Bo Peng, Ph.D.

About

Dr. Bo Peng is a Senior Research Scientist with PAII, the U.S. research lab of Ping An Technology. Previously, he was with X, the Moonshot Factory (formerly Google[x]) as an AI resident and with Los Alamos National Lab (LANL) as an Applied Machine Learning Research Fellow.

His research aims at developing scalable and generalizable machine learning and computer vision models to approach key challenges in remote sensing for global-scale real-time natural disaster response. He has received funding from NSF, Microsoft AI for Earth, American Society for Photogrammetry and Remote Sensing (ASPRS) to support his research for tackling real-world challenges including multimodal satellite data fusion, cloud removal, un-/self-/weakly-supervised learning with label scarcity, change detection, disaster damage mapping, etc.

He received Ph.D. in Geography (Remote Sensing) with a Ph.D. Minor in Electrical Engineering (Machine Learning) at Spatial Computing and Data Mining Lab, University of Wisconsin - Madison (UW-Madison), working with Dr. Qunying Huang, the M.Sc. from Department of Electrical & Computer Engineering at UW-Madison, the M.Sc. from Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, and the B.E. from School of Remote Sensing and Information Engineering, Wuhan University.

News

• [06/2022] Double champions in the CVPR 2022 MultiEarth Challenges: Matrix Completion and Image Translation.
• [12/2021] Joined PAII Inc., the U.S. research lab of Ping An Technology, as a Senior Research Scientist, working on computer vision and Remote Sensing.
• [12/2021] Awarded Ph.D. from UW-Madison. Congrats, Dr. Peng!
• [08/2021] Joined X, the Moonshot Factory (formerly Google[x]) as an AI resident.

Selected Publications

Research topics span remote sensing, computer vision, and natural hazards.

• MultiEarth 2022 - The Champion Solution for the Matrix Completion Challenge via Multimodal Regression and Generation

  Bo Peng, Hongchen Liu, Hang Zhou, Yuchuan Gou, Jui-Hsin Lai
  CVPR Workshop on Multimodal Learning for Earth and Environment, 2022
• MultiEarth 2022 - The Champion Solution for Image-to-Image Translation Challenge via Generation Models

  Yuchuan Gou, Bo Peng, Hongchen Liu, Hang Zhou, Jui-Hsin Lai
  CVPR Workshop on Multimodal Learning for Earth and Environment, 2022
• Flood Depth Assessment with Location-based Social Network Data and Google Street View - A Case Study with Buildings as Reference Objects

  Boyuan Zou, Bo Peng, Qunying Huang
  IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2022
• Real-Time Classification of Disaster Images from Social Media with a Self-supervised Learning Framework

  Tianhui Cai, Hongyu Gan, Bo Peng, Qunying Huang, Zhiqiang Zou
  IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2022
• Spatiotemporal Contrastive Representation Learning for Building Damage Classification

  Bo Peng, Qunying Huang*, Jinmeng Rao
  IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2021
• Urban Flood Mapping With Bitemporal Multispectral Imagery Via a Self-Supervised Learning Framework

  Bo Peng, Qunying Huang, Jamp Vongkusolkit, Song Gao, Daniel B. Wright, Zheng N. Fang, Yi Qiang
  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (J-STARS), 2021
• Patch Similarity Convolutional Neural Network for Urban Flood Extent Mapping Using Bi-Temporal Satellite Multispectral Imagery

  Bo Peng, Zonglin Meng, Qunying Huang, Caixia Wang
  Remote Sensing, 2019
• Urban Flood Mapping with Residual Patch Similarity Learning

  Bo Peng, Xinyi Liu, Zonglin Meng, Qunying Huang
  3rd ACM SIGSPATIAL Workshop on AI for Geographic Knowledge Discovery (GeoAI), 2019
• Fast Real-Time Causal Line-wise Progressive Hyperspectral Anomaly Detection via Cholesky Decomposition

  Lifu Zhang, Bo Peng, Feizhou Zhang, Lizhe Wang, Hongming Zhang, Peng Zhang, Qingxi Tong
  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (J-STARS), 2017
• Fast Real-time Target Detection via Target-oriented Band Selection

  Bo Peng, Lifu Zhang, Taixia Wu, Hongming Zhang
  IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016

Awards

• Microsoft AI for Earth Grant, 2020-2022
• Olmstead Award for Outstanding Publication, UW-Madison Geography Dept., 2021
• Applied Machine Learning Research Fellowship, Los Alamos National Laboratory (LANL), 2020
• Fischer Scholarship, American Society for Photogrammetry and Remote Sensing (ASPRS), 2020
• NSF Travel Award, 2019

Services

• GeoAI’22 (The 5th International ACM SIGSPATIAL Workshop on AI for Geographic Knowledge Discovery)
• European Conference on Computer Vision (ECCV) 2022
• The IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022
• IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (2020-2022)

• International Journal of Applied Earth Observation and Geoinformation
• IEEE Geoscience and Remote Sensing Letters (GRSL)
• Journal of Hydrology
• Natural Hazards
• International Journal of Digital Earth (IJDE)
• Environmental Modelling and Software
• Automation in Construction

• IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (2021)
• AAG Geospatial Artificial Intelligence for Natural Hazards (2022)
• AAG Remote Sensing Specialty Group Student Illustrated Paper Competition (2022)

Misc