Geology Reports⌕ Search

SEARCH · Geology Reports

Results for “Preprint”

Search indexed USGS publications on groundwater, aquifers, geologic maps, mineral resources and earthquakes. Explore source records by subject and place.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5Linked to original sources
USGS2024

A habitat suitability model for testing and refining the range of Zuni fleabane, a threatened plant species

Land managers and conservation practitioners need practical tools to protect rare species in light of rapidly changing climate and land use patterns. Habitat suitability models are tools that can inform multiple-use land management decisions and target conservation actions. The narrow endemic Zuni fleabane, Erigeron rhizomatus, occurs on lands managed for multiple uses and was listed as threatened under the Endangered Species Act in 1985 due to the main threat of surface mining. Despite intermittent surveys in recent decades, managers still do not have a comprehensive understanding of suitable habitat characteristics or the geographic extent of suitable habitat across its range. We developed and field-validated a habitat suitability model for Zuni fleabane using an iterative, ensemble approach. We tested the null hypothesis that the model would not identify major new populations outside the known range but rather assist in refining the boundaries of known suitable habitat. We also set out to improve our understanding of biotic and abiotic characteristics that define suitable habitat across geographically distant metapopulations. Our model identified areas with low, medium, high, and very high probability of containing suitable habitat. We identified a new metapopulation beyond the three known (disproving our null hypothesis) as well as additional suitable habitat within the previously known regions. This model predicts where Zuni fleabane habitat likely occurs and may help land managers and conservation practitioners identify new populations, survey habitat at fine scales, avoid impacts from multiple-use management activities, and recover this threatened species.

EcoEvoRxiv↗
USGS2026

Space-based monitoring of penguin diet links sea ice, food webs, and population change

Rapid environmental change is reshaping Antarctic ecosystems through shifts in temperature and sea ice dynamics, with implications for species such as the iconic Adélie penguin ( Pygoscelis adeliae ). Because Antarctic predators rely on a relatively small number of key prey resources in the region 1 whose life histories are intrinsically linked to sea ice, 2 , 3 these abiotic changes are expected to cascade through food webs. However, the scale and remoteness of Antarctica have limited efforts to link environmental change to ecological responses across the continent. Combining tools from imaging spectroscopy, stable isotope analysis, and hierarchical statistical modeling, we reconstructed Adélie penguin diet across the entirety of the species’ global range over a three-decade period (1984–2013) using satellite imagery from the Landsat program. This approach leveraged the distinct spectral properties (a generalized measure of color) of penguin guano as observed by satellites, 4 , 5 which vary according to penguin diet. 6 , 7 We found pronounced differences in diet across the continent and that year-to-year dietary shifts were strongly associated with sea ice dynamics. Higher sea ice corresponded to more fish-based diets, whereas lower sea ice was associated with a greater reliance on krill. Additionally, spatial differences in penguin diet were associated with long-term trends in penguin abundance, linking food web processes to large-scale population dynamics. This study represents the first use of satellite observations to capture trophic dynamics at continental and decadal scales and highlights how environmental change might restructure Antarctic food webs and influence the future of a key sentinel species.

Current Biology↗
USGS2024

Managing water for birds— A tool for the Malheur National Wildlife Refuge

The “Water for Birds Tool” is an Excel-based model designed for resource managers to assess the spatial extent and types of bird habitats in the Malheur National Wildlife Refuge. The model quantifies the area of open water, partial water, and water depths on a monthly timescale during the irrigation season (April–July) from 2021–2024. This model combines previously published datasets and incorporates new measurements collected by partners. Results show that the relation between the amount of bird habitat and the extent (partial and open water) of Malheur Lake varies by bird guild. The Donner und Blitzen River supplied nearly all the surface water inflow to Malheur Lake during the analysis years, emphasizing the importance of informed management of the river. Additional gaging of inflows and diversions, and better estimates of recharge and irrigated areas, will refine estimates of water use on the refuge.

EcoEvoRxiv↗
USGS2026

BioShifts v2 and BioShiftR: Tools for navigating and analysing species range shift data

Species are redistributing their ranges globally in response to climate change, but the fragmented and complex nature of the documented responses make them challenging to track and analyze. Synthesis of species’ range shifts requires careful integration and consideration of varying methods and scales of study. Here, we present an updated database that combines two previous data repositories (BioShifts v1 and CoRE), complete with methodological information from original studies, spatial datasets of species and study locations, and associated climate exposure metrics calculated at multiple scales, together comprising a clean and interoperable relational database for future studies of range shifts. We make these data accessible through a companion open-source software tool, BioShiftR, that simplifies the navigation and analysis of estimated range shift rates in light of varying methods and hypothesized climate drivers. Together, these tools will facilitate tractable and robust downstream studies of range shifts, ultimately improving our understanding of species’ biogeographical responses to climate change.

