Disaster Damage Assessment Research Articles

Simulation Model for Assessing High-Temperature Stress on Rice

Rice is a staple grain crop extensively cultivated in Fujian Province, China. This study examined the impact of high-temperature stress on rice yield and its components, focusing on four representative rice varieties, including early and middle rice grown in Fujian Province. Results indicate significant yield losses, with the most severe reduction of 60.8% observed during the flowering stage of early rice and over 40% during the meiosis and flowering stages of middle rice. High-temperature stress primarily affects early rice yield more at the flowering stage than at the grain-filling stage, whereas in middle rice, it is more severe at the meiosis stage than at the flowering stage. Leveraging historical climatic data spanning the past 20 years, a simulation model for high-temperature stress on rice yield was developed to assess disaster-induced yield loss rates, aiming to enhance prevention and disaster damage assessment for rice under high-temperature stress. Application of the model to four rice planting sites in Fujian Province revealed contrasting temporal changes between loss rates and meteorological yield, with middle rice experiencing more severe damage than early rice. The model’s effectiveness is validated by the strong correspondence between yield loss rate and meteorological yield across different regions, highlighting its robust simulation capabilities.

Robust change detection for remote sensing images based on temporospatial interactive attention module

Change Detection (CD) is a vital monitoring method in Earth observation, especially pertinent for land-use analysis, city management, and disaster damage assessment. However, in the era of constellation interconnection and air-sky collaboration, the changes in the Regions Of Interest (ROI) cause many false detections due to geometric perspective rotation and temporal style difference. In response to these challenges, we introduce CDNeXt, this framework elucidates a robust and efficient method for combining Siamese networks based on the pre-trained backbone with the innovative Temporospatial Interactive Attention Module (TIAM) for remote sensing imagery. The CDNeXt can be categorized into four primary components: Encoder, Interactor, Decoder, and Detector. Notably, the Interactor, powered by TIAM, queries and rebuilds spatial perspective dependencies and temporal style correlations from binary temporal features extracted by the Encoder to enlarge the difference of ROI change. Culminating the process, the Detector integrates the hierarchical features generated by the Decoder, subsequently producing a binary change mask. We have achieved new State-Of-The-Art (SOTA) performance in change detection, with our method surpassing existing techniques on four benchmark datasets: an F1 score of 82.63% on SYSU-CD, 87.14% on LEVIR-CD+, 66.71% on S2Looking, and 71.11% BANDON. To further validate the effectiveness of the TIAM, we compared it to other attention modules in both interactive and non-interactive modes. Our code is available on GitHub: https://github.com/wjj282439449/CDNeXt.

Categorization of tweets for damages: infrastructure and human damage assessment using fine-tuned BERT model.

Identification of infrastructure and human damage assessment tweets is beneficial to disaster management organizations as well as victims during a disaster. Most of the prior works focused on the detection of informative/situational tweets, and infrastructure damage, only one focused on human damage. This study presents a novel approach for detecting damage assessment tweets involving infrastructure and human damages. We investigated the potential of the Bidirectional Encoder Representations from Transformer (BERT) model to learn universal contextualized representations targeting to demonstrate its effectiveness for binary and multi-class classification of disaster damage assessment tweets. The objective is to exploit a pre-trained BERT as a transfer learning mechanism after fine-tuning important hyper-parameters on the CrisisMMD dataset containing seven disasters. The effectiveness of fine-tuned BERT is compared with five benchmarks and nine comparable models by conducting exhaustive experiments. The findings show that the fine-tuned BERT outperformed all benchmarks and comparable models and achieved state-of-the-art performance by demonstrating up to 95.12% macro-f1-score, and 88% macro-f1-score for binary and multi-class classification. Specifically, the improvement in the classification of human damage is promising.

Multi-Step Feature Fusion for Natural Disaster Damage Assessment on Satellite Images

Multi-Step Feature Fusion for Natural Disaster Damage Assessment on Satellite Images

Global Climate Change Analysis based on Shared Socioeconomic Pathway Scenarios and Disaster Damage Analysis Using Hazards-US (HAZUS)

