SEARCH · Search NASA

Results for “Marine Ecosystems”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6

All sources NASA NTRS DOE OSTI

NASA NTRS2019

The NASA Plankton, Aerosol, Cloud, Ocean Ecosystem (PACE) Mission: an Emerging Era of Global, Hyperspectral Earth System Remote Sensing

The Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission represents NASA's next investment in satellite ocean color and the study of Earth's ocean-atmosphere system, enabling new insights into oceanographic and atmospheric responses to Earth's changing climate. PACE objectives include extending systematic cloud, aerosol, and ocean biological and biogeochemical data records, making essential ocean color measurements to further understand marine carbon cycles and ecosystem responses to a changing climate, and improving knowledge of how aerosols influence ocean ecosystems and, conversely, how ocean ecosystems and photochemical processes affect the atmosphere. PACE objectives also encompass management of fisheries, large freshwater bodies, and water quality and reducing uncertainties in climate and radiative forcing models of the Earth system. PACE observations will also provide information on radiative properties of land surfaces and characterization of the vegetation and soils that dominate their reflectance. The primary PACE instrument - the Ocean Color Instrument (OCI) - is a hyperspectral imaging radiometer that spans the ultraviolet to shortwave infrared, with a ground sample distance of 1-kilometer at nadir. This includes continuous collection of spectra from 340 to 890 nanometers in 5-nanometer steps. The PACE payload is complemented by two multi-angle polarimeters with spectral ranges that span the visible to near-infrared region. Scheduled for launch in late 2022-to-early 2023, the PACE observatory will enable significant advances in the study of Earth's biogeochemistry, carbon cycle, clouds, hydrosols, and aerosols in the ocean-atmosphere system. We present a brief overview of the PACE mission, followed by a detailed discussion of the capabilities and design concept of OCI.

Passive Remote Sensing↗

NASA NTRS2019

The NASA Plankton, Aerosol, Cloud, Ocean Ecosystem (PACE) Mission: an Emerging Era of Global, Hyperspectral Earth System Remote Sensing

Gorman, Eric T.↗

NASA NTRS1991

A Cretaceous-Tertiary mass extinction? Were most of Earth's species killed off?

For the past decade, the scientific and popular press have carried frequent articles about a catastrophic mass extinction that supposedly destroyed the majority of the earth's species, including the dinosaurs, approximately 65 million years ago. Since 1980, more than 2000 papers and books have dealt with some aspect of a mass extinction at the Cretaceous-Tertiary (K/T) boundary. One authoritative estimate of the severity of the extinctions is that 60-80% of all the living species became extinct at this boundary (Raup 1988). There appears to be a general acceptance of the fact that such a great catastrophe did occur. Most of the argument among scientists now is devoted to the determination of the cause. In this article, I argue that the species changes at the K/T boundary were neither sudden nor catastrophic. They were most likely caused by a regression of sea level that led to a decrease in primary production.

NASA Discipline Exobiology↗

NASA NTRS2016

State of the Carbon Cycle - Consequences of Rising Atmospheric CO2

The rise of atmospheric CO2, largely attributable to human activity through fossil fuel emissions and land-use change, has been dampened by carbon uptake by the ocean and terrestrial biosphere. We outline the consequences of this carbon uptake as direct and indirect effects on terrestrial and oceanic systems and processes for different regions of North America and the globe. We assess the capacity of these systems to continue to act as carbon sinks. Rising CO2 has decreased seawater pH; this process of ocean acidification has impacted some marine species and altered fundamental ecosystem processes with further effects likely. In terrestrial ecosystems, increased atmospheric CO2 causes enhanced photosynthesis, net primary production, and increased water-use efficiency. Rising CO2 may change vegetation composition and carbon storage, and widespread increases in water use efficiency likely influence terrestrial hydrology and biogeochemical cycling. Consequences for human populations include changes to ecosystem services including cultural activities surrounding land use, agricultural or harvesting practices. Commercial fish stocks have been impacted and crop production yields have been changed as a result of rising CO2. Ocean and terrestrial effects are contingent on, and feedback to, global climate change. Warming and modified precipitation regimes impact a variety of ecosystem processes, and the combination of climate change and rising CO2 contributes considerable uncertainty to forecasting carbon sink capacity in the ocean and on land. Disturbance regime (fire and insects) are modified with increased temperatures. Fire frequency and intensity increase, and insect lifecycles are disrupted as temperatures move out of historical norms. Changes in disturbance patterns modulate the effects of rising CO2 depending on ecosystem type, disturbance frequency, and magnitude of events. We discuss management strategies designed to limit the rise of atmospheric CO2 and reduce uncertainty in forecasts of decadal and centennial feedbacks of rising atmospheric CO2 on carbon storage.

