USGS Science⌕ Search

SEARCH · USGS Science

Results for “Science of the Total Environment”

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.

1,687 records · Page 82Linked to original sources
USGS2026

Stratigraphic notes—Volume 3, 2026

This is the third volume in the U.S. Geological Survey (USGS) series of reports on stratigraphy entitled “Stratigraphic Notes,” which consists of short papers that highlight stratigraphic studies, changes in stratigraphic nomenclature, and explanations of stratigraphic names and concepts used on published geologic maps. “Stratigraphic Notes” is a long-term (multiyear), multivolume publication containing articles that address updates or revisions to stratigraphic nomenclature (and whose content ultimately will be incorporated by National Geologic Map Database personnel into Geolex, https://ngmdb.usgs.gov/Geolex/ ). We welcome papers for the “Stratigraphic Notes” series from geoscientists of the USGS, of State Geological Surveys, and from academicians. Papers can be submitted for publication in “Stratigraphic Notes” by contacting the USGS Geologic Names Committee ( gnc@usgs.gov ). As new “Stratigraphic Notes” volumes are published, links to the volumes will be posted at https://doi.org/10.3133/pp1879 .

Professional Paper↗
USGS2025

Statewide cumulative human health risk assessment of inorganics-contaminated groundwater wells, Montana, USA

Across the United States, rural residents rely on unregulated and generally unmonitored private wells for drinking water, which may pose serious health risks due to unrecognized contaminants. We assessed the nature, degree, and spatial distribution of cumulative health risks from inorganic contaminants in groundwater. Our analysis included nearly 84,000 data points from 6500+ wells, across 51 of Montana's 98 watersheds, using a public groundwater database. We compared a drinking water screening level cumulative risk assessment (CRA) for inorganics based on the U.S. Environmental Protection Agency (EPA) protective health thresholds (Maximum Contaminant Level Goals, Health Advisories [MCLG-HAs]) to a CRA based on EPA public supply enforceable Maximum Contaminant Levels (MCLs). Based on median concentrations of 19 inorganics (antimony, arsenic, barium, beryllium, boron, cadmium, chromium, copper, fluoride, manganese, molybdenum, nickel, nitrate, lead, selenium, strontium, thallium, uranium, zinc), 75% of watersheds had MCLG-HA-based cumulative risk values > 1.0; arsenic and uranium contributed the most risk, followed by strontium, fluoride, manganese and boron. Hence, this screening level (Tier I) CRA indicated widespread potential for unrecognized human health risk to private well users from inorganic contaminants considering both carcinogenic and non-carcinogenic risks. Sensitivity analysis showed that benchmarks applied (MCLG-HAs versus MCLs) exerted the largest control on results. Our findings identify priority regions for Tier 2 risk assessments to elucidate local sources and distributions of geogenic versus anthropomorphic contaminants. Our study is the first statewide assessment of cumulative health risk from groundwater that we are aware of, and results support increased statewide drinking water education and testing to reduce human health risks from contaminated private well water.

Montana↗
USGS2024

Diel temperature signals track seasonal shifts in localized groundwater contributions to headwater streamflow generation at network scale

