USGS Science⌕ Search

SEARCH · USGS Science

Results for “Machine Learning with Applications”

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.

121 records · Page 7Linked to original sources
USGS2019

Lava lake thermal pattern classification using self organizing maps and relationships to eruption processes at Kilauea Volcano, Hawaii

Kīlauea Volcano’s active summit lava lake poses hazards to downwind residents and over 1.6 million Hawai‘i Volcanoes National Park visitors each year. The lava lake surface is dynamic; crustal plates separated by incandescent cracks move across the lake as magma circulates below. We hypothesize that these dynamic thermal patterns are related to changes in other volcanic processes, such that sequences of thermal images may provide information about eruption parameters that are sometimes difficult to measure. The ability to learn about current gas emissions and seismic activity from a remote thermal time-lapse camera would be beneficial when conditions are too hazardous for field measurements. We apply a machine learning algorithm called self-organizing maps (SOM) to thermal infrared time-lapse images of the lava lake collected hourly over 23 April – 21 October 2013 (n=4354). The SOM algorithm can take thousands of seemingly different images, each representing the spatial distribution of relative temperature across the lava lake surface, and group them into clusters based on their similarities. We then relate the resulting clusters to sulfur dioxide emissions and seismic tremor to characterize ties between the SOM classification and different emplacement conditions. The SOM classification results are highly sensitive to the normalization method applied to the input images. The standard pixel-by-pixel normalization method yields a cluster of images defined by the highest observed SO2 emission levels, elevated surface temperatures, and a high proportion of cracks between crustal plates. When lava lake surface patterns are isolated by minimizing the effect of temperature variation between images, relationships with seismic tremor activity emerge, revealing an “intense spatter” cluster, characterized by unstable, broken-up crustal plate patterns on the lava lake surface. This proof of concept study provides a basis for extending the SOM classification method to hazard forecasting and real-time volcanic monitoring applications, as well as comparative studies at other lava lakes.

Hawaii↗
USGS2023

Development and application of a coastal change likelihood assessment for the northeast region, Maine to Virginia

Coastal resources are increasingly affected by erosion, extreme weather events, sea level rise, tidal flooding, and other potential hazards related to climate change. These hazards have varying effects on coastal landscapes because of the compounding of geologic, oceanographic, ecologic, and socioeconomic factors that exist at a given location. An assessment framework is introduced in this report that synthesizes existing datasets that cover the variability of the landscape, and hazards that may act on the landscape, to evaluate the likelihood of coastal change along the U.S. coastline on a decadal scale. The pilot study that aided in the development of the framework was run in the northeastern United States (from Maine to Virginia) and consists of datasets derived from a variety of Federal, State, and local sources. First, a decision-tree-based dataset was built that describes the resistance or integrity of the coastal landscape (called the fabric dataset for the purposes of this report) and includes land cover, elevation, slope, long-term (more than 50 years) shoreline change, dune height, and marsh stability data. A second database was generated from coastal hazards, which are divided into event hazards (for example, flooding, wave power, and probability of storm overwash) and persistent or perpetual hazards (for example, relative sea level rise rate, short-term [about 30-year] shoreline erosion rate, and storm recurrence interval). The fabric dataset was then merged with the coastal hazards databases, and a model training dataset made up of hundreds of polygons was generated from these combined data to support machine learning. The pilot study resulted in location-specific, 10-meter-resolution data classified into five raster datasets that include intrinsic characteristics of the coast used to determine the resistance of the landscape to change, the persistent and event hazards that act on the coast, the machine learning output (coastal change likelihood) based on the cumulative effects of the fabric and hazards datasets, and an estimate of the hazard type (event or persistent) that is the most likely to influence coastal change. Final outcomes are intended to be used as a first-order planning tool to determine which areas of the coast are more likely to change in response to future potential coastal hazards and to examine elements and drivers that make change in a location more likely.