Carbon Cycle↗

NASA NTRS2018

Biogeochemical Effects of Rising Atmospheric CO2 on Terrestrial and Ocean Systems

Rising carbon dioxide (CO2) has decreased seawater pH at long-term observing stations around the world, including in the open ocean north of Oahu, Hawaii, near Alaska's Aleutian Islands, the Gulf of Maine shore, and on Gray's Reef in the southeastern United States. This ocean acidification process has already affected some marine species and altered fundamental ecosystem processes, and further effects are likely. While atmospheric CO rises at approximately the same rate all over the globe, its non-climate effects on land vary depending on climate and dominant species. In terrestrial ecosystems, rising atmospheric CO concentrations are expected to increase plant photosynthesis, growth, and water-use efficiency, though these effects are reduced when nutrients, drought or other factors limit plant growth. Rising CO would likely change carbon storage and influence terrestrial hydrology and biogeochemical cycling, but concomitant effects on vegetation composition and nutrient feedbacks are challenging to predict, making decadal forecasts uncertain. Consequences of rising atmospheric CO are expected to include difficult-to-predict changes in the ecosystem services that terrestrial and ocean systems provide to humans. For instance, ocean acidification resulting from rising CO has decreased the supply of larvae that sustains commercial shellfish production in the northwestern United States. In addition, CO fertilization (increases) plus warming (decreases) are changing terrestrial crop yields. Continued persistence of uptake of carbon by the land and ocean is uncertain. Climate and environmental change create complex feedbacks to the carbon cycle and it is not clear how feedbacks modulate future effects of rising CO on carbon sinks. These are several mechanisms that could reduce future sink capacity.

Biogeochemical↗

NASA NTRS2018

Satellite Remote Sensing: Ocean Color

Satellite ocean color instruments routinely provide global, synoptic views of the Earth's marine biosphere. These spaceborne radiometers measure light exiting the top of the atmosphere at discrete wavelengths in the ultraviolet to shortwave infrared region of the spectrum. This includes measurements of the color of the ocean - information used to infer the contents of the sunlit upper ocean, such as concentrations of phytoplankton, suspended sediments, and dissolved organic carbon. Continuous marine biological, ecological, and biogeochemical data records from satellite ocean color instruments now span over twenty years. This time-series not only supports Earth system and climate research, but also ecosystem and watershed management activities, including detection of nuisance and harmful algal blooms.

Biosphere↗

NASA NTRS2018

NASA Fluid Lensing & MiDAR - Next-Generation Remote Sensing Technologies for Aquatic Remote Sensing

Piti's Tepungan Bay and Tumon Bay, two of five marine preserves in Guam, have not been mapped to a level of detail sufficient to support proposed management strategies. This project addresses this gap by providing high resolution maps to promote sustainable, responsible use of the area while protecting natural resources. Dr. Chirayath, a research scientist at the NASA Ames Laboratory, developed a theoretical model and algorithm called 'Fluid Lensing'. Fluid lensing removes optical distortions caused by moving water, improving the clarity of the images taken of the corals below the surface. We will also be using MiDAR, a next-generation remote sensing instrument that provides real-time multispectral video using an array of LED emitters coupled with NASA's FluidCam Imaging System, which may assist Guam's coral reef response team in understanding the severity and magnitude of coral bleaching events. This project will produce a 3D orthorectified model of the shallow water coral reef ecosystems in Tumon Bay and Piti marine preserves. These 3D models may be printed, creating a tactile diorama and increasing understanding of coral reefs among various audiences, including key decision makers. More importantly, the final data products can enable accurate and quantitative health assessment capabilities for coral reef ecosystems.