Groundwater contributions to streamflow sustain aquatic ecosystem resilience; streams without significant groundwater inputs often have well-coupled air and water temperatures that degrade cold-water habitat during warm low flow periods. Widespread uncertainty in stream-groundwater connectivity across space and time has created disparate predictions of energy and nutrient fluxes across headwater networks, hindering predictions of cold-water habitat resilience under climate change scenarios. Recently, annual paired air and water temperature signals have been harnessed to indicate stream water thermal sensitivity and the dominance of deep versus shallow groundwater influence, although the utility of diel air–water temperature signal metrics for hydrologic inference has remained unexplored. Here we analyzed two consecutive years of locally paired, air–water temperature data from 47 headwater stream sites in the Catskill Mountains, New York, USA, and discovered characteristic seasonal patterns in diel temperature signal sinusoid metrics (amplitude ratio, phase lag, and mean ratio) driven by shifts in streamflow generation mechanisms and stream network position. Hydrologic interpretations of observed patterns were supported by stream heat budget model scenarios and additional analysis of paired air–water temperature data from two streams in Shenandoah National Park, Virginia, USA, with well characterized stream-groundwater connectivity. We found that within smaller tributaries, streamflow generation transitions from runoff to groundwater dominance were driven by hillslope drying during seasonal periods of lower precipitation. This was evidenced by significant correlations (p < 0.01) between daily water:air temperature signal amplitudes (non-linear decreases of ∼ 50 %) and derived base-flow index at 22 of the 28 sites, indicating enhanced local groundwater influence on streamflow promotes decoupling of diel air–water temperature signals. Additionally, ratios between daily water:air temperature signal means were lower in tributaries (∼0.68) when compared to main-stem (∼0.8) sites, increasing linearly throughout the observational period. In conceptual stream heat budget models, groundwater inflow had minimal effects on daily phase lags (∼0.2 hr), but increases in fractional groundwater discharge (0–50 %) depressed daily amplitude (∼20 % to 50 %) and mean ratios (∼15 %), supporting the sensitivity of daily metrics to interpreted changes in seasonal groundwater contributions to streamflow. During observational periods (i.e., April through October 2021 and 2022), significant differences (p < 0.01) between tributary and main-stem air–water metrics occurred when base-flow contributions were highest (∼0.93 vs. ∼ 0.68), as sites lower in the network had daily temperature metrics dominated by stream channel thermal inertia, rather than local groundwater connectivity, showing enhanced air–water diel signal coupling during warmer, drier periods. Divergent air temperature coupling across the network was interpreted as being driven by distance from local groundwater source zones, additional lateral groundwater inflows do not contribute a meaningful fraction to channel discharge lower in the network. Given the growing footprint of stream temperature observations, diel air–water temperature signals can provide distributed metrics sensitive to upstream groundwater discharge. Consequently, these metrics can support ongoing efforts by resource managers and researchers seeking to forecast the resilience of cold-water habitat to climate warming and changing precipitation regimes in mountain headwater streams.

New York, Virginia↗
USGS2026

Tracking baseflow supply dynamics using SWOT data from small groundwater-dominated lakes

In situ surface-water monitoring strategies are biased towards larger perennial streams and lakes and are generally not designed to track mechanisms of baseflow supply contributed by the dynamic storage of aquifers. Additionally, small (< 1 km 2 ) groundwater-influenced lakes and wetlands globally have little in situ monitoring infrastructure. We explored the utility of remotely sensed Surface Water Ocean Topography Satellite (SWOT) data, collected from 2023 onward, to characterise the seasonal and multi-year water-level trends of groundwater flow-through kettle lakes distributed across the permeable sediments of eastern Massachusetts, USA. This analysis indicated that water levels for kettle lakes with areas down to approximately 0.05 km 2 are resolvable in the study area. Our examination of 17 kettle lakes found that SWOT water-surface elevation data closely tracked groundwater levels in adjacent monitoring wells where available, including the timing of seasonal patterns (highest levels generally in late spring), although there was some variation between years and there was a substantial lag in the timing of high water levels for a lake located downgradient from a 30-m-thick vadose zone. Furthermore, SWOT-observed water-level increases in kettle lakes tracked with baseflow increases in two adjacent groundwater-dominated streams, as would be expected from increased hydraulic gradients. Unlike spectral remote sensing, SWOT data are generally not affected by cloud cover, resulting in a potential for groundwater-dominated lakes to be sentinels of dynamic storage patterns, including identification of baseflow drought lags, which are currently ill-defined hydrological processes. SWOT monitoring of groundwater-influenced surface waters shows potential for augmenting existing monitoring wells and streamgages as continuous monitors of groundwater levels and baseflow supply in permeable terrain.

