Oceane Boulais - Academia.edu (original) (raw)

Papers by Oceane Boulais

arXiv (Cornell University), Oct 15, 2020

As climate change increases the intensity of natural disasters, society needs better tools for ad... more As climate change increases the intensity of natural disasters, society needs better tools for adaptation. Floods, for example, are the most frequent natural disaster, but during hurricanes the area is largely covered by clouds and emergency managers must rely on nonintuitive flood visualizations for mission planning. To assist these emergency managers, we have created a deep learning pipeline that generates visual satellite images of current and future coastal flooding. We advanced a state-of-the-art GAN called pix2pixHD, such that it produces imagery that is physically-consistent with the output of an expert-validated storm surge model (NOAA SLOSH). By evaluating the imagery relative to physics-based flood maps, we find that our proposed framework outperforms baseline models in both physicalconsistency and photorealism. While this work focused on the visualization of coastal floods, we envision the creation of a global visualization of how climate change will shape our earth 10. Flood map GAN Pre-flood sat. img. Post-flood satellite image Figure 1: We have generated the first physically-consistent satellite imagery of coastal flood events (mid). During hurricanes, such as Harvey in Houston, TX, the area is largely covered by clouds and emergency responders must rely on nonintuitive flood maps, inferred from models or radar, for mission planning (bottomright, [1]). We propose a novel GAN-based pipeline to convert the flood maps into photorealistic post-flood images, enabling emergency managers to intuitively understand flood impacts.

arXiv (Cornell University), Apr 10, 2021

As climate change increases the intensity of natural disasters, society needs better tools for ad... more As climate change increases the intensity of natural disasters, society needs better tools for adaptation. Floods, for example, are the most frequent natural disaster, and better tools for flood risk communication could increase the support for floodresilient infrastructure development. Our work aims to enable more visual communication of large-scale climate impacts via visualizing the output of coastal flood models as satellite imagery. We propose the first deep learning pipeline to ensure physicalconsistency in synthetic visual satellite imagery. We advanced a state-of-the-art GAN called pix2pixHD, such that it produces imagery that is physically-consistent with the output of an expertvalidated storm surge model (NOAA SLOSH). By evaluating the imagery relative to physics-based flood maps, we find that our proposed framework outperforms baseline models in both physical-consistency and photorealism. We envision our work to be the first step towards a global visualization of how the climate challenge will shape our landscape. Continuing on this path, we show that the proposed pipeline generalizes to visualize reforestation. We also publish a dataset of over 25k labelled image-triplets to study image-to-image translation in Earth observation 1 .

Day 2 Tue, May 03, 2022

In the emerging industry of deep-sea mining for minerals and deposits (e.g., polymetallic nodules... more In the emerging industry of deep-sea mining for minerals and deposits (e.g., polymetallic nodules for nickel, cobalt, copper, and manganese), more data is required to understand the effects of sediment plume generation and predict the distribution of disturbed sediments. There are two main sources of plume generation, the first being at the active mining site where the "collector" directly removes the top layer of the sea floor. The other is the "midwater plume" consisting of unwanted sediment that was collected during extraction that is pumped back into the aphotic zone. The vast majority of plume generation is caused by the collector, causing detrimental and long-lasting impacts on sea floor ecosystems due to the lack of wave activity or strong currents at the sea floor. Therefore, it is crucial to invest in the infrastructure to support the study and constant monitoring over a large area of the sea floor where plume generation is present. Due to the limited nu...

ArXiv, 2020

Thousands of hours of marine video data are collected annually from remotely operated vehicles (R... more Thousands of hours of marine video data are collected annually from remotely operated vehicles (ROVs) and other underwater assets. However, current manual methods of analysis impede the full utilization of collected data for real time algorithms for ROV and large biodiversity analyses. FathomNet is a novel baseline image training set, optimized to accelerate development of modern, intelligent, and automated analysis of underwater imagery. Our seed data set consists of an expertly annotated and continuously maintained database with more than 26,000 hours of videotape, 6.8 million annotations, and 4,349 terms in the knowledge base. FathomNet leverages this data set by providing imagery, localizations, and class labels of underwater concepts in order to enable machine learning algorithm development. To date, there are more than 80,000 images and 106,000 localizations for 233 different classes, including midwater and benthic organisms. Our experiments consisted of training various deep ...

ArXiv, 2020

The latent space modeled by generative adversarial networks (GANs) represents a large possibility... more The latent space modeled by generative adversarial networks (GANs) represents a large possibility space. By interpolating categories generated by GANs, it is possible to create novel hybrid images. We present "Meet the Ganimals," a casual creator built on interpolations of BigGAN that can generate novel, hybrid animals called ganimals by efficiently searching this possibility space. Like traditional casual creators, the system supports a simple creative flow that encourages rapid exploration of the possibility space. Users can discover new ganimals, create their own, and share their reactions to aesthetic, emotional, and morphological characteristics of the ganimals. As users provide input to the system, the system adapts and changes the distribution of categories upon which ganimals are generated. As one of the first GAN-based casual creators, Meet the Ganimals is an example how casual creators can leverage human curation and citizen science to discover novel artifacts wi...

Proceedings of the 14th LACCEI International Multi-Conference for Engineering, Education, and Technology: “Engineering Innovations for Global Sustainability”, 2016

By forming intimate study groups, the void of community within the intense academic lifestyle of ... more By forming intimate study groups, the void of community within the intense academic lifestyle of engineering students can be filled, creating long-lasting connections throughout a student's academic career. This research paper explores and analyzes the techniques of a student-led ad-hoc study group that was formed for a core engineering course. Through examining the trends of a successful student-led study group and its evolutionary transformation enabled by social networking, techniques of developing more collaborative environments for engineering students are enhanced.

