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

Ved Chirayath1, Alan Sheng Xi Li1, Juan Luis Torres-Perez2, Michal Segal-Rozenhaimer3, Sam Purkis4 and Jarrett van den Bergh1, (1)NASA Ames Research Center, Moffett Field, CA, United States, (2)NASA Ames Research Center, Biospheric Science Branch, Moffett Field, United States, (3)NASA Ames Research Center, Moffett Field, United States, (4)Rosenstiel School of Marine, Atmospheric, and Earth Science, University of Miami, Department of Marine Geosciences, Miami, United States
Abstract:
We present NeMO-Net, the first 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 supercomputuer-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 RefineNet 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 Pacific Islands including Fiji, Guam and Peros Banhos where 24-class classification accuracy exceeds 91%.