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 Halogeton occurrence in relation to vegetation, abiotic, and anthropogenic features.

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

Data represent predicted cheatgrass (Bromus tectorum) cover from a quantile regression model. We used quantile regression to model cheatgrass abundance as a function of climate, weather, and disturbance, treating outputs as low to high invasion scenarios.The model was developed using cheatgrass cover data collected by the Bureau of Land Management (BLM) Assessment, Inventory, and Monitoring (AIM) program, paired with covariates representing climate, weather, fire history, and disturbance. Quantile regression estimates different coefficients for each predictor variable at each quantile of interest, allowing a given environmental variable to be more or less important at the high end of the response distribution. The predictions at each statistical quantile of interest can be interpreted as invasion scenarios, as they correspond to low, medium, and high cheatgrass cover for a given set of environmental conditions. This metadata file describes three raster files, which share a geographic extent and resolution and which represent predictions from different quantiles of the same quantile regression model.

Data represent predicted cheatgrass (Bromus tectorum) cover from a quantile regression model. We used quantile regression to model cheatgrass abundance as a function of climate, weather, and disturbance, treating outputs as low to high invasion scenarios.The model was developed using cheatgrass cover data collected by the Bureau of Land Management (BLM) Assessment, Inventory, and Monitoring (AIM) program, paired with covariates representing climate, weather, fire history, and disturbance. Quantile regression estimates different coefficients for each predictor variable at each quantile of interest, allowing a given environmental variable to be more or less important at the high end of the response distribution. The predictions at each statistical quantile of interest can be interpreted as invasion scenarios, as they correspond to low, medium, and high cheatgrass cover for a given set of environmental conditions. This metadata file describes three raster files, which share a geographic extent and resolution and which represent predictions from different quantiles of the same quantile regression model.

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 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.