Massachusetts↗
USGS2026

Monitoring recreation on federally managed lands and waters—Aspects of visitor use

Federally managed public lands and waters receive about 1 billion recreational visits each year. Data on these visitors can aid in guiding policy decisions, managing resources effectively, and communicating the economic contributions of lands and waters. This report explores the methods used by agencies to collect data on aspects of recreational visitor use to Federal lands and waters (apart from visitation numbers, which are the focus of a companion publication). Aspects of recreational visitor use include visitor demographics, recreational activity participation, visitor satisfaction, visitor attitudes and experiences, trip characteristics, and economic contributions. We review practices used to understand aspects of visitor use across seven Federal agencies, revealing similarities such as the use of visitor intercept surveys and coverage of similar topic area, and differences in how survey programs are operationalized and how specific questions on visitor surveys are worded. We also evaluate emerging technologies, such as geolocated social media and mobile device location data, for their potential to aid in understanding aspects of visitor use. This report concludes with potential opportunities to enhance data collection and coordination, ensuring cost-effective data collection and informed decision-making.

SocArXiv↗
USGS2026

Estimating aftershock risk for entry into earthquake-damaged buildings

We present a simple method to estimate the risk of experiencing strong shaking from aftershocks during entry into earthquake-damaged buildings. We compute wait times until the probability of strong ground shaking from aftershocks reaches a predefined risk threshold; for example, a 0.4 percent probability of experiencing Modified Mercalli Intensity 7 or greater shaking during the planned building entry. We also develop a relation between aftershock probability and the probability of strong shaking, so that users can reference the U.S. Geological Survey aftershock forecast during an ongoing aftershock sequence to determine if the risk threshold has been met. We apply our method to active continental regions (for example, the Western United States), stable continental regions (for example, the Central and Eastern United States), and subduction zones (for example, Cascadia or Alaska).

Open-File Report↗
USGS2025

Methods for estimating selected low-flow statistics at gaged and ungaged stream sites in Massachusetts

The U.S. Geological Survey, in cooperation with the Massachusetts Department of Conservation and Recreation, Office of Water Resources, computed selected at-site streamflow statistics at U.S. Geological Survey streamgages in and near Massachusetts and developed regional regression equations for estimating selected streamflows at ungaged stream sites in Massachusetts. Two sets of regional regression equations were developed: (1) the “mainland” equations, for mainland Massachusetts excluding the area covered by the second set, and (2) the “southeastern” equations, for the Plymouth-Carver-Kingston-Duxbury aquifer area in southeastern Massachusetts and for Cape Cod. The regression equations and at-site statistics may be used by Federal, State, and local water managers in addressing water-resources issues relevant in Massachusetts. Regional regression analyses for the mainland equations were developed to estimate the following 27 streamflow statistics: 99-, 98-, 95-, 90-, 85-, 80-, 75-, 70-, 60-, and 50-percent flow durations; monthly June, July, August, and September 90- and 50-percent flow durations; February, June, and August median of the monthly means; harmonic mean; and medians of the following annual low-flow frequency statistics: 7-day; 7-day, 2-year; 7-day, 10-year; 30-day, 2-year; and 30-day, 10-year. The analyses used 81 streamgages with minimal to no regulations in and near Massachusetts. The regression analyses determined that four basin characteristics—drainage area, combined hydrologic soils A and B, streamflow variability index, and annual mean temperature—were the only significant explanatory variables for the different mainland equations. Regional regression equations were developed for the Plymouth-Carver-Kingston-Duxbury aquifer area in southeastern Massachusetts and Cape Cod, because surface-water drainage areas and groundwater contributing areas do not always coincide in this area of the State. The regression analyses to estimate 10 flow durations from the 99th to 50th percentiles used 18 streamflow sites with some occasional minor regulations—because there are few unregulated streams in southeastern Massachusetts. The analyses determined that groundwater contributing area and storage (combined water bodies and wetlands) were the only significant explanatory variables in the southeastern equations.

