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 Exotic Annual Grass (EAG) phenology in the western U.S. rangeland based on 30m near seamless Harmonized Landsat and Sentinel-2 (HLS) Normalized Difference Vegetation Index (NDVI) weekly composites between 2016 and 2021 (Dahal et al., 2022) were processed using these 3 methods: (1) NDVI threshold-based method, (2) manual phenological metrics, and (3) modeling and mapping. The EAG phenology model produced eight metrics identifying the sustainable growth characteristics of 16 EAG species throughout level III Commission for Environmental Cooperation ecoregions, which cover over 190 million hectares of western U.S. potential rangeland for 2017 to 2021. The current suites of 30-m spatial resolution phenological metrics are Start of Season Time (SOST); Start of Season NDVI (SOSN); End of Season Time (EOST); End of Season NDVI (EOSN); Maximum Time (MAXT); Maximum NDVI (MAXN); Duration (DUR); and Amplitude (AMP). Datasets 2017 to 2020 were developed using manually interpreted training data from their respective year, but 2021 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 reflect the vegetation response to changes in weather, vegetation composition, plant life stages pertinent to both agricultural and fire management and are thus important to monitor operationally. The Exotic Annual Grass (EAG) phenology in the western U.S. rangeland based on 30-m Harmonized Landsat and Sentinel-2 (HLS) Normalized Difference Vegetation Index (NDVI) weekly composites between 2016 and 2024 (Dahal et al., 2022) were processed using these 3 methods: (1) NDVI threshold-based method, (2) manual phenological metrics, and (3) modeling and mapping. The EAG phenology model produced two metrics (Start of Season Time [SOST] and End of Season Time [EOST]) and calculated six metrics for identifying the sustained growth characteristics of 15 EAG species throughout 190 million hectares of western U.S. rangeland for 2017 to 2024. The current suite of 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 from 2017 to 2021 were developed using manually interpreted training data specific to each year, while datasets from 2022 to 2024 were produced using the same training set supplemented with additional automated datasets. 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 reflect the vegetation response to changes in weather, vegetation composition, plant life stages pertinent to both agricultural and fire management and are thus important to monitor operationally. The Exotic Annual Grass (EAG) phenology in the western U.S. rangeland based on 30-m Harmonized Landsat and Sentinel-2 (HLS) Normalized Difference Vegetation Index (NDVI) weekly composites between 2016 and 2024 (Dahal et al., 2022) were processed using these 3 methods: (1) NDVI threshold-based method, (2) manual phenological metrics, and (3) modeling and mapping. The EAG phenology model produced two metrics (Start of Season Time [SOST] and End of Season Time [EOST]) and calculated six metrics for identifying the sustained growth characteristics of 15 EAG species throughout 190 million hectares of western U.S. rangeland for 2017 to 2024. The current suite of 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 from 2017 to 2021 were developed using manually interpreted training data specific to each year, while datasets from 2022 to 2024 were produced using the same training set supplemented with additional automated datasets. 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 Exotic Annual Grass (EAG) phenology in the western U.S. rangeland based on 30m near seamless Harmonized Landsat and Sentinel-2 (HLS) Normalized Difference Vegetation Index (NDVI) weekly composites between 2016 and 2023 (Dahal et al., 2022) were processed using these 3 methods: (1) NDVI threshold-based method, (2) manual phenological metrics, and (3) modeling and mapping. The EAG phenology model produced two metrics (Start of Season Time (SOST) and End of Season Time (EOST)) and calculated six metrics for identifying the sustained growth characteristics of 16 EAG species throughout level III Commission for Environmental Cooperation ecoregions, which cover over 190 million hectares of western U.S. potential rangeland for 2017 to 2021. 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 manually interpreted training data from their respective year, but 2022 and 2023 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.

Invasion of exotic annual grass (EAG), such as cheatgrass (Bromus tectorum), red brome (Bromus rubens), and medusahead (Taeniatherum caput-medusae), could have irreversible degradation impact to arid and semiarid rangeland ecosystems in the western United States. The distribution and abundance of these EAG species are highly influenced by weather variables such as temperature and precipitation. We set out to develop a machine learning modelling approach using a lightGBM algorithm to predict how changes in annual and immediate past precipitation regimes impact the abundance of EAG in the study area. The predictive model primarily utilized edaphic and weather variables and a seed source proxy from previous years to make the predictions. We achieved strong training accuracy (r= 0.95 and MdAE=2.36 of percent cover) and test accuracy (r= 0.79 and MdAE=4.54 of percent cover). We predicted five versions of EAG percent cover maps for 2022 with different precipitation scenarios, i.e., with the 9-year average, half of the average, three fourth of the average, one and half of the average, and twice the average precipitation. Five versions of spatially explicit EAG percent cover 2022 datasets can provide valuable information to local and regional land managers so they would know what EAG abundance would look like with certain precipitation scenario.

