The USDA Conservation Reserve Program (CRP) works with farmers and landowners to implement conservation management practices on enrolled lands, with paid contracts ranging from 10 to 15 years in length. The CRP Grasslands practices target restoration of agricultural grassland systems by augmenting native vegetation for pollinators, providing habitat for grassland plants and animals, increasing biodiversity, reducing soil erosion, and improving water quality. The USDA’s CRP has been successful in improving the conservation value of millions of acres of farmlands; however, the program currently lacks spatially explicit information on land cover and vegetation within CRP-enrolled tracts. 

In partnership with the USDA FSA program, the Conservation Biology Institute (CBI) used a combination of remote sensing and machine learning algorithms deployed on the innovative cloud-computing platform, Google Earth Engine, to map grassland characteristics. We used a rich suite of enviro-climatic data, multiple sources of satellite imagery, and Random Forest modeling techniques to predict land cover for study areas in Washington, Colorado, and Kansas, where CRP Grasslands holdings are most prevalent. We used machine learning to create predictive maps of vegetation type by leveraging an extensive set of satellite-derived variables, environmental layers, and federal survey data (from BLM’s AIM and USDA NRCS’s NRI programs). Our initial investigation utilized Landsat 8 satellite data to model vegetation cover across the Washington study area and then scaled up to the Colorado-Kansas study area. The Washington study site was selected for further model enhancements and an in-depth comparison of Landsat 8, Sentinel-2, and MODIS satellite imagery, to evaluate differences in model development and performance among sensor types. We generated vegetation cover predictions for the year 2019 using Random Forest classification models. Classified outputs for the five vegetation cover models – annual grass, perennial grass, annual forb, perennial forb, and bare soil – were post-processed to exclude water and urban land cover and areas that were not relevant for mapping grasslands.

Mapped outputs showing vegetation percent cover predictions from our pilot project have been integrated into CBI’s CRP online decision support tool. This online tool offers functionality for managers and landowners to view, filter, compare and summarize geospatial information relevant for assessing CRP tracts in the study areas. You will need permission from USDA to use the tool, but it is available at https://crptool.org/. Anyone can view the design of the tool at USDA CRPtool.

You can read more details in the following publication.

Degagne, Rebecca; Pizzino, Declan; Friedrich, Hannah; Gough, Mike; Joseph, Gladwin; Strittholt, James; et al. (2022): Mapping Conservation Reserve Program Grasslands in Washington, Colorado, and Kansas with Remote Sensing and Machine Learning. figshare. Journal contribution. https://doi.org/10.6084/m9.figshare.19141853.v1 

Environmental scientists and decision-makers often employ mapping and modeling to address a wide range of complex environmental challenges. Barriers practitioners face include long data processing times, lack of access to robust and up-to-date datasets, and complex programming languages and libraries.

GEODE (the Global Environmental Online Decision Engine) is a web-based mapping and modeling system currently under development at the Conservation Biology Institute. The goal of the GEODE project is to put the power of Google Earth Engine into the hands of environmental scientists, decision makers, and land managers – no programming experience required. 

GEODE is a complete spatial decision support modeling system that can be used to help answer complex management questions and provide critical insight into the challenging environmental problems that threaten biodiversity and the planet’s fragile ecosystems. Users will be able to publish, share, edit, and modify GEODE models so results can be applied to environmental issues anywhere across the globe.

Empowered by GEODE, users benefit from:

By coupling the modeling framework of GEODE with the power of Google Earth Engine, anyone able to use a simple interface will have access the power Google Earth Engine has to offer – and that is a lot!

Conservation Biology Institute is working in partnership with Riverside County Habitat Conservation Agency, Bureau of Land Management, U.S. Fish and Wildlife Service, San Diego Zoo Wildlife Alliance Academy, and others to develop and implement a rangewide conservation plan for the Stephens’ kangaroo rat (Dipodomys stephensi, SKR), a tiny rodent native to Southern California’s shrinking grassland habitats.

The SKR Rangewide Management and Monitoring Plan, developed in collaboration with species managers, researchers, and land owners, complements existing management plans rather than replaces them, recognizing that each location has unique management priorities. Coordinating across local conservation efforts will facilitate collaborative conservation action across the species’ entire range.

The SKR Plan recommends management actions to improve habitat and ameliorate threats from human activities and climate change and provides  a standardized monitoring protocol to track the species’ population status and trends. CBI has developed a customized field data collection application using ArcGIS Field Maps, and our SKR data management team supports the field monitoring effort and ensures long-term integrity of the data in partnership with USFWS’ Ecosphere Program.