Massachusetts↗
USGS2026

Monitoring recreation on federally managed lands and waters—Aspects of visitor use

Federally managed public lands and waters receive around 1 billion recreational visits each year. Data on these visitors can aid in guiding policy decisions, managing resources effectively, and communicating the economic contributions of lands and waters. This report explores the methods used by agencies to collect data on aspects of recreational visitor use to Federal lands and waters (apart from visitation numbers, which are the focus of a companion publication). Aspects of recreational visitor use include visitor demographics, recreational activity participation, visitor satisfaction, visitor attitudes and experiences, trip characteristics, and economic contributions. We review practices used to understand aspects of visitor use across seven Federal agencies, revealing similarities such as the use of visitor intercept surveys and coverage of similar topic areas, and differences in how survey programs are operationalized and how specific questions on visitor surveys are worded. We also evaluate emerging technologies, such as geolocated social media and mobile device location data, for their potential to aid in understanding aspects of visitor use. This report concludes with potential opportunities to enhance data collection and coordination, ensuring cost- effective data collection and informed decision making.

Scientific Investigations Report↗
USGS2026

HyFlood: A surrogate-model-based framework for compound coastal flooding

Compound coastal flooding is a major threat to low-lying coastal regions and is expected to intensify under future climate change projections. However, modeling the joint interaction of waves, storm surge, tides, and rainfall remains computationally demanding, limiting the development of fast and reliable forecast tools. Here we present HyFlood, a hybrid statistical-numerical downscaling framework capable of computing and mapping high-resolution compound flood hazards while substantially reducing the computational cost compared with fully process-based hydrodynamic modeling. HyFlood combines statistical sampling and selection algorithms with a cascade of reduced-complexity surrogate models that emulate nearshore wave transformation, surf-zone hydrodynamics, and coastal, fluvial, and pluvial flooding. The surrogate models employ machine-learning and regression algorithms applied to a low-dimensional representation of the flooding outputs, obtained through statistical dimensionality reduction. The framework is demonstrated in southern O'ahu, Hawai'i, a region exposed to elevated sea levels driven by tides, waves, and storm surge along with frequent precipitation-driven flash flooding. Validation of the surrogates against the physics-based model outputs demonstrates that HyFlood accurately reproduces daily maxima of spatially distributed flooding depths. This hybrid approach offers a scalable and efficient tool to better quantify how changes in flooding drivers translate into hazard and impact assessments, and to support compound-flood risk assessments and climate-change adaptation planning.

Hawaii↗
USGS2024

Flood-inundation maps for the Cuyahoga River at Jaite, Ohio, 2024

Digital flood-inundation maps for a nearly 6-mile reach of the Cuyahoga River at Jaite, Ohio, were created by the U.S. Geological Survey (USGS) in cooperation with the Northeast Ohio Regional Sewer District Board of Trustees. The maps depict estimates of the extent and depth of flooding corresponding to selected water levels (stages) at USGS streamgage 04206425 on the Cuyahoga River at Jaite, Ohio. Water-surface profiles were computed for the stream reach by using a one-dimensional steady-state step-backwater model. The hydraulic model was calibrated to the current USGS streamgage data and then used to compute 15 water-surface profiles for flood stages at 1-foot intervals referenced to the streamgage datum and ranging from 6 to 20 feet, which correspond to below “action stage” to “major flood stage” as reported by the National Weather Service. The simulated water-surface profiles were then used with a geographic information system digital elevation model derived from light detection and ranging data to delineate the areas flooded at each stage. These maps, along with current stage data from the USGS streamgage and forecasted high-flow stages from the National Weather Service, can provide emergency management personnel and residents with information that is critical for flood response activities such as evacuations and road closures, as well as for postflood recovery efforts.

