A machine learning approach to identify barriers in stream networks demonstrates high prevalence of unmapped riverine dams

Buchanan, Brian; Sethi, Suresh A.; Cuppett, Scott; Lung, Megan E.; Jackman, George; Zarri, Liam J.; Duvall, Ethan S.; Dietrich, Jennifer E.; Sullivan, Patrick J.; Dominitz, Alon; Archibald, J. A.; Flecker, Alexander S.; Rahm, Brian G.

doi:10.1016/j.jenvman.2021.113952

Cited by 17 publications

(16 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Europe, collaboration amongst diverse environmental stakeholders and widespread use of crowdsourcing have put needed data in the hands of eel biologists (Belletti et al, 2020; Drouineau et al, 2021). The recent development of a machine learning algorithm that uses geospatial and lidar data to identify dams, even small ones, with reasonable accuracy (true positive rate 89%, false positive rate 1.2%) (Buchanan et al, 2022) may open the door to comprehensive inventories of dams of all sizes.…”

Section: Discussionmentioning

confidence: 99%

“…However, databases concentrate on medium and large dams, leaving most of the several million small dams in the US uninventoried (Table 3 and Table S1). A newly developed machine learning algorithm, used to identify dams in Southeastern New York State, indicated that 80%-94% of dams were previously undocumented by any database (Buchanan et al, 2022). Small dam density in US Atlantic states, based on counts of 0.5-40 ha ponds on 1:24,000 scale maps (Fleming & Stubbs, 2012) and the assumption that two-thirds of ponds are formed by dams (Renwick, 2017), is 0.423 dams/km 2 (Table S2).…”

Section: Use Of Species and Environmental Databasesmentioning

confidence: 99%

“…The recent development of a machine learning algorithm that uses geospatial and lidar data to identify dams, even small ones, with reasonable accuracy (true positive rate 89%, false positive rate 1.2%) (Buchanan et al, 2022) may open the door to comprehensive inventories of dams of all sizes.…”

Section: Datamentioning

confidence: 99%

See 2 more Smart Citations

Thirteen novel ideas and underutilised resources to support progress towards a range‐wide American eel stock assessment

Cairns

Benchetrit

Bernatchez

et al. 2022

Fisheries Management Eco

View full text Add to dashboard Cite

A robust assessment of the American eel (Anguilla rostrata) stock, required to guide conservation efforts, is challenged by the species’ vast range, high variability in demographic parameters and data inadequacies. Novel ideas and underutilised resources that may assist both analytic assessments and spatially oriented modelling include (1) species and environmental databases; (2) mining of data from scattered sources; (3) infilling of data gaps by spatial analysis; (4) age estimation from measurements of DNA methylation; evaluation of eel abundance by (5) larval, (6) glass‐bottom boat, (7) net enclosure and (8) eDNA surveys; (9) accounting for dam‐induced habitat increases in eel watercourse modelling; (10) spatially oriented modelling with and without temporal components; (11) geographically nested modelling of glass eel recruitment; (12) spawner per recruit modelling and (13) life cycle modelling to examine larval allocation effects. Eel biologists are too few to gather the required assessment data across all of the species’ range. Public posting of electrofishing and eDNA metabarcoding data sets and the use of machine learning techniques to comprehensively inventory small dams will help meet some data needs. These approaches address only a small proportion of the assessment challenges that face American eels. Worldwide collaboration amongst Anguilla scientists is a key enabler of progress towards stock assessment goals.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Use Of Species and Environmental Databasesmentioning

confidence: 99%

See 1 more Smart Citation

Thirteen novel ideas and underutilised resources to support progress towards a range‐wide American eel stock assessment

Cairns

Benchetrit

Bernatchez

et al. 2022

Fisheries Management Eco

View full text Add to dashboard Cite

show abstract

“…Consideration of habitat connectivity at landscape scales and its impact on species' ecology is increasingly recognized as crucial for conservation planning in both terrestrial and aquatic systems (Correa Ayram et al, 2016; Flitcroft et al, 2019; Wu, 2013). River fragmentation associated with water control infrastructure is widespread across urbanized areas as both current and derelict dams and culverts remain in place (e.g., Buchanan et al, 2022; Januchowski‐Hartley et al, 2013). Accelerating coastal human population expansion may lead to increased urbanization across salmon‐bearing watersheds (Freeman et al, 2019; Neumann et al, 2015).…”