In this study, a global temperature rise by +1.9 to 5.2 ℃ was expected at the end of the 21st century due to greenhouse gas emissions based on a report from the Intergovernmental Panel on Climate Change, and a 1.6 ℃ increase in annual average temperature in Korea over the last 109 years (1912 to 2020) was confirmed. These climate changes have increased heat waves and extreme climate indices worldwide, and natural disasters have increased in Korea due to irregular changes in heat waves and precipitation. In addition, this study on disaster damage estimation was conducted using Hazards-US-Multi-Hazard (HAZUS-MH), a disaster damage assessment platform used in the United States. HAZUS-MH was selected because it is stable and robust for various disaster scenarios as well as specific geographical and climate conditions and is reliable for disaster management and response even though it has difficulty reflecting specific domestic environments. The results showed that seismic damage reduction costs can be significantly decreased through the integration of early warning and preventive measures under the scenario of Pohang earthquake magnitude 5.4. This study provides insight into domestic climate change and disaster management and emphasizes the need for future response and model development. An effective response to climate change is expected to play an important role in ensuring national and regional safety and stability.

RescueNet: A High Resolution UAV Semantic Segmentation Dataset for Natural Disaster Damage Assessment

Recent advancements in computer vision and deep learning techniques have facilitated notable progress in scene understanding, thereby assisting rescue teams in achieving precise damage assessment. In this paper, we present RescueNet, a meticulously curated high-resolution post-disaster dataset that includes detailed classification and semantic segmentation annotations. This dataset aims to facilitate comprehensive scene understanding in the aftermath of natural disasters. RescueNet comprises post-disaster images collected after Hurricane Michael, obtained using Unmanned Aerial Vehicles (UAVs) from multiple impacted regions. The uniqueness of RescueNet lies in its provision of high-resolution post-disaster imagery, accompanied by comprehensive annotations for each image. Unlike existing datasets that offer annotations limited to specific scene elements such as buildings, RescueNet provides pixel-level annotations for all classes, including buildings, roads, pools, trees, and more. Furthermore, we evaluate the utility of the dataset by implementing state-of-the-art segmentation models on RescueNet, demonstrating its value in enhancing existing methodologies for natural disaster damage assessment.

RTAL: An edge computing method for real-time rice lodging assessment

Rice is a globally important crop that plays an important role in feeding more and more of the world's population as we cope with climate change and population growth. Rice lodging is one of the main yield-reducing factors in rice production, which also has a direct impact on rice quality and leads to harvest difficulties, so it is very important to obtain lodging data in time. Lodging assessment is a tedious task that generally requires a lot of time and labor due to the large area of land involved. This study proposes an edge computing method for rice lodging areas suitable for unmanned aerial vehicles (UAVs) without post-processing, called Real Time Rice Lodging Area Calculation Method (RTAL). The RTAL method is based on deep learning and photogrammetry, and can calculate large-scale farmland lodging areas in real time using only edge computing devices. Tested on the edge computing device Nvidia Jetson Xavier NX, when the ground resolution is 0.1 m, the fastest prediction speed can reach 14417.9 m2/s. When the operation time of a single sortie is 80 min, the predicted area can reach 10 km2. This method greatly improves the efficiency of prediction, and can provide real-time help in rice yield measurement or disaster damage assessment.

Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers.

Preliminary damage assessments (PDA) conducted in the aftermath of a disaster are a key first step in ensuring a resilient recovery. Conventional door-to-door inspection practices are time-consuming and may delay governmental resource allocation. A number of research efforts have proposed frameworks to automate PDA, typically relying on data sources from satellites, unmanned aerial vehicles, or ground vehicles, together with data processing using deep convolutional neural networks. However, before such frameworks can be adopted in practice, the accuracy and fidelity of predictions of damage level at the scale of an entire building must be comparable to human assessments. Towards this goal, we propose a PDA framework leveraging novel ultra-high-resolution aerial (UHRA) images combined with state-of-the-art transformer models to make multi-class damage predictions of entire buildings. We demonstrate that semi-supervised transformer models trained with vast amounts of unlabeled data are able to surpass the accuracy and generalization capabilities of state-of-the-art PDA frameworks. In our series of experiments, we aim to assess the impact of incorporating unlabeled data, as well as the use of different data sources and model architectures. By integrating UHRA images and semi-supervised transformer models, our results suggest that the framework can overcome the significant limitations of satellite imagery and traditional CNN models, leading to more accurate and efficient damage assessments.

