Geology Reports⌕ Search

SEARCH · Geology Reports

Results for “Algorithms”

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 523 records · Page 29Linked to original sources
USGS1992

Geohydrology of, and simulation of ground-water flow in, the Milford-Souhegan glacial-drift aquifer, Milford, New Hampshire

Hydrogeologic data collected since 1990 were assessed and a ground-water-flow model was refined in this study of the Milford-Souhegan glacial-drift aquifer in Milford, New Hampshire. The hydrogeologic data collected were used to refine estimates of hydraulic conductivity and saturated thickness of the aquifer, which were previously calculated during 1988-90. In October 1990, water levels were measured at 124 wells and piezometers, and at 45 stream-seepage sites on the main stem of the Souhegan River, and on small tributary streams overlying the aquifer to improve an understanding of ground-water-flow patterns and stream-seepage gains and losses. Refinement of the ground-water-flow model included a reduction in the number of active cells in layer 2 in the central part of the aquifer, a revision of simulated hydraulic conductivity in model layers 2 and representing the aquifer, incorporation of a new block-centered finite-difference ground-water-flow model, and incorporation of a new solution algorithm and solver (a preconditioned conjugate-gradient algorithm). Refinements to the model resulted in decreases in the difference between calculated and measured heads at 22 wells. The distribution of gains and losses of stream seepage calculated in simulation with the refined model is similar to that calculated in the previous model simulation. The contributing area to the Savage well, under average pumping conditions, decreased by 0.021 square miles from the area calculated in the previous model simulation. The small difference in the contrib- uting recharge area indicates that the additional data did not enhance model simulation and that the conceptual framework for the previous model is accurate.

Water-Resources Investigations Report↗
USGS1981

An examination of techniques for reformatting digital cartographic data/part 1: The raster-to- vector process.

Current graphic devices suitable for high-speed computer input and output of cartographic data are tending more and more to be raster-oriented, such as the rotating drum scanner and the color raster display. However, the majority of commonly used manipulative techniques in computer-assisted cartography and automated spatial data handling continue to require that the data be in vector format. This situation has recently precipitated the requirement for very fast techniques for converting digital cartographic data from raster to vector format for processing, and then back into raster format for plotting. The current article is part one of a two-part paper concerned with examining the state-of-the-art in these conversion techniques. In part one, algorithms to perform all phases of the raster-to-vector process are systematically outlined, and then compared in general terms. Examples of existing implementations of the raster-to-vector process are also described and evaluated. Part two will outline and compare algorithms to perform the reverse process, vector-to-raster conversion. Part two will also discuss raster-to-vector and vector-to-raster conversion as an integrated process.

Cartographica: The International Journal for Geogr↗
USGS1997

Daily air temperature interpolated at high spatial resolution over a large mountainous region

Two methods are investigated for interpolating daily minimum and maximum air temperatures ( T min and T max ) at a 1 km spatial resolution over a large mountainous region (830000 km 2 ) in the U.S. Pacific Northwest. The methods were selected because of their ability to (1) account for the effect of elevation on temperature and (2) efficiently handle large volumes of data. The first method, the neutral stability algorithm (NSA), used the hydrostatic and potential temperature equations to convert measured temperatures and elevations to sea-level potential temperatures. The potential temperatures were spatially interpolated using an inverse-squared-distance algorithm and then mapped to the elevation surface of a digital elevation model (DEM). The second method, linear lapse rate adjustment (LLRA), involved the same basic procedure as the NSA, but used a constant linear lapse rate instead of the potential temperature equation. Cross-validation analyses were performed using the NSA and LLRA methods to interpolate T min and T max each day for the 1990 water year, and the methods were evaluated based on mean annual interpolation error (IE). The NSA method showed considerable bias for sites associated with vertical extrapolation. A correction based on climate station/grid cell elevation differences was developed and found to successfully remove the bias. The LLRA method was tested using 3 lapse rates, none of which produced a serious extrapolation bias. The bias-adjusted NSA and the 3 LLRA methods produced almost identical levels of accuracy (mean absolute errors between 1.2 and 1.3°C), and produced very similar temperature surfaces based on image difference statistics. In terms of accuracy, speed, and ease of implementation, LLRA was chosen as the best of the methods tested.