Ohio↗
USGS2026

Special issue “The 2024 M7.6 Noto Peninsula earthquake and seismic swarm”

The 2024 Mw7.5 (M JMA 7.6) Noto Peninsula earthquake struck the Noto Peninsula, central Japan on January 1, 2024, causing widespread damage. This Mw7.5 mainshock, together with the prolonged seismic swarm that persisted in the northeastern Noto Peninsula since the end of 2020, of which the largest event was the 2023 M JMA 6.5 earthquake, constitutes one of the most significant seismic sequences in Japan in recent decades. The sequence provides a rare opportunity to investigate the complex interplay among swarm activity, fluid migration, fault geometry and distribution, and the preparatory conditions required for a large inland crustal earthquake. Motivated by this scientific context, this special issue brings together studies examining the sequence from diverse disciplinary perspectives, incorporating seismic, geodetic, and tsunami-related observations and modelling.

Noto Peninsula↗
USGS2024

Relatively stable pressure effects and time-increasing thermal contraction control Heber geothermal field deformation

Due to geological complexities and observational gaps, it is challenging to identify the governing physical processes of geothermal field deformation including ground subsidence and earthquakes. In the west and east regions of the Heber Geothermal Field (HGF), decade-long subsidence was occurring despite injection of heat-depleted brines, along with transient reversals between uplift and subsidence. These observed phenomena contradict current knowledge that injection leads to surface uplift. Here we show that high-yield production wells at the HGF center siphon fluid from surrounding regions, which can cause subsidence at low-rate injection locations. Moreover, the thermal contraction effect by cooling increases with time and eventually overwhelms the pressure effects of pressure fluctuation and poroelastic responses, which keep relatively stable during geothermal operations. The observed subsidence anomalies result from the siphoning effect and thermal contraction. We further demonstrate that thermal contraction dominates long-term trends of surface displacement and seismicity growth, while pressure effects drive near-instantaneous changes.

California↗
USGS2024

Groundwater flow model for the Des Moines River alluvial aquifer near Des Moines, Iowa

Des Moines Water Works (DMWW) is a regional municipal water utility that provides residential and commercial water resources to about 600,000 customers in Des Moines, Iowa, and surrounding municipalities in central Iowa. DMWW has identified a need for increased water supply and is exploring the potential for expanding groundwater production capabilities in the Des Moines River alluvial aquifer, where it operates two radial collector wells (RCWs). The U.S. Geological Survey, in cooperation with DMWW, completed a study of the Des Moines River alluvial aquifer and interactions of the RCWs with the aquifer; no previously published model has included the existing well locations, which is the focus of this model. A conceptual and numerical groundwater flow model have been developed to characterize the Des Moines River alluvial aquifer under existing conditions, to simulate water levels observed in the RCWs, and to provide publicly accessible hydrologic data and research that advance understanding of the regional hydrologic system and can potentially be used in the future to evaluate groundwater production scenarios. Model performance was assessed by comparing observed and simulated groundwater levels that included water level elevations, water level changes, water level inequality observations, surface water streamflow, and change in surface water volume from upstream to downstream. Water table elevation in the aquifer layers is on average slightly overestimated with average absolute value error less than 1.5 meters at both RCWs and less than 2.5 meters for all observation wells in the alluvial aquifer layers. The model also accurately simulated water tables greater than the RCW design minimum (a water level threshold at which RCW pumping is reduced) in all timesteps for which water level observation data existed. Water table elevation error was higher in other model layers that were not the focus of the study, and the model did not accurately match streamflow targets.