Aquatic↗

NASA NTRS2022

PACE: How One NASA Mission Aligns With the United Nations Decade of Ocean Science for Sustainable Development (Ocean Shot #1)

The Plankton, Aerosol, Cloud, ocean Ecosystem (PACE; https://pace.gsfc.nasa.gov) mission, scheduled for launch in January 2024, will extend the continuous high-quality ocean color, atmospheric aerosol, and cloud data records begun by NASA in the late 1990s, building on the heritage of the Coastal Zone Color Scanner (CZCS), Sea-viewing Wide Field-of-view Sensor (SeaWiFS), Moderate Resolution Imaging Spectroradiometer (MODIS), and Visible Infrared Imaging Radiometer Suite (VIIRS) (Figure 1). PACE’s global hyperspectral imaging radiometer design concept will enable new discoveries in Earth’s living ocean (Figure 2), such as the diversity of organisms fueling marine food webs and how aquatic ecosystems respond to environmental change. Its instrument payload (Figure 3) will also observe Earth’s atmosphere to study clouds, airborne aerosol particles, and the interactions between the two. Looking at the ocean, clouds, and aerosols together will improve our knowledge of the roles each plays in our evolving planet. Other applications of PACE science data records—from identifying the frequency, extent, and duration of aquatic harmful algal blooms to improving our understanding of air quality—will result in direct economic, recreational, and societal benefits. Ultimately, by extending and expanding NASA’s long record of global Earth satellite observations, the PACE mission will monitor our home planet in new and advanced ways in the coming decade.

Ocean color↗

NASA NTRS1993

Microscale characterization of dissolved organic matter production and uptake in marine microbial mat communities

Intertidal marine microbial mats exhibited biologically mediated uptake of low molecular weight dissolved organic matter (DOM), including D-glucose, acetate, and an L-amino acid mixture at trace concentrations. Uptake of all compounds occurred in darkness, but was frequently enhanced under natural illumination. The photosystem 2 inhibitor, 3-(3,4-dichlorophenyl)-1,1-dimethyl urea (DCMU) generally failed to inhibit light-stimulated DOM uptake. Occasionally, light plus DCMU-amended treatments led to uptake rates higher than light-incubated samples, possibly due to phototrophic bacteria present in subsurface anoxic layers. Uptake was similar with either 3H- or 14C-labeled substrates, indicating that recycling of labeled CO2 via photosynthetic fixation was not interfering with measurements of light-stimulated DOM uptake. Microautoradiographs showed a variety of pigmented and nonpigmented bacteria and, to a lesser extent, cyanobacteria and eucaryotic microalgae involved in light-mediated DOM uptake. Light-stimulated DOM uptake was often observed in bacteria associated with sheaths and mucilage surrounding filamentous cyanobacteria, revealing a close association of organisms taking up DOM with photoautotrophic members of the mat community. The capacity for dark- and light-mediated heterotrophy, coupled to efficient retention of fixed carbon in the mat community, may help optimize net production and accretion of mats, even in oligotrophic waters.

NASA Discipline Exobiology↗

NASA NTRS1996

Calibrating the Ordovician Radiation of marine life: implications for Phanerozoic diversity trends

