Phenological dynamics of terrestrial ecosystems reflect the response of the Earth's vegetation canopy to changes in climate and hydrology and are thus important to monitor operationally. The cheatgrass phenology in the Snake River Plain (SRP) and Northern Basin and Range (NBR) based on 30m near seamless Harmonized Landsat and Sentinel-2 (HLS) Normalized Difference Vegetation Index (NDVI) weekly composites between 2016 and 2022 (Dahal et al., 2022) were processed using a 3 step method. We first identified a set of points to derive an HLS NDVI timeseries based on high probability of cheatgrass and medusahead cover. Second, we extracted the phenological metrics used for training the models by applying a decision tree processing technique on the NDVI timeseries. Finally, we utilized automated machine learning techniques to derive phenological models that were used to develop maps for the entire study area per 30-m pixel. The cheatgrass phenology model produced three metrics (Start of Season Time (SOST), End of Season Time (EOST), and Maximum Time (MAXT)) and calculated five metrics for identifying the sustained growth characteristics of cheatgrass throughout SRP and NBR ecoregions. The current suites of 30-m spatial resolution phenological metrics are SOST; Start of Season NDVI (SOSN); EOST; End of Season NDVI (EOSN); Maximum Time (MAXT); Maximum NDVI (MAXN); Duration (DUR); and Amplitude (AMP). Datasets 2017 to 2021 were developed using decision tree analysis training data from their respective year, but 2022 was developed from unseen NDVI datasets to test robustness of the phenology model. References: Dahal, D.; Pastick, N.J.; Boyte, S.P.; Parajuli, S.; Oimoen, M.J.; Megard, L.J. Multi-Species Inference of Exotic Annual and Native Perennial Grasses in Rangelands of the Western United States Using Harmonized Landsat and Sentinel-2 Data. Remote Sensing 2022, 14, doi:10.3390/rs14040807.

Phenological dynamics of terrestrial ecosystems reflect the response of the Earth's vegetation canopy to changes in climate and hydrology and are thus important to monitor operationally. The medusahead phenology in the Snake River Plain (SRP) and Northern Basin and Range (NBR) based on 30m near seamless Harmonized Landsat and Sentinel-2 (HLS) Normalized Difference Vegetation Index (NDVI) weekly composites between 2016 and 2022 (Dahal et al., 2022) were processed using a 3 step method. We first identified a set of points to derive an HLS NDVI timeseries based on high probability of cheatgrass and medusahead cover. Second, we extracted the phenological metrics used for training the models by applying a decision tree processing technique on the NDVI timeseries. Finally, we utilized automated machine learning techniques to derive phenological models that were used to develop maps for the entire study area per 30-m pixel. The medusahead phenology model produced three metrics (Start of Season Time (SOST), End of Season Time (EOST), and Maximum Time (MAXT)) and calculated five metrics for identifying the sustained growth characteristics of medusahead throughout SRP and NBR ecoregions. The current suites of 30-m spatial resolution phenological metrics are SOST; Start of Season NDVI (SOSN); EOST; End of Season NDVI (EOSN); Maximum Time (MAXT); Maximum NDVI (MAXN); Duration (DUR); and Amplitude (AMP). Datasets 2017 to 2021 were developed using decision tree analysis training data from their respective year, but 2022 was developed from unseen NDVI datasets to test robustness of the phenology model. References: Dahal, D.; Pastick, N.J.; Boyte, S.P.; Parajuli, S.; Oimoen, M.J.; Megard, L.J. Multi-Species Inference of Exotic Annual and Native Perennial Grasses in Rangelands of the Western United States Using Harmonized Landsat and Sentinel-2 Data. Remote Sensing 2022, 14, doi:10.3390/rs14040807.

Phenological dynamics of terrestrial ecosystems reflect the response of the Earth's vegetation canopy to changes in climate and hydrology and are thus important to monitor operationally. The medusahead phenology in the Snake River Plain (SRP) and Northern Basin and Range (NBR) based on 30m near seamless Harmonized Landsat and Sentinel-2 (HLS) Normalized Difference Vegetation Index (NDVI) weekly composites between 2016 and 2022 (Dahal et al., 2022) were processed using a 3 step method. We first identified a set of points to derive an HLS NDVI timeseries based on high probability of cheatgrass and medusahead cover. Second, we extracted the phenological metrics used for training the models by applying a decision tree processing technique on the NDVI timeseries. Finally, we utilized automated machine learning techniques to derive phenological models that were used to develop maps for the entire study area per 30-m pixel. The medusahead phenology model produced three metrics (Start of Season Time (SOST), End of Season Time (EOST), and Maximum Time (MAXT)) and calculated five metrics for identifying the sustained growth characteristics of medusahead throughout SRP and NBR ecoregions. The current suites of 30-m spatial resolution phenological metrics are SOST; Start of Season NDVI (SOSN); EOST; End of Season NDVI (EOSN); Maximum Time (MAXT); Maximum NDVI (MAXN); Duration (DUR); and Amplitude (AMP). Datasets 2017 to 2021 were developed using decision tree analysis training data from their respective year, but 2022 was developed from unseen NDVI datasets to test robustness of the phenology model. References: Dahal, D.; Pastick, N.J.; Boyte, S.P.; Parajuli, S.; Oimoen, M.J.; Megard, L.J. Multi-Species Inference of Exotic Annual and Native Perennial Grasses in Rangelands of the Western United States Using Harmonized Landsat and Sentinel-2 Data. Remote Sensing 2022, 14, doi:10.3390/rs14040807.