EcoEvoRxiv↗
USGS2025

A practical framework for identifying genetic subpopulations and ESUs: Insights for IUCN assessments and broader management

The International Union for Conservation of Nature (IUCN) sets global conservation standards, including the Red List of Threatened Species and the Green Status of Species. Recent analyses showed that genetic diversity has not been effectively considered by IUCN species assessments, despite being fundamental to species’ fitness and adaptive potential. Incorporation of genetic diversity into IUCN assessments can support its successful long-term conservation. To enhance the preservation of genetic diversity, assessments should include genetically meaningful within-species units. Subpopulations are recognized units by the IUCN for protecting natural connectivity, however infrequently evaluated. Evolutionarily Significant Units (ESUs) are currently not recognized as a formal unit by the IUCN. However, incorporating ESUs into conservation frameworks could significantly enhance our capacity to identify and protect adaptive genetic diversity. To facilitate inclusion of these units in IUCN assessments, we outline a widely applicable framework for their identification that uses non-molecular and molecular data for global accessibility.

EcoEvoRxiv↗
USGS2025

A low-cost approach to monitoring streamflow dynamics in small, headwater streams using timelapse imagery and a deep learning model

Despite their ubiquity and importance as freshwater habitat, small headwater streams are under monitored by existing stream gage networks. To address this gap, we describe a low-cost, non-contact, and low-effort method that enables organizations to monitor streamflow dynamics in small headwater streams. The method uses a camera to capture repeat images of the stream from a fixed position. A person then annotates pairs of images, in each case indicating which image has more apparent streamflow or indicating equal flow if no difference is discernible. A deep learning modelling framework called Streamflow Rank Estimation (SRE) is then trained on the annotated image pairs and applied to rank all images from highest to lowest apparent streamflow. From this result a relative hydrograph can be derived. We found that our modelled relative hydrograph dynamics matched the observed hydrograph dynamics well for 11 cameras at 8 streamflow sites in western Massachusetts. Higher performance was observed during the annotation period (median Kendall’s Tau rank correlation 0.75 with range 0.6–0.83) than after it (median Kendall’s Tau 0.59 with range 0.34 – 0.74). We found that annotation performance was generally consistent across the eleven camera sites and two individual annotators and was positively correlated with streamflow variability at a site. A scaling simulation determined that model performance improvements were limited after 1,000 annotation pairs. Our model’s estimates of relative flow, while not equivalent to absolute flow, may still be useful for many applications, such as ecological modelling and calculating event-based hydrological statistics (e.g., the number of out-of-bank floods). We anticipate this method will be a valuable tool to extend existing stream monitoring networks and provide new insights on dynamic headwater systems.

EGUSphere↗
USGS2026

Assessing the prevalence, timing, and rapidity of transitions between hydrological extremes and their relation to meteorological extremes in the conterminous United States

Rapid shifts between droughts and floods, termed hydrological whiplash, challenge water management, yet their timing and drivers remain poorly understood at continental scales. While drought-to-flood (DtF) transitions have received growing attention, flood-to-drought (FtD) transitions — though rarer — pose distinct operational challenges that are less well characterized. These wet-to-dry shifts can disrupt post-flood recovery, strain warm-season water demands, and create compounding risks for infrastructure and water quality. We analyzed daily streamflow records from 3,219 USGS streamgages (1981-2024) to characterize both DtF and FtD transitions across CONUS, with particular emphasis on understanding why these transitions are not symmetric inverses of each other. We test a wide variety of hydrological extreme transition definitions to examine the sensitivity of the number of transitions identified and their rapidity. Additionally, we identify a subset of transitions that may be impactful based on the maximum change in percentile magnitude during a transition. DtF transitions are faster than FtD transitions, and short-term (<= 30-days) transitions in both directions are concentrated in the Northeast, Northwest, and Rocky Mountains regions. Short-term DtF transitions are additionally concentrated in southern California and along the line from North Dakota down to Texas where precipitation approximately equals potential evapotranspiration. We find direction-specific controls: snow-dominated, urban, regulated, and minimally disturbed basins show the most frequent impactful DtF transitions, while regulated basins are most prone to impactful FtD transitions. Rapid and impactful transitions make up a substantially larger fraction of DtF transitions than FtD transitions across nearly all basin types. A key finding is that hydrological and meteorological whiplash rarely coincide: only 19-24% of hydrological extreme transitions co-occur with hydroclimate whiplash, revealing that basin storage, regulation, and routing processes create a fundamental decoupling between climate forcing and streamflow response. Our findings highlight the need to better understand quick hydrological transitions under increasing hydroclimatic volatility, particularly the understudied FtD direction, and the mechanisms by which anthropogenic modifications reshape the hydrological whiplash risk.