Black Marble Nighttime Light Data for Disaster Damage Assessment

This research explores the utilization of the Black Marble nighttime light (NTL) product to detect and assess damage caused by hurricanes, tornadoes, and earthquakes. The study first examines average regional NTL trends before and after each disaster, demonstrating that NTL patterns for hurricanes closely align with the features of a resilience curve, unlike those for earthquakes and tornadoes. The relative NTL change ratio is computed using monthly and daily NTL data, effectively reducing variance due to daily fluctuations. Results indicate the robustness of the NTL change ratio in detecting hurricane damage, whereas its performance in earthquake and tornado assessment was inconsistent and inadequate. Furthermore, NTL demonstrates a high performance in identifying hurricane damage in well-lit areas and the potential to detect damage along tornado paths. However, a low correlation between the NTL change ratio and the degree of damage highlights the method’s limitation in quantifying damage. Overall, the study offers a promising, prompt approach for detecting damaged/undamaged areas, with specific relevance to hurricane reconnaissance, and points to avenues for further refinement and investigation.

Disaster Damage Assessment of Distribution Systems With Incomplete and Incorrect Information

Motivated by the increasing frequency and intensity of extreme weather events, this article aims to effectively assess the scope of zones damaged by natural disasters in distribution systems, which can help for rapid restoration of power supply. Multiple-branch faults and the uncertainty of monitoring information pose huge challenges to Disaster Damage Assessment (DDA). This paper proposes a multiple hypothesis based DDA method to solve this problem. In the proposed method, the novel external environment information is used by updating the objective function with Pre-disaster Prediction Matching Index (PPMI). The reasonable weighting factor of PPMI is theoretically derived. Multiple disaster scenarios are simulated and the DDA results show that the proposed method is more effective. The introduction of PPMI can help to rectify the assessment of zones in high disaster risk zones, thereby improving the overall performance of DDA. Therefore, the proposed DDA method breaks through the assessment bottleneck under limited internal monitoring information. In addition, new technology is proposed to speed up the DDA by setting an effective initial value of optimization, making DDA more efficient.

Developing a conceptual model of post-disaster damage and loss assessment program in the Iranian health sector: a qualitative study protocol

IntroductionAnnual natural and man-made disasters in Iran eventually lead to casualties and considerable financial loss. The success of a reconstruction programme depends on accurate postdisaster damage and loss assessment. Based...

CrowdNAS: A Crowd-guided Neural Architecture Searching Approach to Disaster Damage Assessment

Disaster damage assessment (DDA) has emerged as an important application in disaster response and management, which aims to assess the damage severity of an affected area by leveraging AI (e.g., deep learning) techniques to examine the imagery data posted on social media during a disaster event. In this paper, we focus on a crowd-guided neural architecture searching (NAS) problem in DDA applications. Our goal is to leverage human intelligence from crowdsourcing systems to guide the discovery of the optimal neural network architecture in the design space to achieve the desirable damage assessment performance. Our work is motivated by the limitation that the deep neural network architectures in current DDA solutions are mainly designed by AI experts, which is known to be both time-consuming and error-prone. Two critical technical challenges exist in solving our problem: i) it is challenging to design a manageable NAS space for crowd-based solutions; ii) it is non-trivial to transfer the imperfect crowd knowledge to effective decisions in identifying the optimal neural network architecture of a DDA application. To address the above challenges, we develop CrowdNAS, a crowd-guided NAS framework that develops novel techniques inspired by AI, crowdsourcing, and estimation theory to address the NAS problem. The evaluation results from two real-world DDA applications show that CrowdNAS consistently outperforms the state-of-the-art AI-only, crowd-AI, and NAS baselines by achieving the highest classification accuracy in the damage assessment while maintaining a low computational cost under various evaluation scenarios.

Residential and Non-Residential Building Damage and Loss Assessment in Georgia

This paper responds to the necessity for the creation of a unified disaster damage and loss assessment method for residential and non-residential buildings in Georgia. The objective of this study is to elaborate on an improved standardized formula for damage assessment in the residential and non-residential sector. The formula provides additional clarity to the various worldwide methodologies and frameworks presently used in the damage assessment of buildings and structures. The paper itself provides four key findings: 1) that each assessment approach and the amount of damage and loss calculated for the residential sector are based on various subjective opinions (non-systematic/standardized damage assessment approaches), derived from the best knowledge from commissions created at the municipal level; 2) a review of global methodologies and frameworks revealed a clear gap in the provision of formulas for calculating economic losses in the residential and non-residential sector; 3) the need for a comprehensive explanation of the unit cost of construction in the UNISDR methodology was identified; and 4) the necessity to collect detailed and specific data for the damage and loss calculation, alongside a requirement for frequent renewals of the integrated database (associated with the need for additional resources) – without which it often leads many countries, including Georgia, to use ineffective methodologies (e.g., HAZUS). Therefore, the study offers a new and original approach for assessing damaged buildings and provides an alternative method to fill the gap in the damage assessment of particular types of buildings and structures. Moreover, the paper proposes a building damage assessment formula that does not require specific databases to be frequently updated or integrated within the GIS system.
 Keywords: Disaster Assessment, Residential and Non-residential Sector, Disaster Resilience, Applied Approach, Damage and Loss, Georgia