Invasion of exotic annual grass (EAG), such as cheatgrass (Bromus tectorum), red brome (Bromus rubens), and medusahead (Taeniatherum caput-medusae), could have irreversible degradation impact to arid and semiarid rangeland ecosystems in the western United States. The distribution and abundance of these EAG species are highly influenced by weather variables such as temperature and precipitation. We set out to develop a machine learning modelling approach using a lightGBM algorithm to predict how changes in annual and immediate past precipitation regimes impact the abundance of EAG in the study area. The predictive model primarily utilized edaphic and weather variables and a seed source proxy from previous years to make the predictions. We achieved strong training accuracy (r= 0.95 and MdAE=2.36 of percent cover) and test accuracy (r= 0.79 and MdAE=4.54 of percent cover). We predicted five versions of EAG percent cover maps for 2022 with different precipitation scenarios, i.e., with the 9-year average, half of the average, three fourth of the average, one and half of the average, and twice the average precipitation. Five versions of spatially explicit EAG percent cover 2022 datasets can provide valuable information to local and regional land managers so they would know what EAG abundance would look like with certain precipitation scenario.

The dryland ecosystems of the western United States have been invaded by exotic annual grasses, such as cheatgrass (Bromus tectorum L.), that has promoted increased fire activity and reduced biodiversity detrimental to socio-environmental systems. The use of remote sensing tools to monitor exotic annual grass cover and dynamics over large areas can support early detection and rapid response initiatives. This dataset was generated using in situ observations from Bureau of Land Management's (BLM) Assessment, Inventory, and Monitoring data (AIM) plots, weekly composites of harmonized Landsat and Sentinel-2 (HLS) data, relevant environmental, vegetation, remotely sensed, and geophysical factors and machine learning techniques to develop fractional estimates of exotic annual grass cover at a 30-m spatial resolution for 2016 to 2019. A total of 10,906 AIM plots from years 2016 - 2019 were used to train an ensemble of regression tree models (n=5). Besides cheatgrass (Bromus tectorum), other species such as Bromus arvensis L., Bromus briziformis, Bromus catharticus Vahl, Bromus commutatus, Bromus diandrus, Bromus hordeaceus L., Bromus japonicus, Bromus mardritensis L.,Bromus racemosus, Bromus rubens L., Bromus secalinus L., Bromus texensis (Shear) Hitchc., Taeniatherum caput-medusae were included in the study. The geographic coverage includes rangelands in the Great Basin, the Snake River Plain, the state of Wyoming, and contiguous areas.

The dryland ecosystems of the western United States have been invaded by exotic annual grasses, such as cheatgrass (Bromus tectorum L.), that has promoted increased fire activity and reduced biodiversity detrimental to socio-environmental systems. The use of remote sensing tools to monitor exotic annual grass cover and dynamics over large areas can support early detection and rapid response initiatives. This dataset was generated using in situ observations from Bureau of Land Management's (BLM) Assessment, Inventory, and Monitoring data (AIM) plots, weekly composites of harmonized Landsat and Sentinel-2 (HLS) data, relevant environmental, vegetation, remotely sensed, and geophysical factors and machine learning techniques to develop fractional estimates of exotic annual grass cover at a 30-m spatial resolution for 2016 to 2019. A total of 10,906 AIM plots from years 2016 - 2019 were used to train an ensemble of regression tree models (n=5). Besides cheatgrass (Bromus tectorum), other species such as Bromus arvensis L., Bromus briziformis, Bromus catharticus Vahl, Bromus commutatus, Bromus diandrus, Bromus hordeaceus L., Bromus japonicus, Bromus mardritensis L.,Bromus racemosus, Bromus rubens L., Bromus secalinus L., Bromus texensis (Shear) Hitchc., Taeniatherum caput-medusae were included in the study. The geographic coverage includes rangelands in the Great Basin, the Snake River Plain, the state of Wyoming, and contiguous areas.