It has long been suspected that trends in global marine biodiversity calibrated for the Phanerozoic may be affected by sampling problems. However, this possibility has not been evaluated definitively, and raw diversity trends are generally accepted at face value in macroevolutionary investigations. Here, we analyze a global-scale sample of fossil occurrences that allows us to determine directly the effects of sample size on the calibration of what is generally thought to be among the most significant global biodiversity increases in the history of life: the Ordovician Radiation. Utilizing a composite database that includes trilobites, brachiopods, and three classes of molluscs, we conduct rarefaction analyses to demonstrate that the diversification trajectory for the Radiation was considerably different than suggested by raw diversity time-series. Our analyses suggest that a substantial portion of the increase recognized in raw diversity depictions for the last three Ordovician epochs (the Llandeilian, Caradocian, and Ashgillian) is a consequence of increased sample size of the preserved and catalogued fossil record. We also use biometric data for a global sample of Ordovician trilobites, along with methods of measuring morphological diversity that are not biased by sample size, to show that morphological diversification in this major clade had leveled off by the Llanvirnian. The discordance between raw diversity depictions and more robust taxonomic and morphological diversity metrics suggests that sampling effects may strongly influence our perception of biodiversity trends throughout the Phanerozoic.

Non-NASA Center↗

NASA NTRS2020

NeMO-Net – The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment

We present NeMO-Net, the Srst open-source deep convolutional neural network (CNN) and interactive learning and training software aimed at assessing the present and past dynamics of coral reef ecosystems through habitat mapping into 10 biological and physical classes. Shallow marine systems, particularly coral reefs, are under significant pressures due to climate change, ocean acidification, and other anthropogenic pressures, leading to rapid, often devastating changes, in these fragile and diverse ecosystems. Historically, remote sensing of shallow marine habitats has been limited to meter-scale imagery due to the optical effects of ocean wave distortion, refraction, and optical attenuation. NeMO-Net combines 3D cm-scale distortion-free imagery captured using NASA FluidCam and Fluid lensing remote sensing technology with low resolution airborne and spaceborne datasets of varying spatial resolutions, spectral spaces, calibrations, and temporal cadence in a supercomputer-based machine learning framework. NeMO-Net augments and improves the benthic habitat classification accuracy of low-resolution datasets across large geographic ad temporal scales using high-resolution training data from FluidCam.NeMO-Net uses fully convolutional networks based upon ResNet and ReSneNet to perform semantic segmentation of remote sensing imagery of shallow marine systems captured by drones, aircraft, and satellites, including WorldView and Sentinel. Deep Laplacian Pyramid Super-Resolution Networks (LapSRN) alongside Domain Adversarial Neural Networks (DANNs) are used to reconstruct high resolution information from low resolution imagery, and to recognize domain-invariant features across datasets from multiple platforms to achieve high classification accuracies, overcoming inter-sensor spatial, spectral and temporal variations.Finally, we share our online active learning and citizen science platform, which allows users to provide interactive training data for NeMO-Net in 2D and 3D, integrated within a deep learning framework. We present results from the PaciSc Islands including Fiji, Guam and Peros Banhos 1 1 2 1 3 1 where 24-class classification accuracy exceeds 91%.

Chirayath, Ved↗

NASA NTRS2019

The Plankton, Aerosol, Cloud, Ocean Ecosystem (PACE) Mission: Status, Science, Advances

The PACE mission represents NASA’s next investment in ocean color, cloud, and aerosol data records to enable continued and advanced insight into oceanographic and atmospheric responses to Earth’s changing climate. The Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission represents NASA’s next investment in satellite ocean color and the study of Earth’s ocean-atmosphere system, enabling new insights into oceanographic and atmospheric responses to Earth's changing climate. PACE objectives include extending systematic cloud, aerosol, and ocean biological and biogeochemical data records, making essential ocean color measurements to further understand marine carbon cycles, food web processes, and ecosystem responses to a changing climate, and improving knowledge of how aerosols influence ocean ecosystems and, conversely, how ocean ecosystems and photochemical processes affect the atmosphere. PACE objectives also encompass management of fisheries, large freshwater bodies, and air and water quality and reducing uncertainties in climate and radiative forcing models of the Earth system. PACE observations will provide information on radiative properties of land surfaces and characterization of the vegetation and soils that dominate their reflectance. The primary PACE instrument is a spectrometer that spans the ultraviolet to shortwave infrared, with a ground sample distance of 1-km at nadir. This payload is complemented by two multi-angle polarimeters with spectral ranges that span the visible to near-infrared region. Scheduled for launch in late 2022-to-early 2023, the PACE observatory will enable significant advances in the study of Earth’s biogeochemistry, carbon cycle, clouds, hydrosols, and aerosols in the ocean-atmosphere-land system. Here, we present an overview of the PACE mission, including its developmental history, science objectives, instrument payload, observatory characteristics, and data products.