Connecticut, Delaware, Maine, Maryland, Massachuse↗
USGS2021

Machine learning predictions of nitrate in groundwater used for drinking supply in the conterminous United States

Groundwater is an important source of drinking water supplies in the conterminous United State (CONUS), and presence of high nitrate concentrations may limit usability of groundwater in some areas because of the potential negative health effects. Prediction of locations of high nitrate groundwater is needed to focus mitigation and relief efforts. A three-dimensional extreme gradient boosting (XGB) machine learning model was developed to predict the distribution of nitrate. Nitrate was predicted at a 1 km resolution for two drinking water zones, each of variable depth, one for domestic supply and one for public supply. The model used measured nitrate concentrations from 12,082 wells and included predictor variables representing well characteristics, hydrologic conditions, soil type, geology, land use, climate, and nitrogen inputs. Predictor variables derived from empirical or numerical process-based models were also included to integrate information on controlling processes and conditions. The model provided accurate estimates at national and regional scales: the training (R 2 of 0.83) and hold-out (R 2 of 0.49) data fits compared favorably to previous studies. Predicted nitrate concentrations were less than 1 mg/L across most of the CONUS. Nationally, well depth, soil and climate characteristics, and the absence of developed land use were among the most influential explanatory factors. Only 1% of the area in either water supply zone had predicted nitrate concentrations greater than 10 mg/L; however, about 1.4 M people depend on groundwater for their drinking supplies in those areas. Predicted high concentrations of nitrate were most prevalent in the central CONUS. In areas of predicted high nitrate concentration, applied manure, farm fertilizer , and agricultural land use were influential predictor variables. This work represents the first application of XGB to a three-dimensional national-scale groundwater quality model and provides a significant milestone in the efforts to document nitrate in groundwater across the CONUS.

Science of the Total Environment↗
USGS2025

Hyperspectral imaging of river bathymetry using an ensemble of regression trees

Remote sensing has emerged as an effective tool for characterizing river systems, and machine learning (ML) techniques could make this approach even more powerful. To explore this possibility, we developed an ML-based workflow for hyperspectral imaging of river bathymetry using an ensemble of regression trees (HIRBERT). This approach involves using paired observations of depth and reflectance to select wavelength bands as predictors and then train a depth retrieval model; applying the model to the image yields a spatially continuous bathymetric map. We used data from five rivers with diverse morphologies and optical characteristics to assess whether HIRBERT can (1) provide more accurate depth estimates than a band ratio-based algorithm and (2) extend the range of depths detectable via remote sensing. Relative to single band combinations identified via optimal band ratio analysis (OBRA), regression tree ensembles improved depth retrieval performance, with observed versus predicted (OP) regression R 2 values increasing for all five sites. Similarly, HIRBERT provided more reliable depth estimates than OBRA over the full range of depths present along each river. These results suggest that by incorporating additional spectral information from multiple wavelength bands, ML could enhance bathymetric mapping across a range of river environments. In addition, we show how graphical tools can facilitate interpretation of ML-based depth retrieval models and yield insight regarding relationships between depth and reflectance. The HIRBERT workflow is packaged in free, standalone software developed to support applications in river research and management. Although ML can enhance remote sensing of river bathymetry, the limitations of this approach must also be acknowledged: Field measurements of water depth are required to train a depth retrieval model and the resulting model should only be applied to the image from which the training data were derived. The inherently image-specific nature of this approach implies that developing generalized regression tree ensembles that could be applied at larger scales would require additional research.