We provide fractional cover estimates for exotic annual grass (EAG) species and one native perennial grass species on a weekly basis from mid-April to late June 2025. The cover estimates reflect actual conditions of the previous week and are released in an expedited manner, within 7-13 days of the latest satellite observation used for that weekly prediction. Each weekly release contains five fractional cover maps along with their corresponding confidence maps. The following 16 species are included in the overall EAG cover estimate (species followed by * indicate specific maps for that species); field brome* (Bromus arvensis), rattlesnake brome (Bromus briziformis), rescuegrass (Bromus catharticus) Bald brome (Bromus commutatus and Bromus racemosus), ripgut brome (Bromus diandrus), soft brome (Bromus hordeaceus and Bromus hordeaceus spp. hordeaceus), Japanese brome (Bromus japonicus), compact brome (Bromus madritensis and Bromus madritensis ssp. Rubens), red brome (Bromus rubens), rye brome (Bromus secalinus), cheatgrass* (Bromus tectorum), Texas brome (Bromus texensis), medusahead* (Taeniatherum caput-medusae). Sandberg blue grass (Poa secunda) is not considered an EAG by this project or included in the EAG layer. We map Poa secunda separately as it can have similar phenology to many invasive grasses such as cheatgrass. These datasets were generated leveraging field observations from Bureau of Land Management (BLM) Assessment, Inventory, and Monitoring (AIM) data plots; Harmonized Landsat and Sentinel-2 (HLS) based Normalized Difference Vegetation Index (NDVI); other relevant environmental, vegetation, remotely sensed, and geophysical drivers; and artificial intelligence/machine learning techniques. A total of 40,154 AIM plots from years 2016–2024 were used to train an ensemble of five-fold regression-tree models using a cross-validation approach (each observation was used as test data once and as training data four times) that developed all the fractional cover maps. The geographic coverage includes arid and semi-arid rangelands in the western U.S classified as shrubs or grassland/herbaceous by the 2023 Land Cover product from Annual National Land Cover Database (NLCD) CONUS Collection 1.0 at or below 2350-m elevation. Note: Maps of April 18th, 2025, were developed using satellite observation data no later than April 12. Maps of April 25th, 2025, were developed using satellite observation data no later than April 19. Maps of May 2nd, 2025, were developed using satellite observation data no later than April 26. Maps of May 9th, 2025, were developed using satellite observation data no later than May 3. Maps of May 16th, 2025, were developed using satellite observation data no later than May 10. Maps of May 23rd, 2025, were developed using satellite observation data no later than May 17. Maps of May 30th, 2025, were developed using satellite observation data no later than May 24. Maps of June 6th, 2025, were developed using satellite observation data no later than May 30. Releases: First Release: April 18, 2025 (ver. 1.0). Revision: April 25, 2025 (ver. 2.0). Revision: May 2, 2025 (ver. 3.0). Revision: May 9, 2025 (ver. 4.0). Revision: May 16, 2025 (ver. 5.0). Revision: May 22, 2025 (ver. 6.0). Revision: May 30, 2025 (ver. 7.0). Revision: June 6, 2025 (ver. 8.0)

We provide fractional cover estimates for exotic annual grass (EAG) species and one native perennial grass species on a weekly basis from mid-April to late June 2025. The cover estimates reflect actual conditions of the previous week and are released in an expedited manner, within 7-13 days of the latest satellite observation used for that weekly prediction. Each weekly release contains five fractional cover maps along with their corresponding confidence maps. The following 16 species are included in the overall EAG cover estimate (species followed by * indicate specific maps for that species); field brome* (Bromus arvensis), rattlesnake brome (Bromus briziformis), rescuegrass (Bromus catharticus) Bald brome (Bromus commutatus and Bromus racemosus), ripgut brome (Bromus diandrus), soft brome (Bromus hordeaceus and Bromus hordeaceus spp. hordeaceus), Japanese brome (Bromus japonicus), compact brome (Bromus madritensis and Bromus madritensis ssp. Rubens), red brome (Bromus rubens), rye brome (Bromus secalinus), cheatgrass* (Bromus tectorum), Texas brome (Bromus texensis), medusahead* (Taeniatherum caput-medusae). Sandberg blue grass (Poa secunda) is not considered an EAG by this project or included in the EAG layer. We map Poa secunda separately as it can have similar phenology to many invasive grasses such as cheatgrass. These datasets were generated leveraging field observations from Bureau of Land Management (BLM) Assessment, Inventory, and Monitoring (AIM) data plots; Harmonized Landsat and Sentinel-2 (HLS) based Normalized Difference Vegetation Index (NDVI); other relevant environmental, vegetation, remotely sensed, and geophysical drivers; and artificial intelligence/machine learning techniques. A total of 40,154 AIM plots from years 2016–2024 were used to train an ensemble of five-fold regression-tree models using a cross-validation approach (each observation was used as test data once and as training data four times) that developed all the fractional cover maps. The geographic coverage includes arid and semi-arid rangelands in the western U.S classified as shrubs or grassland/herbaceous by the 2023 Land Cover product from Annual National Land Cover Database (NLCD) CONUS Collection 1.0 at or below 2350-m elevation. Note: Maps released on April 18th, 2025, were developed using satellite observation data no later than April 12. Maps released on April 25th, 2025, were developed using satellite observation data no later than April 19. Maps released on May 2nd, 2025, were developed using satellite observation data no later than April 26. Maps released on May 9th, 2025, were developed using satellite observation data no later than May 3. Maps released on May 16th, 2025, were developed using satellite observation data no later than May 10. Maps released on May 23rd, 2025, were developed using satellite observation data no later than May 17. Maps released on May 30th, 2025, were developed using satellite observation data no later than May 24. Maps released on June 6th, 2025, were developed using satellite observation data no later than May 30. Maps released on June 24th, 2025, were developed using satellite observation data no later than June 1. Maps released on June 20th, 2025, were developed using satellite observation data no later than June 14. Releases: First Release: April 18, 2025 (ver. 1.0). Revision: April 25, 2025 (ver. 2.0). Revision: May 2, 2025 (ver. 3.0). Revision: May 9, 2025 (ver. 4.0). Revision: May 16, 2025 (ver. 5.0). Revision: May 22, 2025 (ver. 6.0). Revision: May 30, 2025 (ver. 7.0). Revision: June 6, 2025 (ver. 8.0), Revision: June 24, 2025 (ver. 9.0), note that week 9 was released after week 10. Revision: June 20, 2025 (ver. 10.0).