Columbia River basin↗
USGS2024

Automatic identification and quantification of volcanic hotspots in Alaska using HotLINK: The hotspot learning and identification network

An increase in volcanic thermal emissions can indicate subsurface and surface processes that precede, or coincide with, volcanic eruptions. Space-borne infrared sensors can detect hotspots—defined here as localized volcanic thermal emissions—in near-real-time. However, automatic hotspot detection systems are needed to efficiently analyze the large quantities of data produced. While hotspots have been automatically detected for over 20 years with simple thresholding algorithms, new computer vision technologies, such as convolutional neural networks (CNNs), can enable improved detection capabilities. Here we introduce HotLINK: the Hotspot Learning and Identification Network, a CNN trained to detect hotspots with a dataset of −3,800 satellite-based, Visible Infrared Imaging Radiometer Suite (VIIRS) images from Mount Veniaminof and Mount Cleveland volcanoes, Alaska. We find that our model achieves an accuracy of 96% (F1-score 0.92) when evaluated on −1,700 unseen images from the same volcanoes, and 95% (F1-score 0.67) when evaluated on −3,000 images from six additional Alaska volcanoes (Augustine Volcano, Bogoslof Island, Okmok Caldera, Pavlof Volcano, Redoubt Volcano, Shishaldin Volcano). In comparison with an existing threshold-based hotspot detection algorithm, MIROVA (Coppola et al., Geological Society, London, Special Publications, 2016, 426, 181–205), our model detects 22% more hotspots and produces 12% fewer false positives. Additional testing on −700 labeled Moderate Resolution Imaging Spectroradiometer (MODIS) images from Mount Veniaminof demonstrates that our model is applicable to this sensor’s data as well, achieving an accuracy of 98% (F1-score 0.95). We apply HotLINK to 10 years of VIIRS data and 22 years of MODIS data for the eight aforementioned Alaska volcanoes and calculate the radiative power of detected hotspots. From these time series we find that HotLINK accurately characterizes background and eruptive periods, similar to MIROVA, but also detects more subtle warming signals, potentially related to volcanic unrest. We identify three advantages to our model over its predecessors: 1) the ability to detect more subtle volcanic hotspots and produce fewer false positives, especially in daytime images; 2) probabilistic predictions provide a measure of detection confidence; and 3) its transferability, i.e., the successful application to multiple sensors and multiple volcanoes without the need for threshold tuning, suggesting the potential for global application.

Alaska↗
USGS2021

A novel framework to predict relative habitat selection in aquatic systems: Applying machine learning and resource selection functions to acoustic telemetry data from multiple shark species

Resource selection functions (RSFs) have been widely applied to animal tracking data to examine relative habitat selection and to help guide management and conservation strategies. While readily used in terrestrial ecology, RSFs have yet to be extensively used within marine systems. As acoustic telemetry continues to be a pervasive approach within marine environments, incorporation of RSFs can provide new insights to help prioritize habitat protection and restoration to meet conservation goals. To overcome statistical hurdles and achieve high prediction accuracy, machine learning algorithms could be paired with RSFs to predict relative habitat selection for a species within and even outside the monitoring range of acoustic receiver arrays, making this a valuable tool for marine ecologists and resource managers. Here, we apply RSFs using machine learning to an acoustic telemetry dataset of four shark species to explore and predict species-specific habitat selection within a marine protected area. In addition, we also apply this RSF-machine learning approach to investigate predator-prey relationships by comparing and averaging tiger shark relative selection values with the relative selection values derived for eight potential prey-species. We provide methodological considerations along with a framework and flexible approach to apply RSFs with machine learning algorithms to acoustic telemetry data and suggest marine ecologists and resource managers consider adopting such tools to help guide both conservation and management strategies.

Buck Island Reef National Monument, St Croix↗
USGS2022

Medium spatial resolution mapping of global land cover and land cover change across multiple decades from Landsat