California, Idaho, Nebraska, Oregon, Wyoming↗
USGS2025

A generalized deep learning model to detect and classify volcano seismicity

Volcano seismicity is often detected and classified based on its spectral properties. However, the wide variety of volcano seismic signals and increasing amounts of data make accurate, consistent, and efficient detection and classification challenging. Machine learning (ML) has proven very effective at detecting and classifying tectonic seismicity, particularly using Convolutional Neural Networks (CNNs) and leveraging labeled datasets from regional seismic networks. Progress has been made applying ML to volcano seismicity, but efforts have typically been focused on a single volcano and are often hampered by the limited availability of training data. We build on the method of Tan et al. [2024] ( 10.1029/2024JB029194 ) to generalize a spectrogram-based CNN termed the VOlcano Infrasound and Seismic Spectrogram Neural Network ( VOISS-Net ) to detect and classify volcano seismicity at any volcano. We use a diverse training dataset of over 270,000 spectrograms from multiple volcanoes: Pavlof, Semisopochnoi, Tanaga, Takawangha, and Redoubt volcanoes\replaced (Alaska, USA); Mt. Etna (Italy); and Kīlauea, Hawai`i (USA). These volcanoes present a wide range of volcano seismic signals, source-receiver distances, and eruption styles. Our generalized VOISS-Net model achieves an accuracy of 87 % on the test set. We apply this model to continuous data from several volcanoes and eruptions included within and outside our training set, and find that multiple types of tremor, explosions, earthquakes, long-period events, and noise are successfully detected and classified. The model occasionally confuses transient signals such as earthquakes and explosions and misclassifies seismicity not included in the training dataset (e.g. teleseismic earthquakes). We envision the generalized VOISS-Net model to be applicable in both research and operational volcano monitoring settings.

Volcanica↗
USGS2025

Automated snow cover detection on mountain glaciers usingspaceborne imagery and machine learning

Tracking the extent of seasonal snow on glaciers over time is critical for assessing glacier vulnerability and the response of glacierized watersheds to climate change. Existing snow cover products do not reliably distinguish seasonal snow from glacier ice and firn, preventing their use for glacier snow cover detection. Despite previous efforts to classify glacier surface facies using machine learning on local scales, currently there is no published comparison of machine learning models for classifying glacier snow cover across different satellite image products. We present an automated snow detection workflow for mountain glaciers using supervised machine-learning-based image classifiers and Landsat 8 and 9, Sentinel-2, and PlanetScope satellite imagery. We develop the image classifiers by testing numerous machine learning algorithms with training and validation data from the U.S. Geological Survey Benchmark Glacier Project glaciers. The workflow produces daily to twice monthly time series of several glacier mass balance and snowmelt indicators (snow-covered area, accumulation area ratio, and seasonal snow line) from 2013 to present. Workflow performance is assessed by comparing automatically classified images and snow lines to manual interpretations at each glacier site. The image classifiers exhibit overall accuracies of 92%–98%, K scores of 84%–96%, and F scores of 93%–98% for all image products. The median difference between automatically and manually delineated median snow line altitudes is 31m (IQR of 73to0m)across all image products. The Sentinel-2 classifier (support vector machine) produces the most accurate glacier mass balance and snowmelt indicators and distinguishes snow from ice and f irn the most reliably. Although they are less accurate, the Landsat- and PlanetScope-derived estimates greatly enhance the temporal coverage of observations. The transient accumulation area ratio produces the least noisy time series, making it the most reliable indicator for characterizing seasonal snow trends. The temporally detailed accumulation area ratio time series reveal that the timing of minimum snow cover conditions varies by up to a month between Arctic (63°N) and midlatitude (48°N) sites, underscoring the potential for bias when estimating glacier minimum snow cover conditions from a single late-summer image. Widespread application of our automated snow detection workflow has the potential to improve regional assessments of glacier mass balance, land ice representations within Earth system models, water resources, and the impacts of climate change on snow cover across broad spatial scales.

The Cryosphere↗
USGS2024

A transferable approach for quantifying benthic fish sizes and densities in annotated underwater images

1. Benthic fishes are a common target of scientific monitoring but are difficult to quantify because of their close association to bottom habitats that are hard to access. Advances in image-acquisition technologies, machine vision, and deep learning have made capturing and quantifying fishes with cameras increasingly feasible. We present a method and open-source software called ‘FishScale’ to estimate benthic fish lengths, numeric abundance, and biomass density in underwater environments assessed with down-looking monocular images. 2. ‘FishScale’ estimates fish abundances and size frequencies from near-nadir monocular images where fish have already been semantically segmented. The software accounts for lens distortion, underwater magnification effects, and fish body curvature to automatically estimate fish lengths and the areas of images where they were captured. Numeric and biomass density are estimated through a deterministic machine vision algorithm that requires a user-provided length-weight relationship for species of interest and calibration images. 3. Results from validation studies show that lengths and weights can be estimated with high accuracy and precision for round goby ( Neogobius melanostomus ) captured in distorted action camera images, and from large-bodied lake trout ( Salvelinus namaycush ) imaged with a machine vision camera. The real-world utility of the approach is demonstrated in a case study estimating round goby abundances and size frequencies along a 10.7-km transect surveyed with an autonomous underwater vehicle in Lake Michigan, USA. 4. Our validation studies demonstrate that the approach estimates benthic and benthopelagic fish lengths and weights with little bias and good accuracy and precision for species with much different body shapes and sizes. The method is applicable to data collected using a variety of nadir imaging approaches with widespread applications to fisheries monitoring and quantification of any species or object for which nadir images and working distances between the camera and feature of interest are available.