Iowa↗
USGS2026

A diatom-based quantitative sea-ice proxy for the Bering and Chukchi seas

Sea ice affects Earth's climate system on both regional and global scales. Its incorporation into climate can be used to achieve more accurate predictions of future climate. However, instrumental records of sea-ice concentration do not extend earlier than 1978. In an effort to extend this record, we constructed a proxy using the generalized additive model based on relative abundances of five easy-to-identify diatom species found in sediment samples across the Bering and Chukchi seas. Here we present the first quantitative diatom-based sea-ice proxy developed for Beringia. The developed proxy has been applied to two sediment cores in the Bering Sea ranging from 0 to 25.7 ka (HLY0204 51JPC) and 369 to 430 ka (IODP Exp 323 Site U1345) and one in the Chukchi Sea ranging from 2.7 to 10 ka (HLY0204 24JPC). The obtained reconstructions of sea-ice concentrations are similar, but not identical to previously published qualitative and nearby records based on other proxies. Because our results are quantitative, they can be incorporated into regional climate models. The proxy is publicly available as an R Shiny application (app) and can be applied to any diatom count from marine sediments in the region.

Bering Sea, Chukchi Sea↗
USGS2026

Compact seismicity bursts have different characteristics from regional seismicity

Earthquakes tend to cluster, developing into sequences driven by stress perturbations and transient fault-zone processes. Depending on the driving process, earthquake sequences show differing behaviors. This variability challenges our ability to observe or distinguish these driving processes in high resolution. Here we systematically identify seismicity bursts throughout southern California using new statistical methods and examine their causes with other independent geophysical observations. Seismicity bursts are defined as statistically significant seismicity rate anomalies. Our approach has the advantage of being data driven, depending on few earthquake occurrence assumptions. We find abundant seismicity bursts across southern California, most frequently occurring along the San Jacinto Fault and in the Salton Sea and Coso geothermal fields. These seismicity bursts are highly compact in space and time, often encompassed by a 5 km radius and have durations less than 10 hr. Many of the seismicity bursts have their largest earthquake near the beginning of the sequence, but the largest earthquake is usually not an obvious mainshock. We utilize a variety of independent geophysical data sets to analyze the characteristics of the seismicity bursts, finding that the seismicity bursts have low b-values, low spectral stress drops, and varied stress ratios compared to regional seismicity. These differences suggest that seismicity bursts are driven by transient processes acting frequently across fault networks.

California↗
USGS2026

A cross-site comparison of ecosystem- and plot-scale methane fluxes across multiple sites

Wetland and upland ecosystems play significant but opposing roles in the global methane (CH 4 ) budget, acting as natural sources and sinks, respectively. Two of the most common approaches for measuring CH 4 fluxes (FCH 4 ) are chambers, which measure fluxes at fine spatial scales (ca. 1 m 2 ), and eddy covariance (EC) towers, which integrate fluxes across larger footprints (ca. 100–10 000 m 2 ). Although chamber and EC observations have been combined in various syntheses and databases to estimate CH 4 budgets, a unified cross-site evaluation of FCH 4 estimates at plot and ecosystem scales is lacking. As a first step toward a systematic spatiotemporal scaling of EC tower and chamber footprints, we quantified differences in site-level aggregate FCH 4 between EC and chamber measurements ( Δ FCH 4 ) across ten wetland and upland sites at half-hourly, hourly, daily, weekly, monthly, and annual timescales. We found that ecosystem-scale median FCH 4 was consistently higher than plot-scale FCH 4 at all temporal scales, with the smallest difference at the daily timescale (multi-site median Δ FCH 4 : 1.36 nmol m −2 s −1 ; median ecosystem-scale FCH 4 = 1.56 nmol m −2 s −1 , median plot-scale FCH 4 = 0.06 nmol m −2 s −1 ) and the largest at annual scales (2.58 nmol m −2 s −1 ; median ecosystem-scale FCH 4 = 25.91 nmol m −2 s −1 , median plot-scale FCH 4 = 6.55 nmol m −2 s −1 ). In general, the agreement between ecosystem- and plot-scale FCH 4 decreased with finer temporal resolution (from Spearman ρ = 0.95 at the annual scale to ρ = 0.65 at the half-hourly scale), while Δ FCH 4 variation was greatest at daily-to-annual scales. Key environmental predictors of Δ FCH 4 across the ten sites included plot-scale spatial heterogeneity, dominant vegetation type, vapor pressure deficit, atmospheric pressure, and friction velocity at the daily and monthly scales. Wind direction was a significant predictor only at the monthly scale, suggesting EC footprint effects at these sites. These findings suggest that accounting for variability in EC footprint extent, chamber measurement placement, and measurement artifacts is key to reconciling multi-scale FCH 4 observations across diverse ecosystems and refining CH 4 budgets.

