Evan Sheehan

Goddard Space Flight Center

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Burak Uzkent

Amazon (United States)

Stefano Ermon

Stanford University

Marshall Burke

Stanford University

David B. Lobell

Stanford University

Chenlin Meng

Stanford University

Irene Shivaei

Centro de Astrobiología

Bryan J. Holler

Space Telescope Science Institute

Katherine T. Murray

Vanderbilt University

A. Coulais

Laboratoire d’Etudes du Rayonnement et de la Matière en Astrophysique et Atmosphères

Timothy Grundy

Rutherford Appleton Laboratory

Cooperative Institutions

Space Telescope Science Institute

418

Goddard Space Flight Center

145

Johns Hopkins University

Michigan Science Center

University of Arizona

Max Planck Institute for Astronomy

Northrop Grumman (United States)

Max Planck Society

California Institute of Technology

Centre National de la Recherche Scientifique

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Learning to Interpret Satellite Images Using Wikipedia

arXiv (Cornell University) (2018)

Evan Sheehan Burak Uzkent Chenlin Meng Zhongyi Tang Marshall Burke

Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we propose using Wikipedia as a previously untapped source of rich, georeferenced textual information with global coverage. We construct a novel large-scale, multi-modal dataset by pairing geo-referenced Wikipedia articles with satellite imagery of their corresponding locations. To prove the efficacy of this dataset, we focus on the African continent and train a deep network to classify images based on labels extracted from articles. We then fine-tune the model on a human annotated dataset and demonstrate that this weak form of supervision can drastically reduce the quantity of human annotated labels and time required for downstream tasks.

Georeference

Source

Cite

Citations (8)

Predicting Economic Development using Geolocated Wikipedia Articles

Evan Sheehan Chenlin Meng Matthew Tan Burak Uzkent Neal Jean

Progress on the UN Sustainable Development Goals (SDGs) is hampered by a persistent lack of data regarding key social, environmental, and economic indicators, particularly in developing countries. For example, data on poverty - the first of seventeen SDGs - is both spatially sparse and infrequently collected in Sub-Saharan Africa due to the high cost of surveys. Here we propose a novel method for estimating socioeconomic indicators using open-source, geolocated textual information from Wikipedia articles. We demonstrate that modern NLP techniques can be used to predict community-level asset wealth and education outcomes using nearby geolocated Wikipedia articles. When paired with nightlights satellite imagery, our method outperforms all previously published benchmarks for this prediction task, indicating the potential of Wikipedia to inform both research in the social sciences and future policy decisions.

Encyclopedia

Socioeconomic development

10.1145/3292500.3330784

Cite

Citations (65)

has2k1/plotnine: v0.4.0

Hassan Kibirige Greg Lamp Jan Katins O Austin gdowding

10.5281/zenodo.1325309

Cite

Citations (2)

The Science Performance of JWST as Characterized in Commissioning

Publications of the Astronomical Society of the Pacific (2023)

Jane R. Rigby Marshall D. Perrin Michael W. McElwain Randy A. Kimble S. D. Friedman

Abstract This paper characterizes the actual science performance of the James Webb Space Telescope (JWST), as determined from the six month commissioning period. We summarize the performance of the spacecraft, telescope, science instruments, and ground system, with an emphasis on differences from pre-launch expectations. Commissioning has made clear that JWST is fully capable of achieving the discoveries for which it was built. Moreover, almost across the board, the science performance of JWST is better than expected; in most cases, JWST will go deeper faster than expected. The telescope and instrument suite have demonstrated the sensitivity, stability, image quality, and spectral range that are necessary to transform our understanding of the cosmos through observations spanning from near-earth asteroids to the most distant galaxies.

10.1088/1538-3873/acb293

Cite

Citations (229)

Brainstorm, Chainstorm, Cheatstorm, Tweetstorm

Haakon Faste Nir Rachmel Russell Essary Evan Sheehan

In this paper we describe the results of a design-driven study of collaborative ideation. Based on preliminary findings that identified a novel digital ideation paradigm we refer to as chainstorming, or online communication brainstorming, two exploratory studies were performed. First, we developed and tested a distributed method of ideation we call cheatstorming, in which previously generated brainstorm ideas are delivered to targeted local contexts in response to a prompt. We then performed a more rigorous case study to examine the cheatstorming method and consider its possible implementation in the context of a distributed online ideation tool. Based on observations from these studies, we conclude with the somewhat provocative suggestion that ideation need not require the generation of new ideas. Rather, we present a model of ideation suggesting that its value has less to do with the generation of novel ideas than the cultural influence exerted by unconventional ideas on the ideating team. Thus brainstorming is more than the pooling of "invented" ideas, it involves the sharing and interpretation of concepts in unintended and (ideally) unanticipated ways.

