On 3 April 2024, a magnitude 7.4 quake--Taiwan's strongest in 25 years--shook the country's eastern coast. Stringent building codes spared most structures, but mountainous and remote villages were devastated by landslides. When disasters affect large and inaccessible areas, responders often turn to satellite images to pinpoint affected areas and prioritise relief efforts. But mapping landslides from satellite imagery by eye can be time-intensive, said Lorenzo Nava, who is jointly based at Cambridge's Departments of Earth Sciences and Geography. "In the aftermath of a disaster, time really matters," he said.

Traditionally, neural networks have been employed to learn the mapping between finite-dimensional Euclidean spaces. However, recent research has opened up new horizons, focusing on the utilization of deep neural networks to learn operators capable of mapping infinite-dimensional function spaces. In this work, we employ two state-of-the-art neural operators, the deep operator network (DeepONet) and the Fourier neural operator (FNO) for the prediction of the nonlinear time history response of structural systems exposed to natural hazards, such as earthquakes and wind. Specifically, we propose two architectures, a self-adaptive FNO and a Fast Fourier Transform-based DeepONet (DeepFNOnet), where we employ a FNO beyond the DeepONet to learn the discrepancy between the ground truth and the solution predicted by the DeepONet. To demonstrate the efficiency and applicability of the architectures, two problems are considered. In the first, we use the proposed model to predict the seismic nonlinear dynamic response of a six-story shear building subject to stochastic ground motions. In the second problem, we employ the operators to predict the wind-induced nonlinear dynamic response of a high-rise building while explicitly accounting for the stochastic nature of the wind excitation. In both cases, the trained metamodels achieve high accuracy while being orders of magnitude faster than their corresponding high-fidelity models.

Modern spacecraft are increasingly relying on machine learning (ML). However, physical equipment in space is subject to various natural hazards, such as radiation, which may inhibit the correct operation of computing devices. Despite plenty of evidence showing the damage that naturally-induced faults can cause to ML-related hardware, we observe that the effects of radiation on ML models for space applications are not well-studied. This is a problem: without understanding how ML models are affected by these natural phenomena, it is uncertain "where to start from" to develop radiation-tolerant ML software. As ML researchers, we attempt to tackle this dilemma. By partnering up with space-industry practitioners specialized in ML, we perform a reflective analysis of the state of the art. We provide factual evidence that prior work did not thoroughly examine the impact of natural hazards on ML models meant for spacecraft. Then, through a "negative result", we show that some existing open-source technologies can hardly be used by researchers to study the effects of radiation for some applications of ML in satellites. As a constructive step forward, we perform simple experiments showcasing how to leverage current frameworks to assess the robustness of practical ML models for cloud detection against radiation-induced faults. Our evaluation reveals that not all faults are as devastating as claimed by some prior work. By publicly releasing our resources, we provide a foothold -- usable by researchers without access to spacecraft -- for spearheading development of space-tolerant ML models.

Climate change results in an increased probability of extreme weather events that put societies and businesses at risk on a global scale. Therefore, near real-time mapping of natural hazards is an emerging priority for the support of natural disaster relief, risk management, and informing governmental policy decisions. Recent methods to achieve near real-time mapping increasingly leverage deep learning (DL). However, DL-based approaches are designed for one specific task in a single geographic region based on specific frequency bands of satellite data. Therefore, DL models used to map specific natural hazards struggle with their generalization to other types of natural hazards in unseen regions. In this work, we propose a methodology to significantly improve the generalizability of DL natural hazards mappers based on pre-training on a suitable pre-task. Without access to any data from the target domain, we demonstrate this improved generalizability across four U-Net architectures for the segmentation of unseen natural hazards. Importantly, our method is invariant to geographic differences and differences in the type of frequency bands of satellite data. By leveraging characteristics of unlabeled images from the target domain that are publicly available, our approach is able to further improve the generalization behavior without fine-tuning. Thereby, our approach supports the development of foundation models for earth monitoring with the objective of directly segmenting unseen natural hazards across novel geographic regions given different sources of satellite imagery.