Land cover maps are essential for characterizing the biophysical properties of the Earth’s land areas. Because land cover information synthesizes a rich array of information related to both the ecological condition of land areas and their exploitation by humans, they are widely used for basic and applied research that requires information related to land surface properties (e.g., terrestrial carbon models, water balance models, weather, and climate models) and are core inputs to models and analyses used by natural resource scientists and land managers. As the Earth’s global population has grown over the last several decades rates of land cover change have increased dramatically, with enormous impacts on ecosystem services (e.g., biodiversity, water supply, carbon sequestration, etc.). Hence, accurate information related to land cover is essential for both managing natural resources and for understanding society’s ecological, biophysical, and resource management footprint. To address the need for high-quality land cover information we are using the global record of Landsat observations to compile annual maps of global land cover from 2001 to 2020 at 30 m spatial resolution. To create these maps we use features derived from time series of Landsat imagery in combination with ancillary geospatial data and a large database of training sites to classify land cover at annual time step. The algorithm that we apply uses temporal segmentation to identify periods with stable land cover that are separated by breakpoints in the time series. Here we provide an overview of the methods and data sets we are using to create global maps of land cover. We describe the algorithms used to create these maps and the core land cover data sets that we are creating through this effort, and we summarize our approach to accuracy assessment. We also present a synthesis of early results and discuss the strengths and weaknesses of our early map products and the challenges that we have encountered in creating global land cover data sets from Landsat. Initial accuracy assessment for North America shows good overall accuracy (77.0 ± 2.0% correctly classified) and 79.8% agreement with the European Space Agency (ESA) WorldCover product. The land cover mapping results we report provide the foundation for robust, repeatable, and accurate mapping of global land cover and land cover change across multiple decades at 30 m spatial resolution from Landsat.

Frontiers in Remote Sensing↗
USGS2021

Surface flow velocities from space: Particle image velocimetry of satellite video of a large, sediment-laden river

Conventional, field-based streamflow monitoring in remote, inaccessible locations such as Alaska poses logistical challenges. Safety concerns, financial considerations, and a desire to expand water-observing networks make remote sensing an appealing alternative means of collecting hydrologic data. In an ongoing effort to develop non-contact methods for measuring river discharge, we evaluated the potential to estimate surface flow velocities from satellite video of a large, sediment-laden river in Alaska via particle image velocimetry (PIV). In this setting, naturally occurring sediment boil vortices produced distinct water surface features that could be tracked from frame to frame as they were advected by the flow, obviating the need to introduce artificial tracer particles. In this study, we refined an end-to-end workflow that involved stabilization and geo-referencing, image preprocessing, PIV analysis with an ensemble correlation algorithm, and post-processing of PIV output to filter outliers and scale and geo-reference velocity vectors. Applying these procedures to image sequences extracted from satellite video allowed us to produce high resolution surface velocity fields; field measurements of depth-averaged flow velocity were used to assess accuracy. Our results confirmed the importance of preprocessing images to enhance contrast and indicated that lower frame rates (e.g., 0.25 Hz) lead to more reliable velocity estimates because longer capture intervals allow more time for water surface features to translate several pixels between frames, given the relatively coarse spatial resolution of the satellite data. Although agreement between PIV-derived velocity estimates and field measurements was weak ( R 2 = 0.39) on a point-by-point basis, correspondence improved when the PIV output was aggregated to the cross-sectional scale. For example, the correspondence between cross-sectional maximum velocities inferred via remote sensing and measured in the field was much stronger ( R 2 = 0.76), suggesting that satellite video could play a role in measuring river discharge. Examining correlation matrices produced as an intermediate output of the PIV algorithm yielded insight on the interactions between image frame rate and sensor spatial resolution, which must be considered in tandem. Although further research and technological development are needed, measuring surface flow velocities from satellite video could become a viable tool for streamflow monitoring in certain fluvial environments.

Alaska↗
USGS2018

Probabilistic substrate classification with multispectral acoustic backscatter: A comparison of discriminative and generative models

We propose a probabilistic graphical model for discriminative substrate characterization, to support geological and biological habitat mapping in aquatic environments. The model, called a fully-connected conditional random field (CRF), is demonstrated using multispectral and monospectral acoustic backscatter from heterogeneous seafloors in Patricia Bay, British Columbia, and Bedford Basin, Nova Scotia. Unlike previously proposed discriminative algorithms, the CRF model considers both the relative backscatter magnitudes of different substrates and their relative proximities. The model therefore combines the statistical flexibility of a machine learning algorithm with an inherently spatial treatment of the substrate. The CRF model predicts substrates such that nearby locations with similar backscattering characteristics are likely to be in the same substrate class. The degree of allowable proximity and backscatter similarity are controlled by parameters that are learned from the data. CRF model results were evaluated against a popular generative model known as a Gaussian Mixture model (GMM) that doesn’t include spatial dependencies, only covariance between substrate backscattering response over different frequencies. Both models are used in conjunction with sparse bed observations/samples in a supervised classification. A detailed accuracy assessment, including a leave-one-out cross-validation analysis, was performed using both models. Using multispectral backscatter, the GMM model trained on 50% of the bed observations resulted in a 75% and 89% average accuracies in Patricia Bay and Bedford Basin, respectively. The same metrics for the CRF model were 78% and 95%. Further, the CRF model resulted in a 91% mean cross-validation accuracy across four substrate classes at Patricia Bay, and a 99.5% mean accuracy across three substrate classes at Bedford Basin, which suggest that the CRF model generalizes extremely well to new data. This analysis also showed that the CRF model was much less sensitive to the specific number and locations of bed observations than the generative model, owing to its ability to incorporate spatial autocorrelation in substrates. The CRF therefore may prove to be a powerful ‘spatially aware’ alternative to other discriminative classifiers.