Illinois, Indiana, Michigan, Wisconsin↗
USGS2024

Analysis and review of fishery-dependent data for Hawaiian nearshore noncommercial fisheries

Noncommercial, shore-based fisheries provide economic, social, and cultural services to communities throughout the Hawaiian Islands. The State of Hawai‘i Department of Land and Natural Resources (DLNR), Division of Aquatic Resources (DAR) routinely conducts surveys to monitor noncommercial fisheries such that estimates of fishing effort and catch by gear type can be generated and used to implement more sustainable management practices. DAR executes both the Hawai‘i Marine Recreational Fishery Survey (HMRFS), a nationally standardized survey that focuses on intercepting fishers at access points (i.e., boat ramps) across the main Hawaiian Islands, and a set of roving creel surveys on O‘ahu, Maui Nui, and Kaua‘i that observe and intercept fishers at locations along the shoreline outside of those targeted by HMRFS. The latter set of creel surveys were designed to complement HMRFS by expanding its geographic coverage and thus providing a more representative picture of noncommercial fishing in Hawai‘i. Sustainable management priorities set by DAR rely on the availability of statewide, fishery- dependent data. Thus, we collate information from island-based roving creel surveys into a cohesive Statewide Creel Survey Database. Further, we provide preliminary analyses and describe ways that surveys could be streamlined to improve future data collection, analysis, and utility. In so doing, we synthesize the most detailed information to-date about noncommercial shore-based fisheries of Hawai‘i. The unprecedented spatial and temporal coverage of DAR’s dataset reveals the value of their survey efforts over the last decade to address fishery management needs. Our primary objectives, results, and conclusions are summarized below: 1) Integrate DAR roving creel survey data from different islands into a single Statewide Creel Survey Dataset (Chapter II). We describe the collation of creel survey data from O‘ahu, Maui Nui, and Kaua‘i into a statewide dataset. We also offer ways in which these surveys could be streamlined to meet the needs of managers and decision makers. Briefly, these are to create a statewide strategic plan, standardize the execution of standard operating procedures, centralize the creel survey database and associated metadata, and consider using technology that improves the data pipeline, including transitioning from paper-based to electronic systems for data entry and processing. 2) Assess whether the new Statewide Creel Survey Dataset can provide inputs for length-based stock assessments (Chapter III). Only on Maui were interviews conducted with associated catch data. There was reasonably high taxonomic coverage (42 species from 186 interviews with 310 fishers), but low sample sizes for nearly all species precluded the development of length-based stock assessments. We provide summary statistics from the existing data and briefly discuss how technologies could be used to automate analysis of images of noncommercial catch. 3) Analyze the Statewide Creel Survey Dataset for spatial and temporal patterns in fishing effort (Chapter IV): a. Visualizing noncommercial fishing pressure . We found that fishing effort (mean number of fishers observed per survey event at a site) on O'ahu was over three times greater than that recorded during similar surveys conducted on Maui or Kaua'i. We create maps that display the distribution of angling and spearfishing effort around each of the three islands. b. Factors that predict fishing “hotspots” around Maui . Fishing effort on Maui was associated with areas with more wave power and less parking availability. There were half as many fishers in areas with parking lots than in areas with parking on the road shoulder only. c. Changes in fishing effort during the COVID-19 pandemic . There was no change in fishing effort on O‘ahu during the first year of the pandemic, but there was a 20% decline in year 2 and a 33% decline in year 3, both in comparison to pre-pandemic levels. Pre-pandemic creel survey data were unavailable for Maui and Kaua‘i, but fishing effort on these islands also declined as the pandemic progressed at similar or greater rates than those observed on O‘ahu. 4) Quantify potential bias in survey methods by experimentally deriving fisher detection probabilities of shore-based and drone-based surveys (Chapter V): a. Shore-based surveys . We conducted roving creel surveys for four months at three locations around Hilo Bay, designed to emulate and estimate the efficacy of DAR standard operating procedures. There was high