Advancing Observation of Ocean Biogeochemistry, Biology, and Ecosystems With Cost-Effective in situ Sensing Technologies

Wang, Zhaohui Aleck; Moustahfid, Hassan; Mueller, Amy; Michel, Anna P. M.; Mowlem, Matthew C.; Glazer, Brian T.; Mooney, T. Aran; Michaels, William; McQuillan, Jonathan S.; Robidart, Julie; Churchill, James H.; Sourisseau, Marc; Daniel, Anne; Schaap, Allison; Monk, Sam; Friedman, Kim; Brehmer, Patrice

doi:10.3389/fmars.2019.00519

Cited by 53 publications

(44 citation statements)

References 170 publications

(183 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new approach, CANYON-MED, was subsequently created and trained using an artificial neural network ensemble model. The approach takes advantage of the accuracy of EOVs systematically measured today (Wang et al, 2019), whether during scientific cruises or by autonomous platforms. The model was built as an ensemble of 10 optimized multi-layered perceptron feed-forward neural networks.…”

Section: Discussionmentioning

confidence: 99%

A Regional Neural Network Approach to Estimate Water-Column Nutrient Concentrations and Carbonate System Variables in the Mediterranean Sea: CANYON-MED

et al. 2020

View full text Add to dashboard Cite

A regional neural network-based method, "CANYON-MED" is developed to estimate nutrients and carbonate system variables specifically in the Mediterranean Sea over the water column from pressure, temperature, salinity, and oxygen together with geolocation and date of sampling. Six neural network ensembles were developed, one for each variable (i.e., three macronutrients: nitrates (NO − 3), phosphates (PO 3− 4) and silicates (SiOH 4), and three carbonate system variables: pH on the total scale (pH T), total alkalinity (A T), and dissolved inorganic carbon or total carbon (C T), trained using a specific quality-controlled dataset of reference "bottle" data in the Mediterranean Sea. This dataset is representative of the peculiar conditions of this semi-enclosed sea, as opposed to the global ocean. For each variable, the neural networks were trained on 80% of the data chosen randomly and validated using the remaining 20%. CANYON-MED retrieved the variables with good accuracies (Root Mean Squared Error): 0.73 µmol.kg −1 for NO − 3 , 0.045 µmol.kg −1 for PO 3− 4 and 0.70 µmol.kg −1 for Si(OH) 4 , 0.016 units for pH T , 11 µmol.kg −1 for A T and 10 µmol.kg −1 for C T. A second validation on the ANTARES independent time series confirmed the method's applicability in the Mediterranean Sea. After comparison to other existing methods to estimate nutrients and carbonate system variables, CANYON-MED stood out as the most robust, using the aforementioned inputs. The application of CANYON-MED on the Mediterranean Sea data from autonomous observing systems (integrated network of Biogeochemical-Argo floats, Eulerian moorings and ocean gliders measuring hydrological properties together with oxygen concentration) could have a wide range of applications. These include data quality control or filling gaps in time series, as well as biogeochemical data assimilation and/or the initialization and validation of regional biogeochemical models still lacking crucial reference data. Matlab and R code are available at https:// github.com/MarineFou/CANYON-MED/.

show abstract

Section: Discussionmentioning

confidence: 99%

A Regional Neural Network Approach to Estimate Water-Column Nutrient Concentrations and Carbonate System Variables in the Mediterranean Sea: CANYON-MED

et al. 2020

View full text Add to dashboard Cite

show abstract

“…to improve our current sensing systems. Look for opportunities to reduce the costs of measurements without decreasing their quality (e.g., Wang et al, 2019), in such a way that future equipment could be embarked with as standard tools on cruises and/or autonomous platforms (floats, gliders).…”