Brainstorming

Ideation

Pooling

Exploratory research

10.1145/2470654.2466177

Cite

Citations (33)

Efficient Conditional Pre-training for Transfer Learning

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2022)

Shuvam Chakraborty Burak Uzkent Kumar Ayush Kumar Tanmay Evan Sheehan

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and improves convergence rate and generalization on the target task. Although pre-training on large-scale datasets is very useful for new methods or models, its foremost disadvantage is high training cost. To address this, we propose efficient filtering methods to select relevant subsets from the pre-training dataset. Additionally, we discover that lowering image resolutions in the pre-training step offers a great trade-off between cost and performance. We validate our techniques by pre-training on ImageNet in both the unsupervised and supervised settings and finetuning on a diverse collection of target datasets and tasks. Our proposed methods drastically reduce pre-training cost and provide strong performance boosts. Finally, we improve the current standard of ImageNet pre-training by 1-3% by tuning available models on our subsets and pre-training on a dataset filtered from a larger scale dataset.

Training set

Transfer of learning

Deep Neural Networks

10.1109/cvprw56347.2022.00469

Cite

Citations (10)

Predicting Economic Development using Geolocated Wikipedia Articles

arXiv (Cornell University) (2019)

Evan Sheehan Chenlin Meng Matthew Tan Burak Uzkent Neal Jean

Progress on the UN Sustainable Development Goals (SDGs) is hampered by a persistent lack of data regarding key social, environmental, and economic indicators, particularly in developing countries. For example, data on poverty --- the first of seventeen SDGs --- is both spatially sparse and infrequently collected in Sub-Saharan Africa due to the high cost of surveys. Here we propose a novel method for estimating socioeconomic indicators using open-source, geolocated textual information from Wikipedia articles. We demonstrate that modern NLP techniques can be used to predict community-level asset wealth and education outcomes using nearby geolocated Wikipedia articles. When paired with nightlights satellite imagery, our method outperforms all previously published benchmarks for this prediction task, indicating the potential of Wikipedia to inform both research in the social sciences and future policy decisions.

Encyclopedia

Socioeconomic development

10.48550/arxiv.1905.01627

Cite

Citations (0)

ACE: Age Calculation Engine-A Design Environment for Cosmogenic Dating Techniques

Kenneth E. Anderson Elizabeth H. Bradley Marek Zreda Laura Rassbach Chris Zweck

ACE (age calculation engine; previously called iCronus) is a design environment for analyzing data used in cosmogenic dating methods. It is supported by a software architecture designed with flexibility, scalability, security and safety in mind. These properties have allowed us to create an environment that directly supports the tasks that geoscientists perform as they work on developing new algorithms for cosmogenic dating, such as running calibrations, defining new experiments, and evaluating the impacts of scaling factors on the calculated ages of samples. Our goal is to provide geoscientists using cosmogenic dating methods with a flexible and powerful software infrastructure upon which to base their future research efforts. In this paper, we describe the design of the ACE system and compare it to existing cosmogenic dating software. We also discuss how our system has been evaluated and our plans for future work.

10.1109/advcomp.2007.4401896

Cite

Citations (0)

Predicting Economic Development using Geolocated Wikipedia Articles

arXiv (Cornell University) (2019)

Evan Sheehan Chenlin Meng Matthew Tan Burak Uzkent Neal Jean

Progress on the UN Sustainable Development Goals (SDGs) is hampered by a persistent lack of data regarding key social, environmental, and economic indicators, particularly in developing countries. For example, data on poverty --- the first of seventeen SDGs --- is both spatially sparse and infrequently collected in Sub-Saharan Africa due to the high cost of surveys. Here we propose a novel method for estimating socioeconomic indicators using open-source, geolocated textual information from Wikipedia articles. We demonstrate that modern NLP techniques can be used to predict community-level asset wealth and education outcomes using nearby geolocated Wikipedia articles. When paired with nightlights satellite imagery, our method outperforms all previously published benchmarks for this prediction task, indicating the potential of Wikipedia to inform both research in the social sciences and future policy decisions.

Encyclopedia

Socioeconomic development

Source

Cite

Citations (18)

Learning to Interpret Satellite Images Using Wikipedia

arXiv (Cornell University) (2018)

Evan Sheehan Burak Uzkent Chenlin Meng Zhongyi Tang Marshall Burke

Georeference

10.48550/arxiv.1809.10236

Cite

Citations (0)