This work builds upon a habitat suitability model developed in 2019 by Conservation Biology Institute using Sentinel-2 satellite imagery and being updated in time to support the 2024 monitoring season. These updatable landscape-scale habitat maps are the foundation for statistically-defensible monitoring and play a key role in planning coordinated conservation of the species.

This work is funded by the U.S. Bureau of Land Management. For more information about this effort, please contact Wayne Spencer at wdspencer@consbio.org or Brian Shomo at bshomo@wrcog.us.

Please see the SKR Rangewide Management and Monitoring Website for The SKR Rangewide Management and Monitoring Plan and Protocol, as well as other documents, maps, and data from this project.

Stephens’ kangaroo rat (Dipodomys stephensi, SKR). Photo by Moose Peterson.

Cachuma Resource Conservation District (RCD) is working in partnership with Conservation Biology Institute, LegacyWorks, and Sharyn Main Consulting on the Regional Priority Plan to Reduce Wildfire Risk and Improve Forest Health in Santa Barbara County (RPP), which is a flagship project of the Santa Barbara County Conservation Blueprint. Funded by the California Coastal Conservancy, the RPP helps with the planning, mapping, and prioritization of projects that will proactively address wildfire threat in Santa Barbara County, as well as improve forest and habitat health.

The RPP is a multi-prong collaboration, which focuses on public and private land in the wildland/urban interface (WUI). CBI is the lead for a component of the project, to develop a sophisticated decision-support mapping tool to not only predict areas of high fire-risk on a landscape scale, but also help the community prioritize where fire risk mitigation projects should occur. The tool will serve as a community resource within the Santa Barbara County Conservation Blueprint and should improve communication, network building, and support community priorities through a regional approach to fire resilience and habitat health. The project team is talking with the many agencies and stakeholders involved, and facilitating the collaborative decision-making process.

CBI is collaborating with the United States Department of Agriculture (USDA) and the Farm Service Agency to produce an online application depicting ecological and economic features across Bottomland Hardwood Forest Conservation Reserve Program lands in the state of Mississippi. The Conservation Reserve Program (CRP) pays landowners to maintain these Bottomland Hardwood Forests providing important ecological benefits such as removing nitrogen and phosphorus from water, storing flood waters and reducing downstream flooding, trapping sediment, and promoting carbon sequestration. These benefits provided by the CRP are in addition to the restoration and enhancement of wetlands and wildlife habitat. The key ecological and economic features across these CRP lands will be estimated using remote sensing satellite imagery from the Sentinel satellite platform and machine learning modeling using a random forest approach. Additionally CBI staff will be conducting on the ground assessments of the ecological metrics during the 2019 field season. 

By providing an online platform that provides metrics on these CRP lands, the USDA Farm Service Agency will be able to better monitor and evaluate existing acres of Bottomland Hardwood Forests that are part of the Conservation Reserve Program. This project is a pilot to determine the utility of the online platform and remote sensing methods, which if proven useful can be expanded to all regions where the CRP restores and enhances Bottomland Hardwood Forests.

The Random Forest modelling process was used to estimate various forest biometric measurements like biomass, density, height, etc., for CRP lands in Mississippi. These were also converted to economic values using standard procedures. We used Forest Inventory and Assessment (FIA) as training data and used field samples to augment the validation of the modelling process.  Predicated outputs collected All these outputs were spatialized and incorporated into a customized tool for the USDA Conservation Reserve program. 

The CRP tool allows USDA staff, land owners, and third-party organizations to view pertinent spatial information and guide decision making in relation to the status of CRP farms in Mississippi state. This tool allows one to summarize, filter and compare CRP farm tracts across counties and watersheds. You can also download reports in either of two appropriate formats (PDF or CSV). We have also included three different base layers, and relevant contextual data layers that you can view in relation to the CRP farm tracts. You will need permission from USDA to use the tool, but it is available at www.crptool.org. Anyone can view the design of the tool at https://www.sketch.com/s/feba6e2a-ff3e-4c3c-8d2d-9ea4f6bdc896.