Geosciences↗
USGS2011

Comparison of Bayesian clustering and edge detection methods for inferring boundaries in landscape genetics

Recently, techniques available for identifying clusters of individuals or boundaries between clusters using genetic data from natural populations have expanded rapidly. Consequently, there is a need to evaluate these different techniques. We used spatially-explicit simulation models to compare three spatial Bayesian clustering programs and two edge detection methods. Spatially-structured populations were simulated where a continuous population was subdivided by barriers. We evaluated the ability of each method to correctly identify boundary locations while varying: (i) time after divergence, (ii) strength of isolation by distance, (iii) level of genetic diversity, and (iv) amount of gene flow across barriers. To further evaluate the methods’ effectiveness to detect genetic clusters in natural populations, we used previously published data on North American pumas and a European shrub. Our results show that with simulated and empirical data, the Bayesian spatial clustering algorithms outperformed direct edge detection methods. All methods incorrectly detected boundaries in the presence of strong patterns of isolation by distance. Based on this finding, we support the application of Bayesian spatial clustering algorithms for boundary detection in empirical datasets, with necessary tests for the influence of isolation by distance

International Journal of Molecular Sciences↗
USGS2019

Monitoring landscape dynamics in central U.S. grasslands with harmonized Landsat-8 and Sentinel-2 time series data

Remotely monitoring changes in central U.S. grasslands is challenging because these landscapes tend to respond quickly to disturbances and changes in weather. Such dynamic responses influence nutrient cycling, greenhouse gas contributions, habitat availability for wildlife, and other ecosystem processes and services. Traditionally, coarse-resolution satellite data acquired at daily intervals have been used for monitoring. Recently, the harmonized Landsat-8 and Sentinel-2 (HLS) data increased the temporal frequency of the data. Here we investigated if the increased data frequency provided adequate observations to characterize highly dynamic grassland processes. We evaluated HLS data available for 2016 to (1) determine if data from Sentinel-2 contributed to an improvement in characterizing landscape processes over Landsat-8 data alone, and (2) quantify how observation frequency impacted results. Specifically, we investigated into estimating annual vegetation phenology, detecting burn scars from fire, and modeling within-season wetland hydroperiod and growth of aquatic vegetation. We observed increased sensitivity to the start of the growing season (SOST) with the HLS data. Our estimates of the grassland SOST compared well with ground estimates collected at a phenological camera site. We used the Continuous Change Detection and Classification (CCDC) algorithm to assess if the HLS data improved our detection of burn scars following grassland fires and found that detection was considerably influenced by the seasonal timing of the fires. The grassland burned in early spring recovered too quickly to be detected as change events by CCDC; instead, the spectral characteristics following these fires were incorporated as part of the ongoing time-series models. In contrast, the spectral effects from late-season fires were detected both by Landsat-8 data and HLS data. For wetland-rich areas, we used a modified version of the CCDC algorithm to track within-season dynamics of water and aquatic vegetation. The addition of Sentinel-2 data provided the potential to build full time series models to better distinguish different wetland types, suggesting that the temporal density of data was sufficient for within-season characterization of wetland dynamics. Although the different data frequency, in both the spatial and temporal dimensions, could cause inconsistent model estimation or sensitivity sometimes; overall, the temporal frequency of the HLS data improved our ability to track within-season grassland dynamics and improved results for areas prone to cloud contamination. The results suggest a greater frequency of observations, such as from harmonizing data across all comparable Landsat and Sentinel sensors, is still needed. For our study areas, at least a 3-day revisit interval during the early growing season (weeks 14–17) is required to provide a >50% probability of obtaining weekly clear observations.