Combining satellite technology with machine learning may allow scientists to better track and prepare for climate-induced natural hazards, according to research presented last month at the annual meeting of the American Geophysical Union. Over the last few decades, rising global temperatures have caused many natural phenomena like hurricanes, snowstorms, floods and wildfires to grow in intensity and frequency. While humans can't prevent these disasters from occurring, the rapidly increasing number of satellites that orbit the Earth from space offers a greater opportunity to monitor their evolution, said C.K Shum, co-author of the study and a professor at the Byrd Polar Research Center and in earth sciences at The Ohio State University. He said that potentially allowing people in the area to make informed decisions could improve the effectiveness of local disaster response and management. "Predicting the future is a pretty difficult task, but by using remote sensing and machine learning, our research aims to help create a system that will be able to monitor these climate-induced hazards in a manner that enables a timely and informed disaster response," said Shum.

Abstract--Natural disasters can cause substantial negative socio-economic impacts around the world, due to mortality, relocation, rates, and reconstruction decisions. Robotics has been successfully applied to identify and rescue victims during the occurrence of a natural hazard. However, little effort has been taken to deploy solutions where an autonomous robot can save the life of a citizen by itself relocating it, without the need to wait for a rescue team composed of humans. Reinforcement learning approaches can be used to deploy such a solution, however, one of the most famous algorithms to deploy it, the Q-learning, suffers from biased results generated when performing its learning routines. In this research a solution for citizen relocation based on Partially Observable Markov Decision Processes is adopted, where the capability of the Double Q-learning in relocating citizens during a natural hazard is evaluated under a proposed hazard simulation engine based on a grid world. The performance of the solution was measured as a success rate of a citizen relocation procedure, where the results show that the technique portrays a performance above 100% for easy scenarios and near 50% for hard ones.

Disasters stemming from natural hazards are increasing in both frequency and intensity, reflecting the immediate reality of climate change and prompting a growing succession of humanitarian crises. Fortunately, new technologies can help detect and prepare for extreme weather and other hazards, as well as communicate to people and communities effectively about the necessary response. "We are all exposed to natural hazards, and this will worsen in the future," said Jürg Luterbacher, Director of Science and Innovation of the World Meteorological Organization (WMO), at a recent AI for Good online seminar. "We need to act upon them accordingly." WMO has set out, along with the International Telecommunication Union (ITU) and the United Nations Environment Programme (UNEP), to explore the potential of artificial intelligence (AI) to strengthen disaster mitigation worldwide.

Citizen scientists have helped researchers discover new types of galaxies, design drugs to fight COVID-19, and map the bird world. The term describes a range of ways that the public can meaningfully contribute to scientific and engineering research, as well as environmental monitoring. As members of the Computing Community Consortium (CCC) recently argued in a Quadrennial Paper, "Imagine All the People: Citizen Science, Artificial Intelligence, and Computational Research," non-scientists can help advance science by "providing or analyzing data at spatial and temporal resolutions or scales and speeds that otherwise would be impossible given limited staff and resources." Recently, citizen scientists' efforts have found a new purpose: helping researchers develop machine learning models, using labeled data and algorithms, to train a computer to solve a specific task. This approach was pioneered by the crowdsourced astronomy project Galaxy Zoo, which started leveraging citizen scientists in 2007.

The machine learning community has recently had increased interest in the climate and disaster damage domain due to a marked increased occurrences of natural hazards (e.g., hurricanes, forest fires, floods, earthquakes). However, not enough attention has been devoted to mitigating probable destruction from impending natural hazards. We explore this crucial space by predicting building-level damages on a before-the-fact basis that would allow state actors and non-governmental organizations to be best equipped with resource distribution to minimize or preempt losses. We introduce PreDisM that employs an ensemble of ResNets and fully connected layers over decision trees to capture image-level and meta-level information to accurately estimate weakness of man-made structures to disaster-occurrences. Our model performs well and is responsive to tuning across types of disasters and highlights the space of preemptive hazard damage modelling.

AI is providing new opportunities in a range of fields, from business to industrial design to entertainment. How might machine- and deep-learning help us create safer, more sustainable, and resilient built environments? A team of researchers from the NSF NHERI SimCenter, computational modeling and simulation center for the natural hazards engineering community-based at the University of California, Berkeley, have developed a suite of tools called BRAILS--Building Recognition using AI at Large-Scale--that can automatically identify characteristics of buildings in a city and even detect the risks that a city's structures would face in an earthquake, hurricane, or tsunami. Charles (Chaofeng) Wang, a postdoctoral researcher at the University of California, Berkeley, and the lead developer of BRAILS, says the project grew out of a need to quickly and reliably characterize the structures in a city. "We want to simulate the impact of hazards on all of the buildings in a region, but we don't have a description of the building attributes," Wang said. "For example, in the San Francisco Bay area, there are millions of buildings.