EGUSphere↗
USGS2026

A snapshot of Joshua tree (Yucca brevifolia and Y. jaegeriana) stand structure in the eastern Mojave Desert of California

The long-term viability of the iconic Joshua tree of the Mojave Desert is being evaluated. In 2022, we measured the abundance and heights of Joshua tree stems on 62 1000 m2 plots in the eastern Mojave Desert of California. The 2022 plots were represented by 33 plots in a population of western Joshua trees (Yucca brevifolia) and 29 plots in a population of eastern Joshua trees (Y. jaegeriana). Five plots had no Joshua trees; two of which in the western Joshua tree population were destroyed by fire. The 57 plots with Joshua trees supported 627 stems ranging from stems less than 25 cm to mature trees. The plots were examined by abundance and four size classes of the stems, as indicated by their height and indicative of their reproductive status. The western Joshua tree population had more stems (407) than the eastern population (220 stems) although the median difference was not significant. The western population had significantly more stems in pre-reproductive size classes, juvenile (> 25 cm to one-meter, p = 0.001) and sub_adult (> one- to two-meters, p = 0.001), than the eastern population but significantly fewer adult (> two-meters, p < 0.001) stems. The eastern population had significantly greater mean height of adult trees (302 cm +/- 75.3 cm) than the western population (263 cm +/- 52.9 cm) and a larger proportion of stems taller than two-meters (56%) than the western population (39%). In contrast, the western population has 77% of its population in younger size classes (> 25 cm to < 2 meters). These abundance and size class measures alone do not predict whether either population has sufficient natural stand regeneration for long term persistence, but the younger size class structure of the western population suggests greater long-term resilience than for the eastern population.

BioRxiv↗
USGS2026

Genomic structural variation rescues a classic biological invader from a population bottleneck

Invasion genetics presents a classic paradox: how do species successfully spread despite severe population bottlenecks? The brown treesnake ( Boiga irregularis ) in Guam represents a striking example of this phenomenon, having been introduced with only a handful of individuals. We show that the population endured an extreme bottleneck, with roughly half of the genome exhibiting runs of homozygosity, comparable to species of conservation concern. Despite this, we uncovered extensive diversity in the form of nearly 19,000 genomic structural variants, which affect almost eight times more of the genome than single-nucleotide variants and provide material for ‘rescuing’ the population from inbreeding-driven declines. Structural variant density was highest in gene promoters, where recombination and DNA repair often occur, providing a mechanism for rapid evolution of gene-linked diversity. This diversity is enriched in genes vital for adaptive immunity and olfaction, suggesting genomic diversity in key chromosomal regions can rescue populations from inbreeding. This work has critical implications for invasion biology and conservation genetics practitioners.

BioRxiv↗
USGS2026

Stopover population estimate and migration ecology of Red Knots C. c. rufa at the Delaware Bay, USA, 2025

Red Knots ( Calidris canutus rufa ) rely on Atlantic horseshoe crab ( Limulus polyphemus ) eggs in the Delaware Bay to refuel during northward migration. Intensive harvest of horseshoe crabs in the 1990s contributed to declines in Red Knot numbers. In 2013, the Atlantic States Marine Fisheries Commission adopted an Adaptive Resource Management (ARM) framework to balance sustainable horseshoe crab harvest with ecosystem integrity and Red Knot recovery, requiring annual stopover population estimates. We estimated the 2025 passage population of Red Knots at Delaware Bay using a Bayesian analysis of a Jolly–Seber mark–resight model which accounts for population turnover and imperfect detection. We also evaluated change in migration timing between 2011 and 2025 with model-derived estimates of arrival at the Delaware Bay each year. The 2025 passage population was 54,043 individuals (95% credible interval: 47,926–61,928), an increase of approximately 17% over 2024 and only the second year since 2011 to exceed 50,000 individuals. Despite the increase, overlapping credible intervals across years indicate a stable stopover population. Migration timing has remained consistent, with 50% of the population typically arriving by 18 May and no evidence of advancement since 2011. These findings provide meaningful input for the ARM framework, supporting sustainable harvest of horseshoe crabs while maintaining adequate foraging opportunities for Red Knots and other shorebirds.