Minnesota↗
USGS2019

Overall methodology design for the United States National Land Cover Database 2016 products

The National Land Cover Database (NLCD) 2016 provides a suite of data products, including land cover and land cover change of the conterminous United States from 2001 to 2016, at two- to three-year intervals. The development of this product is part of an effort to meet the growing demand for longer temporal duration and more frequent, accurate, and consistent land cover and change information. To accomplish this, we designed a new land cover strategy and developed comprehensive methods, models, and procedures for NLCD 2016 implementation. Major steps in the new procedures consist of data preparation, land cover change detection and classification, theme-based postprocessing, and final integration. Data preparation includes Landsat imagery selection, cloud detection, and cloud filling, as well as compilation and creation of more than 30 national-scale ancillary datasets. Land cover change detection includes single-date water and snow/ice detection algorithms and models, two-date multi-index integrated change detection models, and long-term multi-date change algorithms and models. The land cover classification includes seven-date training data creation and 14-run classifications. Pools of training data for change and no-change areas were created before classification based on integrated information from ancillary data, change-detection results, Landsat spectral and temporal information, and knowledge-based trajectory analysis. In postprocessing, comprehensive models for each land cover theme were developed in a hierarchical order to ensure the spatial and temporal coherence of land cover and land cover changes over 15 years. An initial accuracy assessment on four selected Landsat path/rows classified with this method indicates an overall accuracy of 82.0% at an Anderson Level II classification and 86.6% at the Anderson Level I classification after combining the primary and alternate reference labels. This methodology was used for the operational production of NLCD 2016 for the Conterminous United States, with final produced products available for free download.

Remote Sensing↗
USGS2020

Gap fill of Land surface temperature and reflectance products in Analysis Ready Data

The recently released Landsat Analysis Ready Data (ARD) over the United States provides the opportunity to investigate landscape dynamics using dense time series observations at 30-m resolution. However, the dataset often contains data gaps (or missing data) because of cloud contamination or data acquisition strategy. We present a new algorithm that focuses on data gap filling using clear observations from orbit overlap regions. Multiple linear regression models were established for each pixel time series to estimate stable predictions and uncertainties. The model's training data came from stratified random samples based on the time series similarity between the pixel and data from the overlap regions. The algorithm was evaluated using four tiles (5,000 × 5,000 30-m pixels for each tile) from 2018 land surface temperature data (LST) in Atlanta, Georgia. The accuracy was assessed using 1,000 randomly masked pixels and daily air temperature from eight ground stations. Both assessments showed the r2 value above 0.75, except two stations with mixed Landsat pixels. We also compared our results with the eMODIS LST product in terms of annual mean temperature. The two maps showed a similar spatial pattern at the region level, but our results showed more spatial detail in the urban area that matched the pattern of impervious surface. We also applied the method on ARD surface reflectance bands at Fairbanks, Alaska, to illustrate its improvements in surface reflectance products and in land change modeling. This approach can also be applied to other datasets, vegetation indexes, or spectral reflectance bands of other sensors.

Remote Sensing↗
USGS2020

Inferring surface flow velocities in sediment-laden Alaskan rivers from optical image sequences acquired from a helicopter

The remote, inaccessible location of many rivers in Alaska creates a compelling need for remote sensing approaches to streamflow monitoring. Motivated by this objective, we evaluated the potential to infer flow velocities from optical image sequences acquired from a helicopter deployed above two large, sediment-laden rivers. Rather than artificial seeding, we used an ensemble correlation particle image velocimetry (PIV) algorithm to track the movement of boil vortices that upwell suspended sediment and produce a visible contrast at the water surface. This study introduced a general, modular workflow for image preparation (stabilization and geo-referencing), preprocessing (filtering and contrast enhancement), analysis (PIV), and postprocessing (scaling PIV output and assessing accuracy via comparison to field measurements). Applying this method to images acquired with a digital mapping camera and an inexpensive video camera highlighted the importance of image enhancement and the need to resample the data to an appropriate, coarser pixel size and a lower frame rate. We also developed a Parameter Optimization for PIV (POP) framework to guide selection of the interrogation area (IA) and frame rate for a particular application. POP results indicated that the performance of the PIV algorithm was highly robust and that relatively large IAs (64–320 pixels) and modest frame rates (0.5–2 Hz) yielded strong agreement ( R 2 > 0 . 9 "> R 2 > 0 . 9 ) between remotely sensed velocities and field measurements. Similarly, analysis of the sensitivity of PIV accuracy to image sequence duration showed that dwell times as short as 16 s would be sufficient at a frame rate of 1 Hz and could be cut in half if the frame rate were doubled. The results of this investigation indicate that helicopter-based remote sensing of velocities in sediment-laden rivers could contribute to noncontact streamgaging programs and enable reach-scale mapping of flow fields.