P Jeremy Werdell↗

NASA NTRS2018

Developing a Community of Practice for Applied Uses of Future PACE Data to Address Food Security Challenges

Ocean color satellite measurements have yielded valuable information about the base of the marine food web for over 20 years. The Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission is building an advanced spectrometer to further refine ecosystem monitoring. Higher spectral resolution data from PACE will enable identification of additional marine biological indicators and their response to multiple stressors to guide sustainable management. Seafood is an important source of protein for a significant number of people. Wild catches cannot match increasing demand and their sustainability is in question. Aquaculture is an ever more important industry to feed the world's population. We share early efforts to engage a community of practice around food security to increase satellite data product use in support of resource management, business decisions, and policy analysis. Understanding the needs of applied scientists as well as non-traditional users of satellite data early in the PACE mission process will improve planning and preparation for a broader user base and hopefully help to mitigate food insecurity.

Schollaert Uz, Stephanie↗

NASA NTRS2018

NASA NeMO-Net

We present preliminary results from NASA NeMO-Net, the first neural multi-modal observation and training network for global coral reef assessment. NeMO-Net is an open-source deep convolutional neural network (CNN) and interactive active learning training software in development which will assess the present and past dynamics of coral reef ecosystems. NeMO-Net exploits active learning and data fusion of mm-scale remotely sensed 3D images of coral reefs captured using fluid lensing with the NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as hyperspectral airborne remote sensing data from the ongoing NASA CORAL mission and lower-resolution satellite data to determine coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. Aquatic ecosystems, particularly coral reefs, remain quantitatively misrepresented by low- resolution remote sensing as a result of refractive distortion from ocean waves, optical attenuation, and remoteness. Machine learning classification of coral reefs using FluidCam mm-scale 3D data show that present satellite and airborne remote sensing techniques poorly characterize coral reef percent living cover, morphology type, and species breakdown at the mm, cm, and meter scales. Indeed, current global assessments of coral reef cover and morphology classification based on km-scale satellite data alone can suffer from segmentation errors greater than 40%, capable of change detection only on yearly temporal scales and decameter spatial scales, significantly hindering our understanding of patterns and processes in marine biodiversity at a time when these ecosystems are experiencing unprecedented anthropogenic pressures, ocean acidification, and sea surface temperature rise. NeMO-Net leverages our augmented machine learning algorithm that demonstrates data fusion of regional FluidCam (mm, cm-scale) airborne remote sensing with global low-resolution (m, km-scale) airborne and spaceborne imagery to reduce classification errors up to 80% over regional scales. Such technologies can substantially enhance our ability to assess coral reef ecosystems dynamics.

NASA↗

NASA NTRS2018

NeMO-Net & Fluid Lensing: The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment Using Fluid Lensing Augmentation of NASA EOS Data

We present preliminary results from NASA NeMO-Net, the first neural multi-modal observation and training network for global coral reef assessment. NeMO-Net is an open-source deep convolutional neural network (CNN) and interactive active learning training software in development which will assess the present and past dynamics of coral reef ecosystems. NeMO-Net exploits active learning and data fusion of mm-scale remotely sensed 3D images of coral reefs captured using fluid lensing with the NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as hyperspectral airborne remote sensing data from the ongoing NASA CORAL mission and lower-resolution satellite data to determine coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. Aquatic ecosystems, particularly coral reefs, remain quantitatively misrepresented by low-resolution remote sensing as a result of refractive distortion from ocean waves, optical attenuation, and remoteness. Machine learning classification of coral reefs using FluidCam mm-scale 3D data show that present satellite and airborne remote sensing techniques poorly characterize coral reef percent living cover, morphology type, and species breakdown at the mm, cm, and meter scales. Indeed, current global assessments of coral reef cover and morphology classification based on km-scale satellite data alone can suffer from segmentation errors greater than 40%, capable of change detection only on yearly temporal scales and decameter spatial scales, significantly hindering our understanding of patterns and processes in marine biodiversity at a time when these ecosystems are experiencing unprecedented anthropogenic pressures, ocean acidification, and sea surface temperature rise. NeMO-Net leverages our augmented machine learning algorithm that demonstrates data fusion of regional FluidCam (mm, cm-scale) airborne remote sensing with global low-resolution (m, km-scale) airborne and spaceborne imagery to reduce classification errors up to 80% over regional scales. Such technologies can substantially enhance our ability to assess coral reef ecosystems dynamics.