BioRxiv↗
USGS2026

Status of round goby invasion fronts in New York and Quebec: Implications for Lake Champlain

Invasive round goby Neogobius melanostomus have advanced eastward through the state of New York and provinces of Ontario and Quebec over the past two decades and are approaching Lake Champlain, one of the largest lakes in North America. This manuscript describes international efforts to monitor round goby populations during 2021–2025 on (a) the southern approach to Lake Champlain via the Hudson River and Champlain Canal, and (b) the northern approach to Lake Champlain via the Saint Lawrence River and Richelieu River. Monitoring utilized environmental DNA (eDNA), backpack electrofishing, beach seining, benthic trawling, and viral hemorrhagic septicemia virus (VHSV) testing. In the Champlain Canal, round goby were captured as far north as the downstream side of the C1 dam (97 kilometers [km] from Lake Champlain) while eDNA detections occurred as far north as the upstream side of the C2 dam (90 km from Lake Champlain). In the Richelieu River, round goby were captured as far south as Saint-Marc-sur-Richelieu (82 km from Lake Champlain) while the southern-most eDNA detections occurred near the Canadian side of the international border (4 km from Lake Champlain). Water temperature influenced habitat usage of round goby in the Champlain Canal, with catch rates in near-shore areas declining at < 10 °C. All VHSV test results were non-detections at the mouth of the Richelieu River, while one positive and two inconclusive results occurred along the Champlain Canal. Together, these data have informed multiple mitigation measures and have implications for management of aquatic invasive species across North America.

BioRxiv↗
USGS2026

Columbia Basin pygmy rabbit recovery planning through structured decision making

The endangered Columbia Basin pygmy rabbit (CBPR) faces multiple threats, particularly increasing risk of larger and more intense wildfires due to climate change, emerging disease, and sagebrush habitat loss due to agriculture and development. Through the use of conservation breeding, the CBPR wild population grew from a low of 16 individuals captured in 2001 to over 100 individuals in two subpopulations in 2024. However, these subpopulations are geographically proximate, with potential risk that both subpopulations could be affected by a single wildfire or disease event. Additionally, a succession of setbacks in the breeding program has prompted a natural re-evaluation point for the CBPR conservation program. We undertook a structured decision-making (SDM) process with participants from both Washington Department of Fish and Wildlife (WDFW) and US Fish and Wildlife Service (USFWS) to develop a strategy that is sustainable and implementable for guiding management in the coming decades across the range of the CBPR, taking into account changing conditions and updated information. A population model that incorporated both demographic and high impact event uncertainties was developed to test how alternative strategies – defined by conservation breeding program, vaccination, and translocation components – affect CBPR population growth and cost objectives. Based on analysis of the model results, we identified the following actions that appear to have the greatest potential to allow WDFW and USFWS to meet their conservation objectives for CBPR: Continue conservation breeding program, and possibly expand to include an island subpopulation (an isolated, unfenced area that can serve as a source for rabbits while requiring fewer management inputs) Continue Rabbit Hemorrhagic Disease Virus (RHDV2) annual vaccinations in both breeding and wild populations When juveniles are available for translocation, prioritize recovery areas that are in the establishing phase In addition, while not analyzed explicitly in the model, discussions during the SDM process led to the identification of the following actions, which the group considered to have potential to benefit the CBPR either directly or indirectly: Increase the amount of suitable habitat available to pygmy rabbits Increase protections for existing and potential recovery areas Design future monitoring to better estimate survival and reproduction, with an emphasis on understanding how these vital rates vary between wild and semi-captive individuals, between vaccinated and unvaccinated individuals, and as a function of habitat factors

BioRxiv↗
USGS2026

A genomic tool to tackle cryptic diversity demonstrates the potential for off-target use of GT-seq panels