agreement between paired observers in counting fishers, leading to near-perfect detection probabilities of both anglers (94%) and spearfishers (97%), but relatively low agreement and detection probabilities of other fishers (throw net, ‘opihi picking, etc.) (52%). b. Drone-based surveys . We used an unmanned aerial vehicle (UAV; operated by DAR staff) to collect imagery of fishers along the Hilo Bay shoreline. We used still images and video clips (with known fishing activity) to build an online survey that was distributed to DAR and HCFRU personnel, asking them to count and categorize resource users as a snorkeler, spearfisher, angler, or other fisher. Only 40.0% of the responses correctly counted and categorized resource users in the image. Anglers were correctly identified and enumerated in 90.0% of the responses, but the correct response rates of the other three user categories ranged from 67.8% – 79.4%. Snorkelers and anglers tended to be undercounted while spearfishers and other fishers were overcounted. 5) Review the potential for incorporating emerging technologies that will improve, augment, and evolve creel survey data collection, especially for spearfishing (Chapter VI). Within the context of monitoring shore-based noncommercial fishing, we review the use of electronic data entry/processing systems with geospatial and image capabilities, field cameras, drones, smart buoys, citizen science apps, data mining social media, artificial intelligence and machine learning. We highlight several of the challenges and considerations when implementing these technologies into creel surveys and provide a synthesis of options that could be used to better estimate spearfishing. The general conclusion of this assessment is that the DAR roving creel survey program is collecting valuable data that supplement the existing HMRFS efforts. However, there are a number of areas that could be improved to make these efforts a more effective tool for decision-making processes in resource management and conservation: 1) Establishment of clear statewide and island objectives for the Statewide Creel Survey Dataset. Currently, data collection efforts are focused towards addressing a very broad purpose – supplementing the HMRFS data collection efforts. However, the results of the preliminary analyses conducted as part of this project suggest that the data could be used to address other areas of need if these objectives were clearly defined. Further, the design of the creel survey would benefit from greater standardization of survey protocols between islands and an effort to define a) the acceptable margins of error associated with the estimates generated by these data and b) the minimum level of change that the surveys would need to detect to be useful to managers. 2) Centralization of data entry, data quality assessment, and data accessibility. Currently, each DAR office manages data entry, checks the data for errors, and is responsible for managing and storing the data. Instituting a centralized data entry system, particularly an online database that can receive survey data from tablets or smartphones running a standardized data collection application would improve efficiency, reduce data entry errors, and accelerate the availability of data to managers. A substantial amount of time and effort from the project described in this report was devoted to checking the dataset for errors. The development and application of data quality assurance protocols would ensure that the data are reliable and available in a timely fashion to support management decisions. 3) Address lingering questions regarding the efficacy of current survey protocols to capture and characterize the spearfishing component of the noncommercial fishery. The results presented in the report suggest that the current creel survey protocols do a good job detecting spearfishers when present but are not capturing sufficient data about their catch or total effort. There are also questions remaining as to whether the survey times and sites are sufficiently capturing the behavior of spearfishers in Hawai‘i. A more thorough assessment – whether through additional research, alteration of survey design, or review of data by representatives of the spearfishing community – would provide insight on how to use the Statewide Creel Survey Database to inform management of spearfishing. 4) Investigate the integration of technological advancements into the creel survey methods. As priorities and needs are developed and formalized, it would be valuable to consider how various technological advancements might enhance and streamline data collection or open new avenues of inquiry.