Alaska↗
USGS2021

Exploring VIIRS continuity with MODIS in an expedited capability for monitoring drought-related vegetation conditions

Vegetation has been effectively monitored using remote sensing time-series vegetation index (VI) data for several decades. Drought monitoring has been a common application with algorithms tuned to capturing anomalous temporal and spatial vegetation patterns. Drought stress models, such as the Vegetation Drought Response Index (VegDRI), often use VIs like the Normalized Difference Vegetation Index (NDVI). The EROS expedited Moderate Resolution Imaging Spectroradiometer (eMODIS)-based, 7-day NDVI composites are integral to the VegDRI. As MODIS satellite platforms (Terra and Aqua) approach mission end, the Visible Infrared Imaging Radiometer Suite (VIIRS) presents an alternate NDVI source, with daily collection, similar band passes, and moderate spatial resolution. This study provides a statistical comparison between EROS expedited VIIRS (eVIIRS) 375-m and eMODIS 250-m and tests the suitability of replacing MODIS NDVI with VIIRS NDVI for drought monitoring and vegetation anomaly detection. For continuity with MODIS NDVI, we calculated a geometric mean regression adjustment algorithm using 375-m resolution for an eMODIS-like NDVI (eVIIRS’) eVIIRS’ = 0.9887 × eVIIRS − 0.0398. The resulting statistical comparisons (eVIIRS’ vs. eMODIS NDVI) showed correlations consistently greater than 0.84 throughout the three years studied. The eVIIRS’ VegDRI results characterized similar drought patterns and hotspots to the eMODIS-based VegDRI, with near zero bias.

Kansas↗
USGS2021

Estimating actual evapotranspiration over croplands using vegetation index methods and dynamic harvested area

Advances in estimating actual evapotranspiration (ETa) with remote sensing (RS) have contributed to improving hydrological, agricultural, and climatological studies. In this study, we evaluated the applicability of Vegetation-Index (VI) -based ETa (ET-VI) for mapping and monitoring drought in arid agricultural systems in a region where a lack of ground data hampers ETa work. To map ETa (2000–2019), ET-VIs were translated and localized using Landsat-derived 3- and 2-band Enhanced Vegetation Indices (EVI and EVI2) over croplands in the Zayandehrud River Basin (ZRB) in Iran. Since EVI and EVI2 were optimized for the MODerate Imaging Spectroradiometer (MODIS), using these VIs with Landsat sensors required a cross-sensor transformation to allow for their use in the ET-VI algorithm. The before- and after- impact of applying these empirical translation methods on the ETa estimations was examined. We also compared the effect of cropping patterns’ interannual change on the annual ETa rate using the maximum Normalized Difference Vegetation Index (NDVI) time series. The performance of the different ET-VIs products was then evaluated. Our results show that ETa estimates agreed well with each other and are all suitable to monitor ETa in the ZRB. Compared to ETc values, ETa estimations from MODIS-based continuity corrected Landsat-EVI (EVI2) (EVI MccL and EVI2 MccL ) performed slightly better across croplands than those of Landsat-EVI (EVI2) without transformation. The analysis of harvested areas and ET-VIs anomalies revealed a decline in the extent of cultivated areas and a loss of corresponding water resources downstream. The findings show the importance of continuity correction across sensors when using empirical algorithms designed and optimized for specific sensors. Our comprehensive ETa estimation of agricultural water use at 30 m spatial resolution provides an inexpensive monitoring tool for cropping areas and their water consumption.