CBI initially developed predictive maps of tree height, tree density, biomass, basal area, and forest type using Random Forest machine learning models. Numerous satellite-derived indices from the European Space Agency’s (ESA) Sentinel-1 and Sentinel-2 sensors, in addition to soils and topography data, were used as predictor inputs. We then refined these predictive models, focusing primarily on biomass improvements, by implementing new methods for processing Sentinel-1 imagery on the cloud computing platform Google Earth Engine (GEE); significantly updating model code; and incorporating preliminary data products derived from NASA’s spaceborne LiDAR mission – the Global Ecosystem Dynamics Investigation (GEDI).  We refined the GEDI LiDAR-derived data products and included them in our models, and overall accuracy for the four forest regression models ranged from 57% to 91%. The Biomass model saw the greatest improvement in accuracy with the R2 increasing by 8%, from 49% to 57%. The Basal Area and Tree Height models both had minor 1-2% increases in accuracy, while the Tree Density model had no improvement. The Forest Type classification model had a negligible improvement in overall accuracy, however, the Elm/Ash/Cottonwood class increased in accuracy by ~6%, from 64% to 70%.

You can get more details in this publication. Degagne, R., Pizzino, D., Friedrich, H, Gough, M., Joseph, G., Iovanna, R., Smith, C. and Strittholt, J. 2022.  Mississippi CRP Forest Remote Sensing with Preliminary Global Ecosystem and Dynamics (GEDI) Mission Derived Data Products. CBI Technical Report 2022-1. 40 pp. (10.6084/m9.figshare.19142147)

Wildfires are becoming larger and more severe, causing negative impacts on our natural ecosystems. These post-fire impacts include invasions of exotic plants and an increase in the risk of mudslides, erosion, and siltation of important stream habitat. It is a daunting challenge for resource managers to determine where restoration can do the most good.

In this pilot project, CBI worked with the Santa Barbara Botanic Garden to develop and test online software coupled with a citizen-science process that helps resource managers identify the best candidate locations for restoration in the aftermath of the Thomas and Whittier Fires in Santa Barbara County.

Spatial data about the landscape are combined in a model that provides a preliminary prioritization map, which is then refined using field observations of professionals and community scientists in the Spring following a fire. The sites can then be visited in person to make the final decision about where to focus restoration efforts to maximize the return on the investment. 

Figure 1. A flow chart displaying the steps involved in prioritizing areas for post-fire restoration  

The community scientists used iNaturalist to record their observations and assist in identifications.  You can see the more than 5,000 observations collected so far on iNaturalist here!

How You Can Learn More :

Watch this short video about the project.

View the model with prioritized restoration locations here.

Explore the restoration prioritization map together with other important data layers and photographs in Data Basin.

Read more technical details in this article. 

Email john.gallo@consbio.org to be notified of community science opportunities when they arise.

Santa Barbara Botanical Garden staff and volunteers. (Photo credits: Denise Knapp).
Identifying plants
Horses grazing in a field at sunset

The Stephens’ kangaroo rat (Dipodomys stephensi) is an endangered mammal of grassland habitats in southern California. CBI is helping to conserve the species using satellite technology and advanced mapping techniques.

Kangaroo rats (or Krats, as biologists often call them) are seed-eating rodents restricted to arid regions of southwestern North America. The 20 or so Krat species are biologically similar to jerboas of the Mideast–and like mideastern jerboas and the kangaroos of Australia, they use their large hind limbs to bound efficiently and elusively through open habitats, especially deserts and grasslands. Being mostly nocturnal, Krats also have huge eyes for night vision and keen ears for hearing predators, like owls and foxes.

Stephens’ kangaroo rat (or biological shorthand, SKR) occupies open, undeveloped grasslands in western Riverside and San Diego counties in southern California. Because much of their habitat has been paved over and fragmented by development, the SKR was listed as Endangered under the the US Endangered Species Act and Threatened under the California ESA in the 1980s. Numerous ecological reserves have since been established to conserve remaining populations. Unfortunately, these scattered Krat reserves are not consistently managed, monitored, or even understood by the responsible resource management agencies, largely because it is difficult to map and track suitable habitat conditions over space and time. Traditional habitat variables, such as vegetation and soil types, are not nuanced enough to reflect the on-ground conditions that SKR need, and management and monitoring approaches differ amongst the reserves.

CBI is helping remedy this situation by using satellite imagery and innovative habitat modeling techniques to develop reliable statistical models to map habitat suitability across the species’ geographic range. In partnership with the US Fish and Wildlife Service, the Riverside County Habitat Conservation Agency (RCHCA), and species experts, we are developing a coordinated approach to mapping SKR habitat suitability to manage and monitor the species in a more scientifically consistent and justified manner. Specifically, we are using European Sentinel-2 satellite imagery, in concert with other reliable geographic data, to develop habitat suitability maps that can be routinely updated over time across the species range as conditions change. The resulting models will be used to inform management and monitoring efforts to conserve and recover this charismatic endangered species.