Section: Discussionmentioning

confidence: 99%

Juvenile salmon habitat use drives variation in growth and highlights vulnerability to river fragmentation

et al. 2022

Self Cite

View full text Add to dashboard Cite

Widespread stream network fragmentation from dams and culverts has altered habitat connectivity in river ecosystems and presents an acute threat to migratory fish. To support watershed management for an iconic migratory fish group, we assessed juvenile salmon growth outcomes across habitat use strategies and characterized how these life histories may be impacted by stream connectivity loss. Juvenile coho salmon (Oncorhynchus kisutch) in the Big Lake drainage, Alaska, USA, were individually tracked over 2012-2013 and categorized into habitat use behaviors, with fish either remaining in streams throughout freshwater residency or migrating seasonally to overwinter in lake habitats. Size, growth rate, and body condition of smolts (n = 1113) were compared across habitat use strategies. Juvenile coho salmon that moved seasonally to lake overwintering habitats, the most frequently observed strategy, grew faster and were significantly larger as smolts compared to their counterparts who remained in streams exclusively (spring Age 1 fish: 18% larger by weight, 9% faster growth rate; spring Age 2+ fish: 26% heavier, 11% faster

show abstract

“…Application of machine learning techniques for classification of water and land pixels with focus on assessing river morphological characteries is gaining prominence. Some recent examples include monitoring channel morphology of Yangtze River headwater using lightweight neural network [26], deep convolutional neural network for characterizing riverscapes in Norway [27], and identifying barriers in stream network using random forest classifier [28]. However, machine learning methods require training datasets, which are not readily available in countries like Myanmar.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Large-Scale Seasonal River Morphological Changes in Ayeyarwady River Using Optical Remote Sensing Data

et al. 2022

View full text Add to dashboard Cite

Monitoring morphologically dynamic rivers over large spatial domains at an adequate frequency is essential for informed river management to protect human life, ecosystems, livelihoods, and critical infrastructures. Leveraging the advancements in cloud-based remote sensing data processing through Google Earth Engine (GEE), a web-based, freely accessible seasonal river morphological monitoring system for Ayeyarwady River, Myanmar was developed through a collaborative process to assess changes in river morphology over time and space. The monitoring system uses Landsat satellite data spanning a 31-year long period (1988–2019) to map river planform changes along 3881.4 km of river length including Upper Ayeyarwady, Lower Ayeyarwady, and Chindwin. It is designed to operate on a seasonal timescale by comparing pre-monsoon and post-monsoon channel conditions to provide timely information on erosion and accretion areas for the stakeholders to support planning and management. The morphological monitoring system was validated with 85 reference points capturing the field conditions in 2019 and was found to be reliable for operational use with an overall accuracy of 89%. The average eroded riverbank area was calculated at around 45, 101, and 134 km2 for Chindwin, Upper Ayeyarwady, and Lower Ayeyarwady, respectively. The historical channel change assessment aided us to identify and categorize river reaches according to the frequency of changes. Six hotspots of riverbank erosion were identified including near Mandalay city, the confluence of Upper Ayeyarwady and Chindwin, near upstream of Magway city, downstream of Magway city, near Pyay city, and upstream of the Ayeyarwady delta. The web-based monitoring system simplifies the application of freely available remote sensing data over the large spatial domain to assess river planform changes to support stakeholders’ operational planning and prioritizing investments for sustainable Ayeyarwady River management.

show abstract

A machine learning approach to identify barriers in stream networks demonstrates high prevalence of unmapped riverine dams

Cited by 17 publications

References 53 publications

Thirteen novel ideas and underutilised resources to support progress towards a range‐wide American eel stock assessment

Thirteen novel ideas and underutilised resources to support progress towards a range‐wide American eel stock assessment

Juvenile salmon habitat use drives variation in growth and highlights vulnerability to river fragmentation

Assessment of Large-Scale Seasonal River Morphological Changes in Ayeyarwady River Using Optical Remote Sensing Data

Contact Info

Product

Resources

About