Xinlei Shao

Xinlei Shao

Auto-generated profile, based on publicly available information

Xinlei Shao

Department of Socio-Cultural Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa, Chiba, 277-8563, Japan

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 November 2025 in Earth System Science Data
Verified
Journal Article
Open access
HCHongruixuan Chen
Hongruixuan Chen
JSJian Song
Jian Song
ODOlivier Dietrich
Olivier Dietrich
CBClifford Broni-Bediako
Clifford Broni-Bediako
WXWeihao Xuan
Weihao Xuan
Naoto YokoyaNaoto Yokoya
Naoto Yokoya
Disaster events occur around the world and cause significant damage to human life and property. Earth observation (EO) data enables rapid and comprehensive building damage assessment, an essential capability crucial in the aftermath of a disaster to reduce human casualties and inform disaster relief efforts. Recent research focuses on developing artificial intelligence (AI) models to accurately map unseen disaster events, mostly using optical EO data. These solutions based on optical data are limited to clear skies and daylight hours, preventing a prompt response to disasters. Integrating multimodal EO data, particularly combining optical and synthetic aperture radar (SAR) imagery, makes it possible to provide all-weather, day-and-night disaster responses. Despite this potential, the lack of suitable benchmark datasets has constrained the development of robust multimodal AI models. In this paper, we present a Building damage assessment dataset using veRy-hIGH-resoluTion optical and SAR imagery (Bright) to support AI-based all-weather disaster response. To the best of our knowledge, Bright is the first open-access, globally distributed, event-diverse multimodal dataset specifically curated to support AI-based disaster response. It covers five types of natural disasters and two types of human-made disasters across 14 regions worldwide, focusing on developing countries where external assistance is most needed. The dataset's optical and SAR images with spatial resolutions between 0.3 and 1 m provide detailed representations of individual buildings, making it ideal for precise damage assessment. We train seven advanced AI models on Bright to validate transferability and robustness. Beyond that, it also serves as a challenging benchmark for a variety of tasks in real-world disaster scenarios, including unsupervised domain adaptation, semi-supervised learning, unsupervised multimodal change detection, and unsupervised multimodal image matching. The experimental results serve as baselines to inspire future research and model development. The dataset (https://doi.org/10.5281/zenodo.14619797, Chen et al., 2025a), along with the code and pretrained models, is available at https://github.com/ChenHongruixuan/BRIGHT (last access: 7 November 2025) and will be updated as and when a new disaster data is available. Bright also serves as the official dataset for the 2025 IEEE GRSS Data Fusion Contest Track II. We hope that this effort will promote the development of AI-driven methods in support of people in disaster-affected areas.

18 December 2024 in Smart Agricultural Technology
Verified
Journal Article
Open access
FZFan Zhao
Fan Zhao
ZRZhiyan Ren
Zhiyan Ren
JWJiaqi Wang
Jiaqi Wang
QWQingyang Wu
Qingyang Wu
DXDianhan Xi
Dianhan Xi
KMKatsunori Mizuno
Katsunori Mizuno

9 September 2024 in Aquatic Conservation: Marine and Freshwater Ecosystems
Verified
Journal Article
Open access
XSXinlei Shao
Xinlei Shao
HCHongruixuan Chen
Hongruixuan Chen
KMKirsty Magson
Kirsty Magson
JWJiaqi Wang
Jiaqi Wang
JSJian Song
Jian Song
JSJun Sasaki
Jun Sasaki
Because coral reef ecosystems face threats from human activities and climate change, coral reef conservation programmes are implemented worldwide. Monitoring coral health provides references for guiding conservation activities. However, current labour‐intensive methods result in a backlog of unsorted images, highlighting the need for automated classification. Few studies have simultaneously utilized accurate labels along with updated algorithms and datasets. This study aimed to create a dataset representing common coral reef conditions and associated stressors in the Indo‐Pacific. Concurrently, it assessed existing classification algorithms and proposed a new multilabel method for automatically detecting coral reef conditions and extracting ecological information. A dataset containing over 20,000 high‐resolution coral images of different health conditions and stressors was constructed based on the field survey. Seven representative deep learning architectures were tested on this dataset, and their performance was quantitatively evaluated using the F1 metric and the match ratio. Based on this evaluation, a new method utilizing the ensemble learning approach was proposed. The proposed method accurately classified coral reef conditions as healthy, compromised, dead and rubble; it also identified corresponding stressors, including competition, disease, predation and physical issues. This method can help develop the coral image archive, guide conservation activities and provide references for decision‐making for reef managers and conservationists. The proposed ensemble learning approach outperforms others on the dataset, showing state‐of‐the‐art (SOTA) performance. Future research should improve its generalizability and accuracy to support global coral reef conservation efforts.

14 May 2025 in Estuarine, Coastal and Shelf Science
Verified
Journal Article
Open access
JCJundong Chen
Jundong Chen
PLPeiran Li
Peiran Li
JLJaeyong Lee
Jaeyong Lee
XSXinlei Shao
Xinlei Shao
FZFan Zhao
Fan Zhao
JSJUN SASAKI
JUN SASAKI

26 November 2025 in Marine Pollution Bulletin
Verified
Journal Article
Closed access
XSXinlei Shao
Xinlei Shao
HCHongruixuan Chen
Hongruixuan Chen
FZFan Zhao
Fan Zhao
KMKirsty Magson
Kirsty Magson
JCJundong Chen
Jundong Chen
JSJUN SASAKI
JUN SASAKI

8 December 2025 in Marine Pollution Bulletin
Verified
Journal Article
Open access
JWJiaqi Wang
Jiaqi Wang
XSXinlei Shao
Xinlei Shao
BMBangzhang Ma
Bangzhang Ma
FZFan Zhao
Fan Zhao
KMKirsty Magson
Kirsty Magson
KMKatsunori Mizuno
Katsunori Mizuno
Coral reef ecosystems are increasingly threatened by climate change and human activities, and conservation organizations worldwide require efficient, cost-effective tools to document habitat conditions, assess artificial reef growth, and monitor corallivore dynamics. Traditional approaches, such as transect surveys with visual inspection, often suffer from low efficiency, limited coverage, and insufficient spatial information. To address these limitations, we developed a low-cost and versatile underwater camera system with three operating modes: surface, horizontal underwater, and curved underwater. The system records continuous video through three synchronized cameras, which are processed using Structure-from-Motion (SfM) photogrammetry to generate 3D reconstructions for habitat and colony-scale monitoring. A point cloud-based semantic segmentation model (KPConv) was then applied to segment the reconstructed point clouds into 'Drupella snails', 'Compromised coral', and 'Others', thereby indicating coral conditions affected by corallivore predation. Field surveys conducted in Koh Tao, Thailand, demonstrated the feasibility of this integrated hardware-software approach. The camera system achieved higher point densities and lower costs compared to conventional methods, while remaining lightweight and cost-effective for community-based conservation. The KPConv model yielded an overall accuracy of 0.916 and a mean Intersection over Union of 0.601, enabling the identification of compromised corals and cryptic Drupella snails. Quantitative assessments based on segmented outputs further revealed coral conditions and provided early warnings of potential Drupella snails outbreaks. In summary, this novel system integrates affordable image collection hardware with 3D reconstruction and semantic segmentation, improving survey efficiency and providing spatially explicit insights for coral reef monitoring, particularly for small-scale corallivore dynamics.