Earth observation and Machine learning for Disaster response.
Accurate and rapid understanding of the full-scale damage after a disaster is fundamental for efficient response and relief post-disaster actions. However, affected areas are often inaccessible after a disaster occurs. In such scenarios, earth observation technologies allow us to observe places inaccessible to humans. Yet, the enormous diversity of remote sensing platforms and modalities makes their analysis difficult. So, we focus on developing intelligent remote sensing image analysis methods based on machine learning and computer vision techniques to automatically extract land information following disasters, such as earthquakes, tsunamis, and landslides.
Assessing Disasters using Numerical Simulation and Machine learning.
Large-scale disasters like tsunamis and floods present unique characteristics in different urban environments. As such, computer simulations enable us to study complex aspects and mechanisms of disasters. Further, the combined applications of machine learning algorithms and computer simulation allows us to expand the limits of standard numerical modeling. So, we focus on developing integrated technologies to rapidly estimate disaster's physics-based features, such as inundation depth and ground deformation. Mainly, we focus on developing real-time disaster modeling methods to support the emergency response capabilities of regions with limited computational resources.
Adriano, B., Yokoya, N., Yamanoi, K., Oishi, S. (2022). Predicting Flood Inundation Depth Based on Machine Learning and Numerical Simulation, In Proceedings of the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJCAI-ECAI), Vienna, Austria, 3207, 58-64.
Adriano, B., Yokoya, N., Miura, H.,Liu, W., Matsuoka M., Koshimura, K. (2021), Learning from multimodal and multitemporal earth observation data for building damage mapping, ISPRS Journal of Photogrammetry and Remote Sensing, 175, 132-143. https://doi.org/10.1016/j.isprsjprs.2021.02.016
Adriano, B., Yokoya, N., Miura, H., Matsuoka, M., and Koshimura, S. (2020), A Semi-automatic Pixel-Object Method for Detecting Landslides Using Multitemporal ALOS-2 Intensity Images, Remote Sensing, 12(13), 561. https://doi.org/10.3390/rs12030561
Adriano, B., Xia, J., Baier, G., Yokoya, N., and Koshimura, S. (2019), Multi-Source Data Fusion Based on Ensemble Learning for Rapid Building Damage Mapping during the 2018 Sulawesi Earthquake and Tsunami in Palu, Indonesia, Remote Sensing, 11(7), 886. https://doi.org/10.3390/rs11070886
Adriano, B., Fujii, Y., Koshimura, K., Mas, E., Ruiz-Angulo, A., Estrada, M. (2017), Tsunami Source Inversion Using Tide Gauge and DART Tsunami Waveforms of the 2017 Mw8.2 Mexico Earthquake, Pure and Applied Geophysics, 175, 35-48. https://doi.org/10.1007/s00024-017-1760-2
Visiting Researcher, Interdisciplinary Graduate School of Science and Technology, Tokyo Institute of Technology.
- Editorial Board Member, Environmental Remote Sensing Section, Remote Sensing
- Associate Editor, Coastal Engineering Journal
- Guest Editor, IEEE Journal on Selected Topics in Applied Earth Observations and Remote Sensing
- IEEE Transactions on Geoscience and Remote Sensing
- IEEE Journal of Selected Topics on Applied Remote Sensing
- IEEE Geoscience and Remote Sensing Letters
- Remote Sensing
- Remote Sensing of Environment
- ISPRS Journal of Photogrammetry and Remote Sensing