.76
4 pooled 1862 NA 129.80 11.99 60.21 48.41 0.30 0.20 0.00 0.65 0.22
5 pooled 100 NA 11.60 56.53 65.54 57.88 0.15 0.85 0.30 0.48 0.82
6 pooled 211 NA 77.91 9.27 57.43 46.31 0.43 0.30 0.02 0.64 0.38
8 pooled 12 NA 8.94 41.61 45.99 41.77 0.10 0.83 0.28 0.40 0.87
Table 2: Plot:Pixel Comparison
Group n PPH Mean FIA MBE RMSE MAE R2 KS AC ACs ACu
target_2014 604 NA 78.49 20.16 53.94 43.56 0.63 0.37 0.57 0.86 0.71
target_2015 550 NA 71.95 23.61 54.27 43.65 0.62 0.41 0.60 0.87 0.73
target_2016 526 NA 77.50 19.83 52.52 42.80 0.65 0.38 0.60 0.86 0.74
target_2017 451 NA 77.24 18.91 56.52 46.00 0.65 0.42 0.56 0.83 0.72
target_2018 403 NA 72.74 23.93 56.13 45.42 0.61 0.42 0.57 0.85 0.72
target_2019 420 NA 69.33 22.51 54.26 44.59 0.63 0.45 0.59 0.86 0.73
pooled 3632 NA 75.21 21.44 54.22 43.99 0.63 0.39 0.58 0.86 0.72
Table 3: 8660 Ha Hex
Group n PPH Mean FIA MBE RMSE MAE R2 KS AC ACs ACu
target_2014 565 1.07 76.82 21.01 52.21 42.41 0.63 0.36 0.59 0.87 0.72
target_2015 490 1.12 71.64 24.55 52.72 42.35 0.63 0.39 0.61 0.87 0.74
target_2016 478 1.10 76.55 20.38 51.98 42.39 0.65 0.38 0.60 0.87 0.74
target_2017 424 1.06 78.32 18.52 55.98 45.17 0.66 0.41 0.56 0.83 0.73
target_2018 377 1.07 71.60 24.81 54.45 44.03 0.62 0.41 0.60 0.86 0.74
target_2019 382 1.10 69.81 22.30 53.93 44.13 0.63 0.43 0.59 0.86 0.73
pooled 1351 2.19 74.66 22.16 45.18 36.48 0.65 0.27 0.63 0.86 0.77
Table 4: 78100 Ha Hex
Group n PPH Mean FIA MBE RMSE MAE R2 KS AC ACs ACu
target_2014 180 3.36 73.39 23.67 38.25 31.29 0.72 0.27 0.69 0.85 0.84
target_2015 173 3.18 69.61 25.72 42.30 34.20 0.61 0.29 0.61 0.83 0.79
target_2016 171 3.08 76.95 19.65 41.87 33.20 0.68 0.24 0.61 0.83 0.78
target_2017 165 2.73 73.77 20.81 42.49 33.96 0.66 0.27 0.62 0.84 0.78
target_2018 160 2.52 69.44 26.89 44.36 35.43 0.63 0.29 0.62 0.82 0.80
target_2019 162 2.59 66.60 25.48 42.93 35.09 0.64 0.31 0.64 0.85 0.79
pooled 203 14.55 69.40 24.89 33.76 27.09 0.72 0.29 0.67 0.80 0.87
Table 5: 216500 Ha Hex
Group n PPH Mean FIA MBE RMSE MAE R2 KS AC ACs ACu
target_2014 74 8.16 73.38 21.60 34.09 28.25 0.72 0.28 0.66 0.81 0.85
target_2015 76 7.24 69.19 26.55 41.22 32.16 0.47 0.33 0.52 0.77 0.74
target_2016 75 7.01 73.60 22.34 34.39 28.04 0.76 0.24 0.71 0.85 0.87
target_2017 72 6.26 73.94 21.19 33.64 27.77 0.72 0.33 0.69 0.84 0.85
target_2018 74 5.45 63.59 29.35 40.82 31.53 0.62 0.30 0.63 0.80 0.83
target_2019 75 5.60 64.86 27.57 41.52 33.18 0.61 0.29 0.62 0.80 0.81
pooled 83 35.59 70.45 24.21 34.69 27.30 0.63 0.34 0.61 0.78 0.83

ECDF Comparisons Across Scales - FIA Plots vs Mapped (SI corrected)

1:1 and GMFR Lines Across Scales - FIA Plots vs Mapped (SI corrected)

Spatial/Distribution Patterns of Local Differences (SI Corrected)

Target 2014 Distribution

Target 2016 Distribution

Target 2019 Distribution

Pooled Distribution

Spatial Differences

Patterns of Local Variability (SI Corrected)

Corrections

If you see mistakes or want to suggest changes, please create an issue on the source repository.

Citation

For attribution, please cite this work as

Johnson (2021, July 29). CAFRI Labs: Landsat:LiDAR-AGB v0.0.5 Map Accuracy - Holdout Plots Only. Retrieved from https://cafri-labs.github.io/acceptable-growing-stock/posts/landsatlidar-agb-v005-map-accuracy-holdout-plots-only/

BibTeX citation

@misc{johnson2021landsat:lidar-agb,
  author = {Johnson, Lucas},
  title = {CAFRI Labs: Landsat:LiDAR-AGB v0.0.5 Map Accuracy - Holdout Plots Only},
  url = {https://cafri-labs.github.io/acceptable-growing-stock/posts/landsatlidar-agb-v005-map-accuracy-holdout-plots-only/},
  year = {2021}
}