CBI is collaborating with the Rogue River-Siskiyou National Forest and the Klamath National Forest in their effort to conserve the Alaska yellow Cedar in its southern range, located in Southern Oregon and Northern California, where it faces extreme extinction risk due to climate change. Concerted conservation efforts are needed to develop and implement conservation and reforestation strategies, in order to manage forest tree species for sustainability in the future. CBI will help coordinate the collection of seeds from trees from 8 sites, tag and geo-reference each tree, gather information on the general health of these stands, and submit the seeds to the national seedbank in Fort Collins. In addition, current-year needles will be also collected from each seed tree for later genetic/genomics analysis by Richard Cronn and team at the Pacific Northwest Research Station of the USFS.

Alaska Yellow Cedar (Callitropsis nootkatensis) has an extensive range from Alaska to Northern California (Fig. 1). It is declining in the northern part of its range due to a combination of factors associated with climate change and is a rare species in the southern part of its range in California and Southern Oregon. These southern populations are relics that occur in isolated stands in sub-alpine zones in cool wet sites at higher elevation > 5000 ft (Fig 2). The species is currently under review for listing as a threatened or endangered species.

Update 12/18

CBI finished cone collections in September, 2018, from six populations across three sites in Southern Oregon and three sites in Northern California. Access to other sites was restricted due to the Klondike Fire burning in Southern Oregon. This completes the first systematic collection of mature cones from these southern populations.

We have recieved word from the US Forest Service, Bend Seed Extractory, located in Bend Oregon, that they have successfully extracted viable seeds. The next step is to send them to the National Seed Laboratory in Dry Branch, Georgia, USA. Once there, these seeds will be entered into the the national germplasm bank making these the very first entries for these relic southern populations.

Needle tissue that was collected from 10 trees at each site will be genetically analyzed by researchers at the USFS Forest Science lab in Corvallis.This analysis will help determine if these populations are genetically distinct sub-populations from their northern counterparts which will help guide conservation of this species.

The Rogue River-Siskiyou National forest office is planning to use some of these seeds to grow seedlings to test for certain traits such as disease resistance and drought tolerance. The hope is that seeds collected from these southern populations may be used for restoration plantings in the northern regions.

In the north, Alaska Yellow Cedar is a valuable timber species but has been declining as a result of the climate crisis.

Conservation of these southern populations may prove to be critical for the longterm management of northern Alaska Yellow Cedars on public and private lands.

Fig 1. Range map for Alaska yellow cedar.

Source: http://tidcf.nrcan.gc.ca/en/trees/factsheet/376

Figure 2. Current known yellow cedar locations in the Siskyou Mountains (CBI 2017)

Landscape connectivity is critical for species dispersal and population resilience. This project is part of the collaborative Landscape Conservation Design (LCD) for the Pacific Northwest coastal ecoregion and conducted in partnership with the North Pacific Landscape Conservation Cooperative. The goal is to identify connectivity pathways and prioritize corridors for 2-4 focal species West of the Cascades in Oregon and Washington. In Oregon, we will work closely with the members of the Oregon Habitat Connectivity Consortium (OHCC) for both the coastal and Willamette valley ecoregions of the state. The methods tested and refined in this project will feed into future Oregon-wide connectivity mapping.

To learn more and explore related maps and datasets, please visit the Data Basin gallery, “Connectivity of Naturalness in Western Washington“. The gallery includes outputs showing the structural connectivity (i.e. naturalness connectivity) for Western Washington.

These data can be used to help guide connectivity conservation efforts. They are the results from the pilot project comparing Omniscape (coreless) and Linkage Mapper (core areas) modeling methods. Extra attention was made to the data inputs and the rigor of the analyses so that the results can be applied, in addition to answering the driving research question.

Primary forests make up approximately one-third of the world’s remaining forests. Globally, they are grossly under-represented in protected areas and subject to industrial-scale logging and “sustainable forest management” that otherwise fragment intact areas. They face unprecedented threats from logging, mining, energy development, and climate change. British Columbia contains two globally important temperate rainforests with substantial primary and intact forest landscapes distributed from the coast (i.e. Great Bear Rainforest – GBR) inland (i.e., Inland Rainforest). Geos Institute proposes to map and assess conservation importance of the primary forests in these regions as a scientific basis for an international campaign aimed at protecting these globally important rainforests. CBI will support Geos Institute and partners in Canada to help map the area accurately, provide scientific input, and also do a carbon flux model for these primary rainforests.