Emergency vehicles (EMVs) play a critical role in a city's response to time-critical events such as medical emergencies and fire outbreaks. The existing approaches to reduce EMV travel time employ route optimization and traffic signal pre-emption without accounting for the coupling between route these two subproblems. As a result, the planned route often becomes suboptimal. In addition, these approaches also do not focus on minimizing disruption to the overall traffic flow. To address these issues, we introduce EMVLight in this paper. This is a decentralized reinforcement learning (RL) framework for simultaneous dynamic routing and traffic signal control. EMVLight extends Dijkstra's algorithm to efficiently update the optimal route for an EMV in real-time as it travels through the traffic network. Consequently, the decentralized RL agents learn network-level cooperative traffic signal phase strategies that reduce EMV travel time and the average travel time of non-EMVs in the network. We have carried out comprehensive experiments with synthetic and real-world maps to demonstrate this benefit. Our results show that EMVLight outperforms benchmark transportation engineering techniques as well as existing RL-based traffic signal control methods.

High-resolution satellite imagery available immediately after disaster events is crucial for response planning as it facilitates broad situational awareness of critical infrastructure status such as building damage, flooding, and obstructions to access routes. Damage mapping at this scale would require hundreds of expert person-hours. However, a combination of crowdsourcing and recent advances in deep learning reduces the effort needed to just a few hours in real time. Asking volunteers to place point marks, as opposed to shapes of actual damaged areas, significantly decreases the required analysis time for response during the disaster. However, different volunteers may be inconsistent in their marking. This work presents methods for aggregating potentially inconsistent damage marks to train a neural network damage detector.

This study proposes a novel method to assess damages in the built environment using a deep learning workflow to quantify it. Thanks to an automated crawler, aerial images from before and after a natural disaster of 50 epicenters worldwide were obtained from Google Earth, generating a 10,000 aerial image database with a spatial resolution of 2 m per pixel. The study utilizes the algorithm Seg-Net to perform semantic segmentation of the built environment from the satellite images in both instances (prior and post-natural disasters). For image segmentation, Seg-Net is one of the most popular and general CNN architectures. The Seg-Net algorithm used reached an accuracy of 92% in the segmentation. After the segmentation, we compared the disparity between both cases represented as a percentage of change. Such a coefficient of change quantifies the overall damage in the built environment; such information gives an estimate of the number of affected households and perhaps the extent of housing damage.

Aerial images provide important situational awareness for responding to natural disasters such as hurricanes. They are well-suited for providing information for damage estimation and localization (DEL); i.e., characterizing the type and spatial extent of damage following a disaster. Despite recent advances in sensing and unmanned aerial systems technology, much of post-disaster aerial imagery is still taken by handheld DSLR cameras from small, manned, fixed-wing aircraft. However, these handheld cameras lack IMU information, and images are taken opportunistically post-event by operators. As such, DEL from such imagery is still a highly manual and time-consuming process. We propose an approach to both detect damage in aerial images and localize it in world coordinates. The approach is based on using structure from motion to relate image coordinates to world coordinates via a projective transformation, using class activation mapping to detect the extent of damage in an image, and applying the projective transformation to localize damage in world coordinates. We evaluate the performance of our approach on post-event data from the 2016 Louisiana floods, and find that our approach achieves a precision of 88%. Given this high precision using limited data, we argue that this approach is currently viable for fast and effective DEL from handheld aerial imagery for disaster response.

During natural disasters, aircraft and satellites are used to survey the impacted regions. Usually human experts are needed to manually label the degrees of the building damage so that proper humanitarian assistance and disaster response (HADR) can be achieved, which is labor intensive and time consuming. Expecting human labeling of major disasters over a wide area gravely slows down the HADR efforts. It is thus of crucial interest to take advantage of the cutting-edge Artificial Intelligence and Machine Learning techniques to speed up the natural infrastructure damage assessment process to achieve effective HADR. Accordingly, the paper demonstrates a systematic effort to achieve efficient building damage classification. First, two novel generative adversarial nets (GANs) are designed to augment data used to train the deep-learning-based classifier. Second, a contrastive learning based method using novel data structures is developed to achieve great performance. Third, by using information fusion, the classifier is effectively trained with very few training data samples for transfer learning. All the classifiers are small enough to be loaded in a smart phone or simple laptop for first responders. Based on the available overhead imagery dataset, results demonstrate data and computational efficiency with 10% of the collected data combined with a GAN reducing the time of computation from roughly half a day to about 1 hour with roughly similar classification performances.

The availability of high-resolution weather radar images underpins effective forecasting and decision-making. In regions beyond traditional radar coverage, generative models have emerged as an important synthetic capability, fusing more ubiquitous data sources, such as satellite imagery and numerical weather models, into accurate radar-like products. Here, we demonstrate methods to augment conventional convolutional neural networks with quantum-assisted models for generative tasks in global synthetic weather radar. We show that quantum kernels can, in principle, perform fundamentally more complex tasks than classical learning machines on the relevant underlying data. Our results establish synthetic weather radar as an effective heuristic benchmark for quantum computing capabilities and set the stage for detailed quantum advantage benchmarking on a high-impact operationally relevant problem.

In this paper, we introduce RaVAEn, a lightweight, unsupervised approach for change detection in satellite data based on Variational Auto-Encoders (VAEs) with the specific purpose of on-board deployment. Applications such as disaster management enormously benefit from the rapid availability of satellite observations. Traditionally, data analysis is performed on the ground after all data is transferred - downlinked - to a ground station. Constraint on the downlink capabilities therefore affects any downstream application. In contrast, RaVAEn pre-processes the sampled data directly on the satellite and flags changed areas to prioritise for downlink, shortening the response time. We verified the efficacy of our system on a dataset composed of time series of catastrophic events - which we plan to release alongside this publication - demonstrating that RaVAEn outperforms pixel-wise baselines. Finally we tested our approach on resource-limited hardware for assessing computational and memory limitations.