satellite data↗

NASA NTRS2018

NeMO-Net - The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment

In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. By combining spatial and spectral information from varying resolutions, we seek to augment and improve the classification accuracy of previously low-resolution datasets at large temporal scales.NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive learning and training software, currently being developed at NASA Ames, is aimed at assessing the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. The latest iteration uses fully convolutional networks to segment and identify coral imagery taken by UAVs and satellites, including WorldView-2 and Sentinel. We present results taken from the Indian Ocean where classification accuracy has exceeded 91% for 24 geomorphological classes given ample training data. In addition, we utilize deep Laplacian Pyramid Super-Resolution Networks (LapSRN) to reconstruct high resolution information from low resolution imagery, trained from various UAV and satellite datasets. Finally, in the case of insufficient training data, we have developed an interactive online platform that allows users to easily segment and submit their classifications, which has been integrated with the current NeMO-Net workflow. Specifically, we present results from the Fiji islands in which preliminary user data has allowed for the accurate identification of 9 separate classes, despite issues such as cloud shadowing and spectral variation. The project is being supported by NASA's Earth Science Technology Office (ESTO) Advanced Information Systems Technology (AIST-16) Program.

Neural↗

NASA NTRS2017

NeMO-Net The Neural Multi-Modal Observation Training Network for Global Coral Reef Assessment

In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. Exploiting the fine-scaled features of these datasets, machine learning methods such as MAP, PCA, and SVM can not only accurately classify the living cover and morphology of these reef systems (below 8 error), but are also able to map the spectral space between airborne and satellite imagery, augmenting and improving the classification accuracy of previously low-resolution datasets.We are currently implementing NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive active learning and training software to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. NeMO-Net will be built upon the QGIS platform to ingest UAV, airborne and satellite datasets from various sources and sensor capabilities, and through data-fusion determine the coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. To achieve this, we will exploit virtual data augmentation, the use of semi-supervised learning, and active learning through a tablet platform allowing for users to manually train uncertain or difficult to classify datasets. The project will make use of Pythons extensive libraries for machine learning, as well as extending integration to GPU and High-End Computing Capability (HECC) on the Pleiades supercomputing cluster, located at NASA Ames. The project is being supported by NASAs Earth Science Technology Office (ESTO) Advanced Information Systems Technology (AIST-16) Program.

Remote Sensin↗

NASA NTRS2017

NeMO-Net: The Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment

In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. Exploiting the fine-scaled features of these datasets, machine learning methods such as MAP, PCA, and SVM can not only accurately classify the living cover and morphology of these reef systems (below 8 percent error), but are also able to map the spectral space between airborne and satellite imagery, augmenting and improving the classification accuracy of previously low-resolution datasets. We are currently implementing NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive active learning and training software to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. NeMO-Net will be built upon the QGIS platform to ingest UAV, airborne and satellite datasets from various sources and sensor capabilities, and through data-fusion determine the coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. To achieve this, we will exploit virtual data augmentation, the use of semi-supervised learning, and active learning through a tablet platform allowing for users to manually train uncertain or difficult to classify datasets. The project will make use of Pythons extensive libraries for machine learning, as well as extending integration to GPU and High-End Computing Capability (HECC) on the Pleiades supercomputing cluster, located at NASA Ames. The project is being supported by NASAs Earth Science Technology Office (ESTO) Advanced Information Systems Technology (AIST-16) Program.

NeMO-Net↗