Biogeosciences↗
USGS2025

Enhancing mineral systems exploration through geochronology, thermochronology, and isotope analysis: USGS Geochron and USGS Isotope databases

A mineral systems approach to mineral exploration provides a comprehensive framework for understanding ore deposit formation by examining the geodynamic, magmatic, hydrothermal, and sedimentary processes responsible for mineralization, alteration, and remobilization of economic mineral deposits. Temporal and thermal constraints on ore genesis are crucial for refining mineral system models and guiding predictive exploration strategies. Geochronology and thermochronology offer invaluable insights into the timing and thermal evolution of ore-forming processes, whereas isotopic analyses provide critical information on the source and geochemical history of ore-forming fluids. Combining these methodologies have proven highly effective for mineral exploration in regions like Australia, however, their combined application has been limited in the United States. To apply these tools to mineral systems-based exploration, the U.S. Geological Survey (USGS) has developed two products: (1) The USGS Geochron Database, and (2) the USGS Isotope Database. These databases provide centralized repositories of geo/thermochronological dates and data (Geochron Database) and both radiogenic and stable isotope data (Isotope Database) generated by the USGS and partners over the past decades. Integrating these datasets together and with traditional exploration approaches provides the mineral exploration community with powerful tools for determining the temporal and thermal histories of ore systems and identifying metallogenic source provinces.

Continental United States↗
USGS2024

Separating signals in elevation data improves supervised machine learning predictions for hydrothermal favorability

A recent study identified topography (land surface elevation above sea level) as an important input dataset (feature) for predicting the location of hydrothermal systems in the Great Basin in Nevada. Yet, topography is generally a result of more than one geological process and may consequently contain multiple distinct signals. For example, the geologic evolution of the Great Basin has produced both crustal thickening (i.e., regional-scale trends in elevation) and thinning via Basin and Range extensional faulting (i.e., valley-scale topographic relief). We postulate that these geologic processes may affect the occurrence of hydrothermal systems differently. Therefore, we separate the regional trend from the valley-scale signal in the Great Basin, and then use them separately to evaluate the importance of each as predictors for hydrothermal favorability. Our prior work applying supervised machine learning (ML) using the data from the Nevada Machine Learning Project demonstrated that employing a training strategy that randomly selects negative training sites produces better performing models for predicting hydrothermal favorability than a training strategy that uses expert-selected negatives. The models created using both training strategies exhibited a west-east geographic trend in the predictions for the favorability of hydrothermal resources. These models generally predicted higher favorability in western Nevada and lower favorability in eastern Nevada. This west-east trend in predicted favorability correlates with elevation across the Great Basin, which trends higher from west to east. By separating the original elevation feature into distinct features for elevation trend (i.e., regional-scale topography) and detrended elevation (i.e., valley-scale or local relative topography), we find that models using the separated topographic signals consistently outperform competing models that use the original elevation feature. Although western Nevada still exhibits higher favorability than eastern Nevada, using separated signals for regional elevation and local structure reduces the west-east prediction trend in the region and emphasizes structures associated with hydrothermal upflow. This work emphasizes how carefully engineering features to represent geological conditions relevant to hydrothermal systems allows ML algorithms to detect important patterns for predicting hydrothermal resource favorability and leads to better model performance.

Conference Paper↗