Hawaii↗
USGS2020

Assessing the potential for spectrally based remote sensing of salmon spawning locations

Remote sensing tools are increasingly used for quantitative mapping of fluvial habitats, yet few techniques exist for continuous sampling of aquatic organisms, such as spawning salmonids. This study assessed the potential for spectrally based remote sensing of salmon spawning locations (i.e., redds) using data acquired from unmanned aircraft systems (UAS) along a large, gravel‐bed river. We developed a novel, semi‐automated approach for detecting salmon redds by applying machine learning classification and object detection techniques to UAS‐based imagery. We found that both true colour (RGB) and hyperspectral imagery could be used to identify salmon redds, though with varying degrees of accuracy. Redds were mapped with accuracies of ~0.75 from RGB imagery using logistic regression and support vector machines (SVM) classification algorithms, but this type of data could not be used to identify redds using Object‐based Image Analysis (OBIA). The hyperspectral imagery was more useful for mapping salmon redds, with accuracies greater than 0.9 for both logistic regression and SVM classifiers; OBIA of the hyperspectral data resulted in redd detection accuracies up to 0.86. The hyperspectral imagery also yielded complementary physical habitat information including water depth and substrate composition, which we quantified on the basis of a spectrally based chlorophyll absorption ratio. Overall, the hyperspectral imagery more effectively identified salmon spawning locations than RGB images and was more conducive to the classification approaches we evaluated. Each type of remotely sensed data had advantages and limitations, which are important for potential users to understand when incorporating UAS‐based data collection into river ecosystem studies.

California↗
USGS2024

Wave runup and total water level observations from time series imagery at several sites with varying nearshore morphologies

Coastal imaging systems have been developed to measure wave runup and total water level (TWL) at the shoreline, which is a key metric for assessing coastal flooding and erosion. However, extracting quantitative measurements from coastal images has typically been done through the laborious task of hand-digitization of wave runup timestacks. Timestacks are images created by sampling a cross-shore array of pixels from an image through time as waves propagate towards and run up a beach. We utilize over 7000 hand-digitized timestacks from six diverse locations to train and validate machine learning models to automate the process of TWL extraction. Using these data, we evaluate two deep learning model architectures for the task of runup detection. One is based on a fully convolutional architecture trained from scratch, and the other is a transformer-based architecture trained using transfer learning. The deep learning models provide a probability of each pixel being either wet or dry. When contoured at the 50% level (equal chance of being wet or dry), the deep learning models more accurately identified TWL maxima than minima at all sites. This resulted in accurate predictions of 2% exceedance runup, but under predictions of significant swash and over predictions of wave setup. Improved agreement with the complete TWL time series was obtained through post-processing by utilizing the wet/dry probability of each pixel to weight the contouring toward lower dryness probabilities for runup minima (maxima agreed well with observations without tuning). Overall, a transformer-based model using transfer learning provided the best agreement with wave runup statistics, including a) the 2% exceedance runup, b) significant swash, and c) wave setup at the shoreline. For a random subset of images, the model was found to be within the uncertainty range of hand-digitization. The relative success of the transfer learning model suggests that fine-tuning a large model has advantages compared to training a smaller model from scratch. Models provide per-pixel probabilistic estimates in less than 10 s per timestack on a single computational unit, versus the more than 5 min required for hand-digitization. The model is therefore well-suited for near real-time applications, allowing for the development of early warning systems for difficult to forecast events. Real-time wave runup and total water level observations can also be incorporated into coastal hazards forecasts for data assimilation and continual model validation and improvement.