Marine Technology Society Journal, 2021

Ocean-going platforms and instruments are integrating cameras for observation and navigation, pro... more Ocean-going platforms and instruments are integrating cameras for observation and navigation, producing a deluge of visual data. The volume of this data collection can rapidly outpace researchers' abilities to process and analyze them. Recent advances in artificial intelligence enable fast, sophisticated analysis of visual data, but have had limited success in the oceanographic world due to lack of dataset standardization, sparse annotation tools, and insufficient formatting and aggregation of existing, expertly curated imagery for use by data scientists. To address this need, we are building FathomNet, a public platform that makes use of existing (and future), expertly curated data to know what is in the ocean and where it is for effective and responsible marine stewardship. This platform is modeled after popular terrestrial datasets (e.g., ImageNet, COCO) that enabled rapid advances in automated visual analysis. FathomNet seeks to engage a wide audience, from the general publi...

Marine Technology Society Journal, 2021

Scientific Reports

The ocean is experiencing unprecedented rapid change, and visually monitoring marine biota at the... more The ocean is experiencing unprecedented rapid change, and visually monitoring marine biota at the spatiotemporal scales needed for responsible stewardship is a formidable task. As baselines are sought by the research community, the volume and rate of this required data collection rapidly outpaces our abilities to process and analyze them. Recent advances in machine learning enables fast, sophisticated analysis of visual data, but have had limited success in the ocean due to lack of data standardization, insufficient formatting, and demand for large, labeled datasets. To address this need, we built FathomNet, an open-source image database that standardizes and aggregates expertly curated labeled data. FathomNet has been seeded with existing iconic and non-iconic imagery of marine animals, underwater equipment, debris, and other concepts, and allows for future contributions from distributed data sources. We demonstrate how FathomNet data can be used to train and deploy models on other...

ArXiv, 2021

Ocean-going platforms are integrating high-resolution camera feeds for observation and navigation... more Ocean-going platforms are integrating high-resolution camera feeds for observation and navigation, producing a deluge of visual data. The volume and rate of this data collection can rapidly outpace researchers’ abilities to process and analyze them. Recent advances in machine learning enable fast, sophisticated analysis of visual data, but have had limited success in the ocean due to lack of data set standardization, insufficient formatting, and aggregation of existing, expertly curated imagery for use by data scientists. To address this need, we have built FathomNet, a public platform that makes use of existing, expertly curated data. Initial efforts have leveraged MBARI’s Video Annotation and Reference System and annotated deep sea video database, which has more than 7M annotations, 1M frame grabs, and 5k terms in the knowledgebase, with additional contributions by National Geographic Society (NGS) and NOAA’s Office of Ocean Exploration and Research. FathomNet has over 160k locali...

IEEE Revista Iberoamericana de Tecnologias del Aprendizaje, 2015

In order to properly address the issues of today's global world, the importance of engineering st... more In order to properly address the issues of today's global world, the importance of engineering students acquiring leadership and professional skills has increased tremendously. In fact, leadership is one of the basic pillars for global economic development. By immersing oneself in an engineering organization or honor society, one learns to cultivate a teamwork mentality that will be invaluable in the future society. Global engineering organizations, such as the Institute of Electrical and Electronic Engineers, the Society of Hispanic Professional Engineers, and Tau Beta Pi Honor Society, have student chapters that offer opportunities to develop those critical leadership skills needed to become an essential asset in the problem solving required to keep the world progressing to its full potential. Throughout this paper, engineering students give the first-person accounts of how becoming a leader within their respective organizations has transformed their undergraduate degree experience. These students have gone on to establish other organizations at Florida Atlantic University that have also enhanced the educational experience of other students and illustrate the importance of emphasizing leadership skills in the Science, Technology, Engineering, Art, and Mathematics fields.

arXiv (Cornell University), Oct 15, 2020

arXiv (Cornell University), Apr 10, 2021

As climate change increases the intensity of natural disasters, society needs better tools for ad... more As climate change increases the intensity of natural disasters, society needs better tools for adaptation. Floods, for example, are the most frequent natural disaster, and better tools for flood risk communication could increase the support for floodresilient infrastructure development. Our work aims to enable more visual communication of large-scale climate impacts via visualizing the output of coastal flood models as satellite imagery. We propose the first deep learning pipeline to ensure physicalconsistency in synthetic visual satellite imagery. We advanced a state-of-the-art GAN called pix2pixHD, such that it produces imagery that is physically-consistent with the output of an expertvalidated storm surge model (NOAA SLOSH). By evaluating the imagery relative to physics-based flood maps, we find that our proposed framework outperforms baseline models in both physical-consistency and photorealism. We envision our work to be the first step towards a global visualization of how the climate challenge will shape our landscape. Continuing on this path, we show that the proposed pipeline generalizes to visualize reforestation. We also publish a dataset of over 25k labelled image-triplets to study image-to-image translation in Earth observation 1 .

Day 2 Tue, May 03, 2022

ArXiv, 2020

Proceedings of the 14th LACCEI International Multi-Conference for Engineering, Education, and Technology: “Engineering Innovations for Global Sustainability”, 2016

Marine Technology Society Journal, 2021

Scientific Reports

ArXiv, 2021

IEEE Revista Iberoamericana de Tecnologias del Aprendizaje, 2015