Infrastructure Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 1217
-
ItemNo Preview AvailableCharacterizing Topographic Influences of Bushfire Severity Using Machine Learning Models: A Case Study in a Hilly Terrain of Victoria, Australia(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2023)Topography plays a significant role in determining bushfire severity over a hilly landscape. However, complex interrelationships between topographic variables and bushfire severity are difficult to quantify using traditional statistical methods. More recently, different machine learning (ML) models are becoming popular in characterizing complex relationships between different environmental variables. Yet, few studies have specifically evaluated the suitability of ML models in predictive bushfire severity analysis. Hence, the aim of this research is twofold. First, to determine suitable ML models by assessing their performances in bushfire severity predictions using remote sensing data analytics, and second to identify and investigate topographic variables influencing bushfire severity. The results showed that random forest (RF) and gradient boosting (GB) models had their distinct advantages in predictive modeling of bushfire severity. RF model showed higher precision (86% to 100%) than GB (59% to 72%) while predicting low, moderate, and high severity classes. Whereas GB model demonstrated better recall, i.e., completeness of positive predictions (56% to 75%) than RF (49% to 61%) for those classes. Closer investigations on topographic characteristics showed a varying relationship of severity patterns across different morphological landform classes. Landforms having lower slope curvatures or with unchanging slopes were more prone to severe burning than those landforms with higher slope curvatures. Our results provide insights into how topography influences potential bushfire severity risks and recommends purpose-specific choice of ML models.
-
ItemNo Preview AvailableMulti-Scale Feature Map Aggregation and Supervised Domain Adaptation of Fully Convolutional Networks for Urban Building Footprint Extraction(MDPI, 2023-01)Automated building footprint extraction requires the Deep Learning (DL)-based semantic segmentation of high-resolution Earth observation images. Fully convolutional networks (FCNs) such as U-Net and ResUNET are widely used for such segmentation. The evolving FCNs suffer from the inadequate use of multi-scale feature maps in their backbone of convolutional neural networks (CNNs). Furthermore, the DL methods are not robust in cross-domain settings due to domain-shift problems. Two scale-robust novel networks, namely MSA-UNET and MSA-ResUNET, are developed in this study by aggregating the multi-scale feature maps in U-Net and ResUNET with partial concepts of the feature pyramid network (FPN). Furthermore, supervised domain adaptation is investigated to minimise the effects of domain-shift between the two datasets. The datasets include the benchmark WHU Building dataset and a developed dataset with 5× fewer samples, 4× lower spatial resolution and complex high-rise buildings and skyscrapers. The newly developed networks are compared to six state-of-the-art FCNs using five metrics: pixel accuracy, adjusted accuracy, F1 score, intersection over union (IoU), and the Matthews Correlation Coefficient (MCC). The proposed networks outperform the FCNs in the majority of the accuracy measures in both datasets. Compared to the larger dataset, the network trained on the smaller one shows significantly higher robustness in terms of adjusted accuracy (by 18%), F1 score (by 31%), IoU (by 27%), and MCC (by 29%) during the cross-domain validation of MSA-UNET. MSA-ResUNET shows similar improvements, concluding that the proposed networks when trained using domain adaptation increase the robustness and minimise the domain-shift between the datasets of different complexity.
-
ItemAn adaptive quadtree-based approach for efficient decision making in wildfire risk assessment(ELSEVIER SCI LTD, 2023-02-01)Rapidly identifying high-risk areas for potential wildfires is crucial for preparedness, disaster management, and operational logistics decisions. With the advancement of technologies such as Cloud computing, high-risk areas can be determined ahead of time by simulating several possible fires based on forecast conditions. However, such systems may take longer and delay decision-making. We introduce a novel approach that harnesses the benefits of quadtree-based search strategies and conditional probability to enable rapid identification of high fire-risk areas and produces an increasingly detailed risk map within a given time frame. We also present a comprehensive performance analysis of different search strategies to investigate the trade-off between risk areas coverage and time efficiency showcasing how decision-makers can modify parameters based on time requirements. Experimental results show that up to 80% of high fire-risk areas in Tasmania can be identified with the proposed approach in about 20% less time than conventional comprehensive sweep methods.
-
ItemApplying Bayesian Models to Reduce Computational Requirements of Wildfire Sensitivity Analyses(MDPI, 2023-03)Scenario analysis and improved decision-making for wildfires often require a large number of simulations to be run on state-of-the-art modeling systems, which can be both computationally expensive and time-consuming. In this paper, we propose using a Bayesian model for estimating the impacts of wildfires using observations and prior expert information. This approach allows us to benefit from rich datasets of observations and expert knowledge on fire impacts to investigate the influence of different priors to determine the best model. Additionally, we use the values predicted by the model to assess the sensitivity of each input factor, which can help identify conditions contributing to dangerous wildfires and enable fire scenario analysis in a timely manner. Our results demonstrate that using a Bayesian model can significantly reduce the resources and time required by current wildfire modeling systems by up to a factor of two while still providing a close approximation to true results.