Coastal Engineering↗
USGS2011

Where the wild things are: Predicting hotspots of seabird aggregations in the California Current System

Marine Protected Areas (MPAs) provide an important tool for conservation of marine ecosystems. To be most effective, these areas should be strategically located in a manner that supports ecosystem function. To inform marine spatial planning and support strategic establishment of MPAs within the California Current System, we identified areas predicted to support multispecies aggregations of seabirds (“hotspots”). We developed habitat‐association models for 16 species using information from at‐sea observations collected over an 11‐year period (1997–2008), bathymetric data, and remotely sensed oceanographic data for an area from north of Vancouver Island, Canada, to the USA/Mexico border and seaward 600 km from the coast. This approach enabled us to predict distribution and abundance of seabirds even in areas of few or no surveys. We developed single‐species predictive models using a machine‐learning algorithm: bagged decision trees. Single‐species predictions were then combined to identify potential hotspots of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Model predictions were applied to the entire California Current for four seasons (represented by February, May, July, and October) in each of 11 years. Overall, bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Predicted hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank), Southern California (adjacent to the Channel Islands), and adjacent to Vancouver Island, British Columbia, that are not currently included in protected areas. Prioritization and identification of multispecies hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA site selection, particularly if complemented by fine‐scale information for focal areas.

California↗
USGS2024

Real-time invasive sea lamprey detection using machine learning classifier models on embedded systems

Invasive sea lamprey ( Petromyzon marinus ) has historically inflicted considerable economic and ecological damage in the Great Lakes and continues to be a major threat. Accurately monitoring sea lampreys are critical to enabling the deployment of more targeted and effective control measures to minimize the impact associated with this species. This paper presents the first stand-alone system for real-time detection of sea lamprey attachment on underwater surfaces through the use of classifier models deployed on a microcontroller system. A range of low-complexity models was explored: single-layer artificial neural networks, logistic regression, Gaussian Naive-Bayes, decision trees, random forest, and Scalable, Efficient, and Fast classifieR (SEFR). Threshold models tuned using a multi-objective optimization formulation were also considered. Classifier models were trained with a dataset generated through live animal testing and presented accuracies between 80 and 86%. The models were deployed on an Arduino microcontroller platform and compared in classification accuracy, detection performance, time complexity, and memory size using real-time detection testing. Classification accuracies between 65 and 75% were observed during validation. Models demonstrated good capture rates for lamprey attachments (63–85%), and average detection delays ranging from 9 to 36 s. A video demonstrating the operation of the system during a real-time validation test is also included in this work. While there is room for improving the accuracy of the system, this research presents the first step toward an electronic sea lamprey monitoring system that can provide a detailed view of sea lamprey activity enhancing control and conservation efforts across its entire range.

Neural Computing and Applications↗
USGS2023

A big data–model integration approach for predicting epizootics and population recovery in a keystone species

Infectious diseases pose a significant threat to global health and biodiversity. Yet, predicting the spatiotemporal dynamics of wildlife epizootics remains challenging. Disease outbreaks result from complex nonlinear interactions among a large collection of variables that rarely adhere to the assumptions of parametric regression modeling. We adopted a nonparametric machine learning approach to model wildlife epizootics and population recovery, using the disease system of colonial black-tailed prairie dogs (BTPD, Cynomys ludovicianus ) and sylvatic plague as an example. We synthesized colony data between 2001 and 2020 from eight USDA Forest Service National Grasslands across the range of BTPDs in central North America. We then modeled extinctions due to plague and colony recovery of BTPDs in relation to complex interactions among climate, topoedaphic variables, colony characteristics, and disease history. Extinctions due to plague occurred more frequently when BTPD colonies were spatially clustered, in closer proximity to colonies decimated by plague during the previous year, following cooler than average temperatures the previous summer, and when wetter winter/springs were preceded by drier summers/falls. Rigorous cross-validations and spatial predictions indicated that our final models predicted plague outbreaks and colony recovery in BTPD with high accuracy (e.g., AUC generally >0.80). Thus, these spatially explicit models can reliably predict the spatial and temporal dynamics of wildlife epizootics and subsequent population recovery in a highly complex host–pathogen system. Our models can be used to support strategic management planning (e.g., plague mitigation) to optimize benefits of this keystone species to associated wildlife communities and ecosystem functioning. This optimization can reduce conflicts among different landowners and resource managers, as well as economic losses to the ranching industry. More broadly, our big data–model integration approach provides a general framework for spatially explicit forecasting of disease-induced population fluctuations for use in natural resource management decision-making.

Arizona, Colorado, Kansas, Montana, Nebraska, New ↗