Section: Priority Iv: Innovate and Develop New And Better Technologiementioning

confidence: 99%

Globally Consistent Quantitative Observations of Planktonic Ecosystems

et al. 2019

View full text Add to dashboard Cite

In this paper we review the technologies available to make globally quantitative observations of particles in general-and plankton in particular-in the world oceans, and for sizes varying from sub-microns to centimeters. Some of these technologies have been available for years while others have only recently emerged. Use of these technologies is critical to improve understanding of the processes that control abundances, distributions and composition of plankton, provide data necessary to constrain and improve ecosystem and biogeochemical models, and forecast changes in marine ecosystems in light of climate change. In this paper we begin by providing the motivation for plankton observations, quantification and diversity qualification on a global scale. We then expand on the state-of-the-art, detailing a variety of relevant and (mostly) mature technologies and measurements, including bulk measurements of plankton, pigment composition, uses of genomic, optical and acoustical methods as well

show abstract

“…Nowadays it is possible to find in general consumer market dedicated systems deployed in surface or in the bottom using underwater digital camera for monitoring and inventories. Some of them are specialized in plankton observation like "Underwater Vision Plankton" UVP, ZooSCAN, FlowCAM (Picheral et al 2010;Wang et al, 2019) others for fish and macrofauna (Brehmer et al, 2019a). The high amount of digital picture and video in database which were too time consuming to be analyzed, can now be processed using Machine Learning.…”

Section: Optical Sensors: Monitoring the Ecosystem Biodiversity And Bio-productivity For Fisheriesmentioning

confidence: 99%

“…Genetic sensors, also referred to as "Ecogenomic" Sensors (Wang et al 2019), bring a wealth of analytical power to existing ocean monitoring instruments through in situ, autonomous detection and enumeration of speci c DNA or RNA sequences, providing information to improve detecting and monitoring of harmful algal blooms, toxins, pathogens, and invasive species to protect health and coastal economies (Scholin et al, 2018). The most advanced and only commercially available genomic sensor is the Environmental Sample Processor (2 nd Generation ESP; available through McLane Labs, Woods Hole, MA).…”

Section: Genetic Sensors: Scientifically-based Decisions For Hab Impact On Coastal Fishery Resourcesmentioning

confidence: 99%

“…There is need for highquality observations at scales that resolve critical ecological processes and are timely for management needs (Szuwalski & Hollowed, 2016). Recent technological advances have improved the spatial and temporal resolution of measurements, performed during conventional scientific surveys to better understand the dynamics and organization of fish populations and their associated habitat in a rapidly changing environment (Moustahfid et al, 2012(Moustahfid et al, , 2016Wang et al, 2019). More reliable and cost-efficient sensors, platforms, and processing technologies have been deployed successfully thanks to partnerships between government agencies, academic institutions and private sectors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Advances in fisheries science through emerging observing technologies

Moustahfid

Michaels

Alger

et al. 2020

Global Oceans 2020: Singapore – U.S. Gulf Coast

Self Cite

View full text Add to dashboard Cite

Fisheries is in need for high-quality observations at scales that resolve critical ecological processes and are timely for management. Recent advances in ocean observing technologies have improved the spatial and temporal resolution of measurements, performed during conventional scientific surveys as collaborative approaches, to better understand the dynamics and organization of fish populations and their associated habitat in a rapidly changing environment. In recent years, more reliable and cost-efficient sensors, platforms, and processing technologies have been deployed successfully, which we envision in the coming decade will revolutionize the wide-scale observations pertinent to ocean ecology and biology. The aim of this work is to review the emerging sensing technologies for selected major ecological and biological parameters relevant to fisheries science, and to identify transformative directions for future development of cost-effective technologies and deployment strategies.

show abstract

Advancing Observation of Ocean Biogeochemistry, Biology, and Ecosystems With Cost-Effective in situ Sensing Technologies

Cited by 53 publications

References 170 publications

A Regional Neural Network Approach to Estimate Water-Column Nutrient Concentrations and Carbonate System Variables in the Mediterranean Sea: CANYON-MED

A Regional Neural Network Approach to Estimate Water-Column Nutrient Concentrations and Carbonate System Variables in the Mediterranean Sea: CANYON-MED

Globally Consistent Quantitative Observations of Planktonic Ecosystems

Advances in fisheries science through emerging observing technologies

Contact Info

Product

Resources

About