A comprehensive understanding of life history is vital to successful species conservation and management. When different life history stages are accompanied by considerable morphological or cryptic variation, such as the egg and larval phases exhibited by most fishes, genomic tools are essential for identifying species so that early-life ecology questions can be studied. Genotyping-in-thousands by sequencing (GT-seq) has recently emerged as a targeted and efficient approach for species identification. We leveraged existing genomic and transcriptomic data to develop a GT-seq panel capable of differentiating the members of the Coregonus artedi complex, a radiation of salmonids in the Laurentian Great Lakes whose members are indistinguishable with mitochondrial DNA barcoding loci and are the focus of bi-national conservation initiatives. Our panel of 494 loci was able to assign fishes in the C. artedi complex to species and lake. We examined cross-amplification in other coregonines with overlapping distributions and found that congeneric Lake Whitefish ( C. clupeaformis ) cross-amplified at 94% of loci and confamilial Round and Pygmy Whitefish ( Prosopium spp.) cross-amplified at 42% and 38% of loci, respectively. We adapted bioinformatic probes to account for Prosopium -specific variants including 22 new SNPs and developed a whitelist of 428 SNPs capable of distinguishing these whitefishes. Finally, we demonstrated performance by identifying 3,066 coregonine larvae and juveniles collected in spring 2019-2021 from Lake Superior. These results hold promise for future insights into the species-specific ecology of early life coregonines and demonstrate the flexibility of GT-seq panels, which may cross-amplify hundreds of informative genome-wide loci in related taxa.

BioRxiv↗
USGS2026

Comparative genomics reveals potential mechanisms of invasion in Phragmites australis (common reed)

Biological invasions are transforming ecosystems worldwide, yet the genomic bases enabling certain species to dominate new environments remain poorly understood. Phragmites australis , a widespread wetland grass with invasive and native subspecies co-occurring in North America, provides a powerful system to investigate genomic mechanisms of invasiveness. We generated independent chromosome-scale genome assemblies for invasive P. australis ssp. australis and co-occurring native ssp. americanus and used comparative genomic and transcriptomic analyses to identify lineage-specific innovations associated with invasive success. The invasive subspecies exhibits genomic novelties through functionally-biased single-copy orthologs, intronless genes, and subgenome expression asymmetry, along with a stress-ready basal transcriptome relative to the native subspecies. Following the removal of aboveground shoots (“cutback”), which measures the ability to recover from damage, the invasive subspecies undergoes stronger transcriptional reprogramming, increased shoot production, and higher biomass accumulation compared to the native. It also displays expansion of gene families and coordinately expressed gene modules that support resource mobilization, growth responses to light, and stress tolerance. Beyond Phragmites , comparative analyses across multiple grass genomes, including eight invasive species with related non-invasive species, revealed repeated expansion of gene families associated with abiotic stress tolerance and developmental regulation, suggesting convergent adaptive strategies in the grass family for invasive success. Together, these results demonstrate genomic architecture linked to invasion success and highlight potential targets for managing invasive grasses.

BioRxiv↗
USGS2026

Distributions of host heterogeneity in susceptibility show signatures of pathogen geographic structure in an insect baculovirus

Segregated variation between populations is a fundamental evolutionary process leading to parasite specialization, yet the resulting impacts on infection heterogeneity within populations are theoretically and empirically understudied. We asked whether the distribution of host susceptibility to infection within populations carries the signatures of geographic structure from pathogen local adaptation, maladaptation, or generalism in a nuclear polyhedrosis virus that infects the Gulf Fritillary butterfly Dione vanillae . For this virus, there is genetic support for two geographically distinct groups within San Diego County, based on whole genome sequencing of 16 virus isolates. Reciprocal laboratory infections showed evidence of two contrasting viral life history strategies: a ‘generalist’ phenotype that consistently infected variable hosts and a ‘specialist’ that performed slightly better in its local host population. As predicted by our theoretical model, the more consistent infection displayed by the generalist across populations corresponded to lower heterogeneity in susceptibility within populations, modeled as gamma distribution. Furthermore, the generalist phenotype was collected over a wider geographic range despite having a tenfold-lower mean infection rate than the specialist, suggesting that a strategy of more consistent infection provides key fitness advantages across diverse host populations. Intriguingly, when there is variation in host susceptibility, interpretations of pathogen local adaptation are dose-dependent. Measuring infectivity across multiple doses enables estimation of the whole distribution of susceptibility, which provides more reliable identification of pathogen specialization to its local host. Our work demonstrates how trait distributions and not only their mean values can carry quantifiable signatures of eco-evolutionary processes in interspecific interactions.