Editorial for the Special Issue: “Integrated Applications of Geo-Information in Environmental Monitoring”

Geo-information technology has been playing an increasingly important role in environmental monitoring in recent decades. With the continuous improvement in the spatial resolution of remote sensing images, the diversification of sensors and the development of processing packages, applications of a variety of geo-information, in particular, multi-resolution remote sensing and geographical data, have become momentous in environmental research, including land cover change detection and modeling, land degradation assessment, geohazard mapping and disaster damage assessment, mining and restoration monitoring, etc. In addition, machine learning algorithms such as Random Forests (RF) and Convolutional Neural Networks (CNN) have improved and deepened the applications of geo-information technology in environmental monitoring and assessment. The purpose of this Special Issue is to provide a platform for communication of high-quality research in the world in the domain of comprehensive application of geo-information technology. It contains 10 high-level scientific papers on the following topics such as desertification monitoring, governance of mining areas, identification of marine dynamic targets, extraction of buildings, and so on.

Editorial on Special Issue “Geo-Information Technology and Its Applications”

Geo-information technology plays a critical role in urban planning and management, land resource quantification, natural disaster risk and damage assessment, smart city development, land cover change modeling and touristic flow management. In particular, the development of big data mining and machine learning techniques (including deep learning) in recent years has expanded the potential applications of geo-information technology and promoted innovation in approaches to mining in different fields. In this context, the International Conference on Geo-Information Technology and its Applications (ICGITA 2019) was held in Nanchang, Jiangxi, China, 11–13 October 2019, co-organized by the Key Laboratory of Digital Land and Resources, East China University of Technology, the Institute of Remote Sensing and Digital Earth (RADI) of the Chinese Academy of Sciences (CAS), which was renamed in 2017 the Aerospace Information Research Institute (AIR), CAS, and the Institute of Space and Earth Information Science of the Chinese University of Hong Kong. The outstanding papers presented at this event and some other original articles were collected and published in this Special Issue “Geo-Information Technology and Its Applications” in the International Journal of Geo-Information. This Special Issue consists of 14 high-quality and innovative articles that explore and discuss the typical applications of geo-information technology in the above-mentioned domains.

Uncertainty‐aware convolutional neural network for explainable artificial intelligence‐assisted disaster damage assessment

Accurate damage assessment is a critical step in post-disaster risk assessment, mitigation, and recovery. Current practices performed by experts and reconnaissance teams in the form of field evaluation require considerable time and resources. Recent advances in remote sensing imagery, artificial intelligence (AI), and computer vision have enhanced automated and rapid disaster damage assessment. Recent literature has shown promising progress in AI-assisted aerial damage assessment. However, accounting for the uncertainty in the outcome for improved quantification of confidence and enhanced model explainability for human decision-makers remains one of the key challenges. Overlooking uncertainty can lead to erroneous decisions, especially in highly-consequential tasks such as damage assessment. The aim of this study is to develop uncertainty-aware deep learning models for the assessment of post-disaster damage using aerial imaging. Within the framework of variational Bayesian inference, Monte Carlo dropout sampling technique is used to propagate epistemic uncertainty in model predictions. With this stochastic setting, the model produces damage prediction labels with softmax as random variables, which helps quantify confidence in the model outcome using appropriate measures of uncertainty. Two networks are implemented and trained separately on two different disaster damage datasets consisting of unmanned aerial vehicle building footage as well as satellite-captured post-disaster imagery. The first network attains 59.4% accuracy in building classification, and the second network gives an accuracy of 55.1%. Results from uncertainty analysis, model confidence quantification, and analyzing model attention zone can lead to more explainable and risk-informed automated damage assessment outcomes using AI technology.