The dataset provides a spatially explicit estimate of 2019 herbaceous annual percent cover predicted on May 1st with an emphasis on annual grasses. The estimate is based on the mean output of two regression-tree models. For one model, we include, as an independent variable amongst other independent variables, a dataset that is the mean of 17-years of annual herbaceous percent cover (https://doi.org/10.5066/F71J98QK). This model's test mean error rate (n = 1670), based on nine different randomizations, equals 4.9% with a standard deviation of +/- 0.15. A second model was developed that did not include the mean of 17-years of annual herbaceous percent cover, and this model's test mean error rate (n = 1670), based on nine different randomizations, equals 5.0% with a standard deviation of +/- 0.11. The mean value for each pixel represents the May 2019 early estimate of annual herbaceous percent cover. The pixel values for the merged 2019 dataset range from 0 to100 percent cover with an overall mean value of 11.20 and a standard deviation of +/-9.77. This dataset is generated by integrating ground-truth measurements of annual herbaceous percent cover with 250-m spatial resolution eMODIS NDVI satellite derived data and geophysical variables into regression-tree software. The geographic coverage includes the Great Basin, the Snake River Plain, the state of Wyoming, and contiguous areas. We applied a mask to areas above 2250-m elevation because annual grasses are unlikely to exist at substantial cover above this threshold. To target likely sagebrush ecosystems, the mask also hid pixels classified as something other than shrub or grassland/herbaceous by the 2011 National Land Cover Dataset (NLCD). Cheatgrass (Bromus tectorum) is the most common annual grass in the study area. It grows from seed, usually in spring, matures quickly, produces seed, and dies. After dying, cheatgrass contributes fine fuels that facilitate fire ignition and spread throughout sagebrush ecosystems. These fires remove sagebrush stands. Increasing fire frequencies, land management practices, and development have all contributed to the fragmentation of the once expansive sagebrush ecosystems. These ecosystems are critical for water quality, reduced fire threats, and the survival of sagebrush-dependent wildlife.

The dataset provides a spatially explicit estimate of 2019 herbaceous annual percent cover predicted on May 1st with an emphasis on annual grasses. The estimate is based on the mean output of two regression-tree models. For one model, we include, as an independent variable amongst other independent variables, a dataset that is the mean of 17-years of annual herbaceous percent cover (https://doi.org/10.5066/F71J98QK). This model's test mean error rate (n = 1670), based on nine different randomizations, equals 4.9% with a standard deviation of +/- 0.15. A second model was developed that did not include the mean of 17-years of annual herbaceous percent cover, and this model's test mean error rate (n = 1670), based on nine different randomizations, equals 5.0% with a standard deviation of +/- 0.11. The mean value for each pixel represents the May 2019 early estimate of annual herbaceous percent cover. The pixel values for the merged 2019 dataset range from 0 to100 percent cover with an overall mean value of 11.20 and a standard deviation of +/-9.77. This dataset is generated by integrating ground-truth measurements of annual herbaceous percent cover with 250-m spatial resolution eMODIS NDVI satellite derived data and geophysical variables into regression-tree software. The geographic coverage includes the Great Basin, the Snake River Plain, the state of Wyoming, and contiguous areas. We applied a mask to areas above 2250-m elevation because annual grasses are unlikely to exist at substantial cover above this threshold. To target likely sagebrush ecosystems, the mask also hid pixels classified as something other than shrub or grassland/herbaceous by the 2011 National Land Cover Dataset (NLCD). Cheatgrass (Bromus tectorum) is the most common annual grass in the study area. It grows from seed, usually in spring, matures quickly, produces seed, and dies. After dying, cheatgrass contributes fine fuels that facilitate fire ignition and spread throughout sagebrush ecosystems. These fires remove sagebrush stands. Increasing fire frequencies, land management practices, and development have all contributed to the fragmentation of the once expansive sagebrush ecosystems. These ecosystems are critical for water quality, reduced fire threats, and the survival of sagebrush-dependent wildlife.

Probability map of Cheatgrass occurrence in relation to vegetation, abiotic and anthropogenic features.

Probability map of Cheatgrass occurrence in relation to vegetation, abiotic, and anthropogenic features.

Probability map of Cheatgrass occurrence in relation to vegetation, abiotic, and anthropogenic features.

Probability map of Cheatgrass occurrence in relation to vegetation, abiotic and anthropogenic features.

Probability map of Cheatgrass occurrence in relation to vegetation, abiotic and anthropogenic features.