Remote Sensing↗
USGS2022

Deep and machine learning image classification of coastal wetlands using unpiloted aircraft system multispectral images and lidar datasets

The recent developments of new deep learning architectures create opportunities to accurately classify high-resolution unoccupied aerial system (UAS) images of natural coastal systems and mandate continuous evaluation of algorithm performance. We evaluated the performance of the U-Net and DeepLabv3 deep convolutional network architectures and two traditional machine learning techniques (support vector machine (SVM) and random forest (RF)) applied to seventeen coastal land cover types in west Florida using UAS multispectral aerial imagery and canopy height models (CHM). Twelve combinations of spectral bands and CHMs were used. Our results using the spectral bands showed that the U-Net (83.80–85.27% overall accuracy) and the DeepLabV3 (75.20–83.50% overall accuracy) deep learning techniques outperformed the SVM (60.50–71.10% overall accuracy) and the RF (57.40–71.0%) machine learning algorithms. The addition of the CHM to the spectral bands slightly increased the overall accuracy as a whole in the deep learning models, while the addition of a CHM notably improved the SVM and RF results. Similarly, using bands outside the three spectral bands, namely, near-infrared and red edge, increased the performance of the machine learning classifiers but had minimal impact on the deep learning classification results. The difference in the overall accuracies produced by using UAS-based lidar and SfM point clouds, as supplementary geometrical information, in the classification process was minimal across all classification techniques. Our results highlight the advantage of using deep learning networks to classify high-resolution UAS images in highly diverse coastal landscapes. We also found that low-cost, three-visible-band imagery produces results comparable to multispectral imagery that do not risk a significant reduction in classification accuracy when adopting deep learning models.

Florida↗
USGS2024

Physics-based satellite-derived bathymetry (SDB) using Landsat OLI images

The estimation of depth in optically shallow waters using satellite imagery can be efficient and cost-effective. Active sensors measure the distance traveled by an emitted laser pulse propagating through the water with high precision and accuracy if the bottom peak intensity of the waveform is greater than the noise level. However, passive optical imaging of optically shallow water involves measuring the radiance after the sunlight undergoes downward attenuation on the way to the sea floor, and the reflected light is then attenuated while moving back upward to the water surface. The difficulty of satellite-derived bathymetry (SDB) arises from the fact that the measured radiance is a result of a complex association of physical elements, mainly the optical properties of the water, bottom reflectance, and depth. In this research, we attempt to apply physics-based algorithms to solve this complex problem as accurately as possible to overcome the limitation of having only a few known values from a multispectral sensor. Major analysis components are atmospheric correction, the estimation of water optical properties from optically deep water, and the optimization of bottom reflectance as well as the water depth. Specular reflection of the sky radiance from the water surface is modeled in addition to the typical atmospheric correction. The physical modeling of optically dominant components such as dissolved organic matter, phytoplankton, and suspended particulates allows the inversion of water attenuation coefficients from optically deep pixels. The atmospheric correction and water attenuation results are used in the ocean optical reflectance equation to solve for the bottom reflectance and water depth. At each stage of the solution, physics-based models and a physically valid, constrained Levenberg–Marquardt numerical optimization technique are used. The physics-based algorithm is applied to Landsat Operational Land Imager (OLI) imagery over the shallow coastal zone of Guam, Key West, and Puerto Rico. The SDB depths are compared to airborne lidar depths, and the root mean squared error (RMSE) is mostly less than 2 m over water as deep as 30 m. As the initial choice of bottom reflectance is critical, along with the bottom reflectance library, we describe a pure bottom unmixing method based on eigenvector analysis to estimate unknown site-specific bottom reflectance.

Remote Sensing↗
USGS2024

An ensemble mean method for remote sensing of actual evapotranspiration to estimate water budget response across a restoration landscape

Estimates of actual evapotranspiration (ETa) are valuable for effective monitoring and management of water resources. In areas that lack ground-based monitoring networks, remote sensing allows for accurate and consistent estimates of ETa across a broad scale—though each algorithm has limitations (i.e., ground-based validation, temporal consistency, spatial resolution). We developed an ensemble mean ETa (EMET) product to incorporate advancements and reduce uncertainty among algorithms (e.g., energy-balance, optical-only), which we use to estimate vegetative water use in response to restoration practices being implemented on the ground using management interventions (i.e., fencing pastures, erosion control structures) on a private ranch in Baja California Sur, Mexico. This paper describes the development of a monthly EMET product, the assessment of changes using EMET over time and across multiple land use/land cover types, and the evaluation of differences in vegetation and water distribution between watersheds treated by restoration and their controls. We found that in the absence of a ground-based monitoring network, the EMET product is more robust than using a single ETa data product and can augment the efficacy of ETa-based studies. We then found increased ETa within the restored watershed when compared to the control sites, which we attribute to increased plant water availability.

Baja California Sur↗