BioRxiv↗
USGS2026

A Lake Charr pangenome reveals highly conserved Ohnologs as drivers of phenotypic diversity

Whole-genome duplication (WGD) is hypothesized to spur evolutionary diversification by producing genome-wide duplicate gene sets (Ohnologs) that are initially functionally redundant but can diverge markedly as the effects of relaxed selection accumulate over time. However, the underlying mechanisms remain unclear, in part because genomic studies often reconstruct Ohnolog evolution over millions of years, during which subsequent mutations can obscure deep-time signals. Investigating the relationship between Ohnolog evolution and diversification on a contemporary timescale offers clearer insights. We explore this relationship in Lake Charr ( Salvelinus namaycush ), where ∼10% of genes are retained highly conserved polyploid duplicates following the Salmonid-Specific Fourth Round WGD. Using 31 chromosome-level assemblies of Lake Charr from morphologically and ecologically diverse populations, joined into a pangenome graph, we characterized 189,555 structural variants (SVs) that were significantly less likely to affect genes retained as sequence-conserved Ohnolog pairs, nuancing the hypothesis that gene redundancy, relaxed selection, and functional diversification are intertwined. However, we found that SVs affecting such conserved Ohnologs may be potent drivers of adaptive evolution. Notably, we identified a putative 938-Kb interchromosomal translocation containing 25 genes with highly conserved Ohnologs in a paralogous (but untranslocated) genomic block. This putative translocation appears to have facilitated Ohnolog divergence in ankrd11 and hp , genes putatively linked to craniofacial and lipid metabolic diversity in sympatric Lake Superior morphs. This research reveals that conserved Ohnologs previously presumed to be redundant remain a reservoir for adaptive change.

BioRxiv↗
USGS2026

Decision analysis in support of proactive planning for chronic wasting disease in Vermont, USA

Chronic wasting disease (CWD), a fatal, transmissible disease in white-tailed deer ( Odocoileus virginianus ) and related species, is spreading across North America but has not yet been detected in Vermont, United States (U.S.). The Vermont Department of Fish and Wildlife, along with partner agencies, wants to develop a proactive prevention and response plan in anticipation of the eventual detection of the disease. Between September 2023 and September 2025, staff from the U.S. Geological Survey and the University of Vermont facilitated a structured decision-making (SDM) process with seven State and Federal agencies that have jurisdiction over some aspect of CWD management in Vermont. The aim of this process was to generate and evaluate alternative response plans against a range of long-term objectives important to the agencies. To aid in the evaluation of the alternatives, we developed a linked set of models for white-tailed deer population and disease dynamics, hunter participation and health, forest health, economic consequences, and agricultural opportunities related to the actions being contemplated as part of the response plan. We evaluated over 256 different permutations of management actions and used multi-criteria decision analysis, a branch of decision analysis designed to help decision makers navigate tradeoffs among competing objectives, to summarize the performance of those alternative strategies against the desired outcomes. Proactive actions—those designed to slow the arrival of CWD to Vermont—were moderately effective, but the most important proactive action was surveillance to detect the disease early after arrival, which triggered response actions after detection. With the insights generated by the SDM process and the results of the analyses, the participating agencies were able to identify a preferred strategy and outline the elements of a proactive response plan. This report describes the SDM process, the technical details of the modeling work, and the results of the analyses. It is intended to serve as the technical basis for Vermont’s response plan.

BioRxiv↗
USGS2026

Classifying and mapping wetland vegetation assemblages in coastal Louisiana with Landsat imagery, 1985-2025

The tidal wetlands of Louisiana comprise about 25% of those found throughout the conterminous United States yet estimates of wetland loss rates in the region between 1932 and 2016 have exceeded 60 km 2 yr -1 . To mitigate further degradation and wetland loss in the region, a globally unprecedented $50B, 50-year plan for coastal Louisiana is driving restoration efforts, and demand exists from multiple stakeholders for regularly updated, regional-scale, accurate land cover information. We used machine learning (random forests; RF) and cloud computing to develop a new Landsat-based, marsh vegetation community geospatial dataset. The dataset depicts wetland vegetation community types defined in a previous study at annual (1985–2025) time steps at 30-m resolution. An RF algorithm was used to integrate training samples with feature variables derived from Landsat imagery, and the resulting geospatial data product achieved an overall correct classification rate of 78%. The approach for development of the land cover dataset presented here has potential for application in other coastal wetland habitats throughout the world.

BioRxiv↗