Geology topics

Susu Xu

Publications and source records attributed to Susu Xu.

5 recordsLinked to original sources

USGS2024

Near-real-time earthquake-induced fatality estimation using crowdsourced data and few-shot large-language models

When a damaging earthquake occurs, immediate information about casualties (e.g., fatalities and injuries) is critical for time-sensitive decision-making by emergency response and aid agencies in the first hours and days. Systems such as the Prompt Assessment of Global Earthquakes for Response (PAGER) by the U.S. Geological Survey (USGS) were developed to provide a forecast of such impacts within about 30 min of any significant earthquake globally. However, existing disaster-induced human loss estimation systems often rely on early casualty reports manually retrieved from global traditional media, which are labor-intensive, time-consuming, and have significant time latencies. Recent approaches use keyword matching and topic modeling to identify human casualty-relevant information from social media but tend to be error-prone when dealing with complex semantics in multi-lingual text data and parsing dynamically changing and conflicting human death and injury numbers shared by various unvetted sources in social media platforms. In this work, we introduce an end-to-end framework to significantly improve the timeliness and accuracy of global earthquake-induced human loss forecasting using multi-lingual, crowdsourced social media. Our framework integrates (i) a hierarchical casualty extraction model built upon large language models, prompt design, and few-shot learning to retrieve quantitative human loss claims from social media, (ii) a physical constraint-aware, dynamic-truth discovery model that discovers the truthful human loss from massive noisy and potentially conflicting human loss claims, and (iii) a Bayesian updating loss projection model that dynamically updates the final loss estimation using discovered truths. We test the framework in real-time on a series of global earthquake events in 2021 and 2022 and show that our framework effectively automates the retrieval of casualty information faster but with comparable accuracy to those now retrieved manually by the USGS. The code associated with this work is made available at: https://github.com/SusuXu-s-Lab/Hierarchical-Earthquake-Casualty-Information-Retrieval

International Journal of Disaster Risk Reduction↗

USGS2023

DisasterNet: Causal Bayesian networks with normalizing flows for cascading hazards

Sudden-onset hazards like earthquakes often induce cascading secondary hazards (e.g., landslides, liquefaction, debris flows, etc.) and subsequent impacts (e.g., building and infrastructure damage) that cause catastrophic human and economic losses. Rapid and accurate estimates of these hazards and impacts are critical for timely and effective post-disaster responses. Emerging remote sensing techniques provide pre- and post-event satellite images for rapid hazard estimation. However, hazards and damage often co-occur or colocate with underlying complex cascading geophysical processes, making it challenging to directly differentiate multiple hazards and impacts from satellite imagery using existing single-hazard models. We introduce DisasterNet, a novel family of causal Bayesian networks to model processes that a major hazard triggers cascading hazards and impacts and further jointly induces signal changes in remotely sensed observations. We integrate normalizing flows to effectively model the highly complex causal dependencies in this cascading process. A triplet loss is further designed to leverage prior geophysical knowledge to enhance the identifiability of our highly expressive Bayesian networks. Moreover, a novel stochastic variational inference with normalizing flows is derived to jointly approximate posteriors of multiple unobserved hazards and impacts from noisy remote sensing observations. Integrating with the USGS Prompt Assessment of Global Earthquakes for Response (PAGER) system, our framework is evaluated in recent global earthquake events. Evaluation results show that DisasterNet significantly improves multiple hazard and impact estimation compared to existing USGS products.

Conference Paper↗

USGS2023

Causality-informed Bayesian inference for rapid seismic ground failure and building damage estimation

Rapid and accurate estimates of seismic ground failure and building damage are beneficial to efficient emergency response and post-earthquake recovery. Traditional approaches, such as physical and geospatial models, have poor accuracy and resolution due to large uncertainties and the limited availability of informing geospatial layers. The introduction of remote sensing techniques has shown potential in providing supplementary information for rapid hazard estimation by analyzing earthquake-induced correlation changes between pre- and post-event satellite images. However, the changes in satellite images are the result of overlapping ground failure, building damage, and environmental noise, making it challenging to categorize and estimate different seismic hazards and impacts directly from satellite images.Here we design a novel causality-informed Bayesian network that continuously updates seismic ground failure and building damage estimates from satellite images by modeling the physical interdependencies between geospatial features, ground failure, building footprints, building damage, and satellite images. The incorporation of physical interdependencies allows an effective fusion of physical models and rich but noisy information from remote sensing observations and reduces bias and uncertainties in estimations. Our experiments show that integrating satellite images through our Bayesian network improves the accuracy of seismic ground failure and building damage estimations.

Conference Paper↗

USGS2022

Seismic multi-hazard and impact estimation via causal inference from satellite imagery

Rapid post-earthquake reconnaissance is important for emergency responses and rehabilitation by providing accurate and timely information about secondary hazards and impacts, including landslide, liquefaction, and building damage. Despite the extensive collection of geospatial data and satellite images, existing physics-based and data-driven methods suffer from low estimation performance due to the complex and event-specific causal dependencies underlying the cascading processes of earthquake-triggered hazards and impacts. Herein, we present a rapid seismic multi-hazard and impact estimation system that leverages advanced statistical causal inference and remote sensing techniques. The unique feature of this system is that it provides accurate and high-resolution estimations on a regional scale by jointly inferring multiple hazards and building damage from satellite images through modeling their causal dependencies. We evaluate our system on multiple seismic events from diverse countries around the globe. Our results corroborate that incorporating causal dependencies significantly improves large-scale estimation accuracy for multiple hazards and impacts compared to existing systems. The results also reveal quantitative causal mechanisms among earthquake-triggered multi-hazard and impact for multiple seismic events. Our system establishes a new way to extract and utilize the complex interactions of multiple hazards and impacts for effective disaster responses and advancing understanding of seismic geological processes.

Nature Communications↗

USGS2022

Integrated strategies for enhanced rapid earthquake shaking, ground failure, and impact estimation employing remotely sensed and ground truth constraints

Estimating earthquake impacts using physical or empirical models is challenging because the three components of loss estimation-shaking, exposure, and vulnerabilities-entail inherent uncertainties. Loss modeling in near-real-time adds additional uncertainties, yet expectations for actionable information with a reasonable level of confidence in the results are real. The modeling approaches described herein augment inherently uncertain prior hazard and loss models with an integrated strategy for updating these priors with ground-truth observations, thereby greatly reducing their uncertainties. Two strategies are employed. Early reports of casualties are used in a Bayesian updating fashion to constrain the possible range of fatalities and to lower the prior models' uncertainties. Additionally, remotely sensed satellite radar data, in the form of a Damage Proxy Map (or DPM), are used in a Bayesian causal graph framework combined with machine learning to optimize the mapping among the physical processes that cause shaking-based building damage, landslides, and liquefaction to prior expectation models. The casual graph framework also affords the potential for removing anthropogenetic noise contained in the imagery. Ultimately, our two-fold model updating strategy will accommodate key ground-truth observations such as fatality reports, locations of building damage, and ground failure reports to converge on actual losses more rapidly.

Conference Paper↗