Effectiveness of PNL technique in disaster damage assessment: evidence from selective case studies

Natural disasters often cause large scale infrastructural damage and disruption of services. In such cases, a rapid damage assessment technique might prove beneficial to assist the disaster management efforts. Percent of normal light (PNL) can be one such technique. In this study, we test the effectiveness of PNL technique in rapid damage assessment from four selected case studies, namely the 2014 cyclone Hudhud, 2015 Gorkha (Nepal) earthquake, 2016 Central Italy earthquake, and the 2018 flood in Kerala. The dataset used has been taken from the Visible Infrared Imaging Radiometer Suite–Day/Night Band (VIIRS-DNB) scan data from the Joint Polar Satellite System (JPSS-1). The change in radiance values from the VIIRS-DNB dataset enables PNL computation to map the disaster affected regions. The results depict that PNL can be a viable alternative for rapid damage assessment.

Deep Learning Assist IoT Search Engine for Disaster Damage Assessment

ABSTRACT In this paper, we address the issue of disaster damage assessments using deep learning (DL) techniques. Specifically, we propose integrating DL techniques into the Internet of Things Search Engine (IoTSE) system to carry out disaster damage assessment. Our approach is to design two scenarios, Single and Complex Event Settings, to complete performance validation using four Convolutional Neural Network (CNN) models. These two scenarios are designed with three possible network services. Our experimental results confirm that all four CNN models can learn each label during the single event setting well. Whereas, with complex event settings, the CNN models have learning difficulty because multiple events have closely related labels.

Transfer Learning for Improving Seismic Building Damage Assessment

The rapid assessment of building damage in earthquake-stricken areas is of paramount importance for emergency response. The development of remote sensing technology has aided in deriving reliable and precise building damage assessments of extensive areas following disasters. It is well documented that convolutional neural network methods have superior performance in earthquake building damage assessment compared with traditional machine learning methods. However, deep learning models require a large number of samples, and sufficient numbers of samples are usually not available in the newly earthquake-stricken areas rapidly enough. At the same time, the historical samples inevitably differ from the new earthquake-affected areas due to the discrepancy of regional building characteristics. For this purpose, this study proposes a data transfer algorithm for evaluating the impact of a single historical training sample on the model performance. Then, beneficial samples are selected to transfer knowledge from the historical data for facilitating the calibration of the new model. Four models are designed with two earthquake damage building datasets and the performance of the models is compared and evaluated. The results show that the data transfer algorithm proposed in this work improves the reliability of the building damage assessment model significantly by filtering samples from the historical data that are suitable for the new task. The performance of the model built based on the data transfer method on the test set of new earthquakes task is approximately 8% higher in overall accuracy compared with the model trained directly with the new earthquake samples when the training data for the new task is only 10% of the historical data and is operating under the objective of four classes of building damage. The proposed data transfer algorithm has effectively enhanced the precision of the seismic building damage assessment in a data-limited context. Thus, it could be applicable to the building damage assessment of new disasters.

On streaming disaster damage assessment in social sensing: A crowd-driven dynamic neural architecture searching approach

Motivated by the recent advances in Internet and communication techniques and the proliferation of online social media, social sensing has emerged as a new sensing paradigm to obtain timely observations of the physical world from “human sensors”. In this study, we focus on an emerging application in social sensing – streaming disaster damage assessment (DDA), which aims to automatically assess the damage severity of affected areas in a disaster event on the fly by leveraging the streaming imagery data about the disaster on social media. In particular, we study a dynamic optimal neural architecture searching (NAS) problem in streaming DDA applications. Our goal is to dynamically determine the optimal neural network architecture that accurately estimates the damage severity for each newly arrived image in the stream by leveraging human intelligence from the crowdsourcing systems. The present study is motivated by the observation that the neural network architectures in current DDA solutions are mainly designed by artificial intelligence (AI) experts, which often leads to non-negligible costs and errors given the dynamic nature of the streaming DDA applications and the lack of real-time annotations of the massive social media data inputs. Two critical technical challenges exist in solving our problem: (i) it is non-trivial to dynamically identify the optimal neural network architecture for each image on the fly without knowing its ground-truth label a priori; (ii) it is challenging to effectively leverage the imperfect crowd intelligence to correctly identify the optimal neural network architecture for each image. To address the above challenges, we developed CD-NAS, a dynamic crowd-AI collaborative NAS framework that carefully explores the human intelligence from crowdsourcing systems to solve the dynamic optimal NAS problem and optimize the performance of streaming DDA applications. The evaluation results from a real-world streaming DDA application show that CD-NAS consistently outperforms the state-of-the-art AI and NAS baselines by achieving the highest disaster damage assessment accuracy while maintaining the lowest computational cost.