Explainable AI (XAI) is a promising means of supporting human-AI collaborations for high-stakes visual detection tasks, such as damage detection tasks from satellite imageries, as fully-automated approaches are unlikely to be perfectly safe and reliable. However, most existing XAI techniques are not informed by the understandings of task-specific needs of humans for explanations. Thus, we took a first step toward understanding what forms of XAI humans require in damage detection tasks. We conducted an online crowdsourced study to understand how people explain their own assessments, when evaluating the severity of building damage based on satellite imagery. Through the study with 60 crowdworkers, we surfaced six major strategies that humans utilize to explain their visual damage assessments. We present implications of our findings for the design of XAI methods for such visual detection contexts, and discuss opportunities for future research.

Up-to-date, granular, and reliable quality of life data is crucial for humanitarian organizations to develop targeted interventions for vulnerable communities, especially in times of crisis. One such quality of life data is access to water, sanitation and hygeine (WASH). Traditionally, data collection is done through door-to-door surveys sampled over large areas. Unfortunately, the huge costs associated with collecting these data deter more frequent and large-coverage surveys. To address this challenge, we have developed a scalable and inexpensive end-to-end WASH estimation workflow using a combination of machine learning and government census data, publicly available satellite images, and crowd-sourced geospatial information. We generate a map of WASH estimates at a granularity of 250m x 250m across the entire country of Colombia. The model was able to explain up to 65% of the variation in predicting access to water supply, sewage, and toilets. The code is made available with MIT License at https://github.com/thinkingmachines/geoai-immap-wash.

Wildfire forecasting is of paramount importance for disaster risk reduction and environmental sustainability. We approach daily fire danger prediction as a machine learning task, using historical Earth observation data from the last decade to predict next-day's fire danger. To that end, we collect, pre-process and harmonize an open-access datacube, featuring a set of covariates that jointly affect the fire occurrence and spread, such as weather conditions, satellite-derived products, topography features and variables related to human activity. We implement a variety of Deep Learning (DL) models to capture the spatial, temporal or spatio-temporal context and compare them against a Random Forest (RF) baseline. We find that either spatial or temporal context is enough to surpass the RF, while a ConvLSTM that exploits the spatio-temporal context performs best with a test Area Under the Receiver Operating Characteristic of 0.926. Our DL-based proof-of-concept provides national-scale daily fire danger maps at a much higher spatial resolution than existing operational solutions.

Humanitarian organizations must have fast and reliable data to respond to disasters. Deep learning approaches are difficult to implement in real-world disasters because it might be challenging to collect ground truth data of the damage situation (training data) soon after the event. The implementation of recent self-paced positive-unlabeled learning (PU) is demonstrated in this work by successfully applying to building damage assessment with very limited labeled data and a large amount of unlabeled data. The self-PU learning is compared with the supervised baselines and traditional PU learning using different datasets collected from the 2011 Tohoku earthquake, the 2018 Palu tsunami, and the 2018 Hurricane Michael. By utilizing only a portion of labeled damaged samples, we show how models trained with self-PU techniques may achieve comparable performance as supervised learning.

Desert locust outbreaks threaten food security in Africa and have affected the livelihoods of millions of people. Furthermore, these outbreaks could potentially become more severe and frequent as a result of climate change. Machine learning (ML) has been demonstrated as an effective approach to locust distribution modelling which may assist in early warning. However, ML requires a significant amount of labelled data to train. Most publicly available labelled data on locusts are presence-only data, where only the sightings of locusts being present at a particular location are recorded. Prior work using ML have resorted to pseudo-absence generation methods as a way to circumvent this issue and build balanced datasets for training. The most commonly used approach is to randomly sample points in a region of interest while ensuring these sampled pseudo-absence points are at least a specific distance away from any true presence points. In this paper, we compare this random sampling approach to more advanced pseudo-absence generation, such as environmental profiling and background extent limitation, for predicting desert locust breeding grounds in Africa. We find that for the algorithms we tested, namely logistic regression (LR), gradient boosting and random forests, LR performed significantly better ($p$-value $< 2.2 \times 10^{-16}$) than the more sophisticated ensemble methods, both in terms of prediction accuracy and F1 score. Although background extent limitation combined with random sampling seemed to boost performance for ensemble methods, no statistically significant differences were detected between the pseudo-absence generation methods used to train LR. In light of this, we conclude that simpler approaches such as random sampling for pseudo-absence generation and linear classifiers such as LR for modelling are sensible and effective for predicting locust breeding grounds across Africa.

Damage assessment after natural disasters is needed to distribute aid and forces to recovery from damage dealt optimally. This process involves acquiring satellite imagery for the region of interest, localization of buildings, and classification of the amount of damage caused by nature or urban factors to buildings. In case of natural disasters, this means processing many square kilometers of the area to judge whether a particular building had suffered from the damaging factors.

In this work, we develop a computational approach for an automated comparison of the same region's satellite images before and after the disaster, and classify different levels of damage in buildings. Our solution is based on Siamese neural networks with encoder-decoder architecture. We include an extensive ablation study and compare different encoders, decoders, loss functions, augmentations, and several methods to combine two images. The solution achieved one of the best results in the Computer Vision for Building Damage Assessment competition.