-
ItemNo Preview AvailableRemote sensing of night-time lights and electricity consumption: A systematic literature review and meta-analysis(WILEY, 2023-04)Abstract Night‐time light (NTL) satellite imagery can provide unique insights into the energy sector. Nevertheless, there are limited studies that have systematically reviewed the literature on the relationship between electricity consumption and NTL. Therefore, this paper aims to provide a systematic review of studies that have explored this relationship. The review identified over 200 regression models estimating electricity consumption using NTL satellite images. The key finding of the review was that there was a large variability in regression performance for model prediction of electricity consumption from NTL imagery, indicating a need for further work to refine the techniques and approaches in this emerging field of remote sensing research. The level of spatial aggregation had an important influence on model performance with larger geographical areas, such as countries or states, providing better estimations.
-
ItemDeep Learning for Remote Sensing Image Scene Classification: A Review and Meta-Analysis(MDPI, 2023-10)Remote sensing image scene classification with deep learning (DL) is a rapidly growing field that has gained significant attention in the past few years. While previous review papers in this domain have been confined to 2020, an up-to-date review to show the progression of research extending into the present phase is lacking. In this review, we explore the recent articles, providing a thorough classification of approaches into three main categories: Convolutional Neural Network (CNN)-based, Vision Transformer (ViT)-based, and Generative Adversarial Network (GAN)-based architectures. Notably, within the CNN-based category, we further refine the classification based on specific methodologies and techniques employed. In addition, a novel and rigorous meta-analysis is performed to synthesize and analyze the findings from 50 peer-reviewed journal articles to provide valuable insights in this domain, surpassing the scope of existing review articles. Our meta-analysis shows that the most adopted remote sensing scene datasets are AID (41 articles) and NWPU-RESISC45 (40). A notable paradigm shift is seen towards the use of transformer-based models (6) starting from 2021. Furthermore, we critically discuss the findings from the review and meta-analysis, identifying challenges and future opportunities for improvement in this domain. Our up-to-date study serves as an invaluable resource for researchers seeking to contribute to this growing area of research.
-
ItemNo Preview AvailableEnhanced multi-level features for very high resolution remote sensing scene classification(SPRINGER LONDON LTD, 2024-05-01)Very high resolution (VHR) remote sensing (RS) scene classification is a challenging task due to the higher inter-class similarity and intra-class variability problems. Recently, the existing deep learning (DL)-based methods have shown great promise in VHR RS scene classification. However, they still provide an unstable classification performance. To address such a problem, we herein propose a DL-based novel approach using an enhanced VHR attention module (EAM), which captures the richer salient multi-scale information for a more accurate representation of the VHR RS image during classification. Experimental results on three widely used VHR RS data sets show that the proposed approach yields a competitive and stable/consistent classification performance with the least standard deviation of 0.001. Further, the highest overall accuracies on the AID, NWPU, and UCM data sets are 95.39%, 93.04%, and 98.61%, respectively. Such encouraging, consistent and improved results shown through detailed ablation and comparative study provide a solution to the remote sensing community for the land use and land cover (LULC) classification problems with more trust and confidence. The source code of this work is available at https://github.com/csitaula/EAM.
-
ItemDisaster-induced disruption of policies for informal urban settlements(Elsevier BV, 2024-07-01)The rapid growth of informal urban settlements (IUS) presents a significant challenge to cities worldwide, particularly regarding disaster vulnerability. Many of their inhabitants are also victims of disaster-induced displacements due to complete loss or government-led relocation programs. The disaster or land-use management policies do not usually tackle the associated vulnerabilities of these informal settlers. Therefore, this research investigates the use case of a disaster-prone city in Colombia, where the policies and their implications at different levels (national to local) are analysed for IUS. To do so, we study the relationship between land use and disaster management policies in the case study of Mocoa in Colombia, examining its 2017 disaster as a disruptor event. The dissection of existing policies and their effectiveness revealed a lack of community engagement in the planning process and in addressing the issues associated with the vulnerabilities of IUS. Conclusions and recommendations are proposed to target community engagement in the planning process after comparing the policies and their challenges before and after the disaster.
-
Item
-
ItemFifth-generation district heating and cooling systems: A review of recent advancements and implementation barriers(PERGAMON-ELSEVIER SCIENCE LTD, 2023-01)As global urbanisation levels continue to rise, supplying urban areas with low emissions energy becomes imperative in the fight against climate change. In areas with high demand density, district heating and cooling systems are generally a more efficient alternative compared to individual solutions, but current systems are mainly powered by fossil fuels and suffer from significant thermal losses due to high operating temperatures. Fifth-generation district heating and cooling systems (5GDHC) is a promising technology, able to address these drawbacks. 5GDHC systems operate at near ambient temperature, ensuring efficient integration of renewable energy sources and waste heat recovery potential. Their ability to provide simultaneous heating and cooling through the same pipeline and bidirectional energy flows allow for load balancing through the harvesting of demand synergies between different users. 5GDHC systems can play an important role in the energy transition but not much is known about their environmental performance over their life cycle and the novelty of the concept means that planning and design guidelines are scarcely present in the literature, hindering their development and further adoption. This study critically reviews recent advancements in the relevant literature as the 5GDHC technology transitions from research and development to the demonstration phase. Moreover, the paper addresses the design parameters and methodologies encountered in the literature for the modelling and operation of 5GDHC systems. Finally, the economic and environmental performance are discussed while presenting an overview of future developments and challenges related to full-scale deployment.