Jagannath Aryal

University of Melbourne | MSD · Department of Infrastructure Engineering

In this paper, the authors present a methodology to solve the weighted barycenter problem when the data is inherently fuzzy. This method, from data clustered by expert visual inspection of maps, calculates bi-dimensional fuzzy numbers from the spatial clusters, which in turn are used to obtain the weighted fuzzy barycenter of a particular area. The...

Beetle infestations have caused significant damage to the pine forest in North America. Early detection of beetle infestation in near real time is crucial, in order to take appropriate steps to control the damage. In this letter, we consider near-realtime detection of beetle infestation in North American pine forests using high temporal resolution...

The management of vegetated areas by urban planners relies on detailed and updated knowledge of their nature and distribution. Manual photo-interpretation of aerial photographs is efficient, but is time consuming. Image segmentation and object-oriented classifications provide a tool to automatically delineate and label vegetation units. Object-orie...

Thematic maps prepared from remotely sensed images require a statistical accuracy assessment. For this purpose, the κ-statistic is often used. This statistic does not distinguish between whether one unit is classified as another, or vice versa. In this paper, the Bradley-Terry (BT) model is applied for accuracy assessment. This model compares categ...

Accurate information retrieval from multi-source and multi-resolution image data constitutes a foundation for knowledge discovery. Scene image classification in the remote sensing (RS) community using aerial very high resolution (VHR) images is one of the well-researched areas, which mostly utilise deep learning (DL)—based methods thanks to their r...

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...

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....

Deep learning (DL) models combined with mobile laser scanning (MLS) datasets have demonstrated immense potential for vegetation segmentation. However, restricted performance and inconsistent behavior across datasets by generic DL models offer notable concerns. Further, to capture the characteristic distribution of vegetation points towards effectiv...

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 exp...

Classification of very high-resolution (VHR) aerial remote sensing (RS) images is a well-established research area in the remote sensing community as it provides valuable spatial information for decision-making. Existing works on VHR aerial RS image classification produce an excellent classification performance; nevertheless, they have a limited ca...

Accurate spatial information on Land use and land cover (LULC) plays a crucial role in city planning. A widely used method of obtaining accurate LULC maps is a classification of the categories, which is one of the challenging problems. Attempts have been made considering spectral (Sp), statistical (St), and index-based (Ind) features in developing...

Although mountain areas account for approximately one fifth of the terrestrial surface, there has been less research focused on fire in these areas compared to lowlands. Mountain fires have distinct behavior due to dynamic winds interacting with the terrain, which can influence the fireline intensity and propagation. For the sake of fire safety of...

Mountain fire can become more complex than fires at lower elevation due to the complex interaction of fire, topography, and weather. The Gell River Fire in Tasmania, Australia occurred in rugged terrain where there are abundant fire sensitive vegetation communities, as well as the presence of infrastructure including high-voltage transmission lines...

Background: We studied Riveaux Road Fire, which was ignited by multiple lightning strikes in January 2019 and burnt more than 637.19 km2 in southern Tasmania, Australia. Aims: We focused on fire weather, such as identification of dynamic wind and vegetation type, in a valley of the study area. Methods: We employed two methods: numerical weather mod...

Agricultural field boundary information is an essential input for precision agriculture. This paper proposes a Multi-scale Multi-task Boundary Detection Deep Learning (DL) Network (MMBDNet) based on spatial attention mechanisms to delineate agricultural fields using high-resolution optical satellite imagery. The designed DL architecture simultaneou...

With the rise of deep learning algorithms nowadays, scene image representation methods have achieved a significant performance boost, particularly in accuracy, in classification. However, the performance is still limited because the scene images are mostly complex having higher intra-class dissimilarity and inter-class similarity problems. To deal...

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....

p>Image classification is one of the prominent tasks influencing the rapid advancement in computer vision using deep learning models such as convolutional neural networks, analogously gaining remarkable attention in remote sensing scene classification. However, the systematic comparability of literature concerning well-established large-scale or ap...

p>Image classification is one of the prominent tasks influencing the rapid advancement in computer vision using deep learning models such as convolutional neural networks, analogously gaining remarkable attention in remote sensing scene classification. However, the systematic comparability of literature concerning well-established large-scale or ap...

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 informat...

Urban buildings are extracted from high-resolution Earth observation (EO) images using semantic segmentation networks like U-Net and its successors. Each re-iteration aims to improve performance by employing a denser skip connection mechanism that harnesses multi-scale features for accurate object mapping. However, denser connections increase netwo...

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 convol...

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 characterising complex rel...

Classification of very high-resolution (VHR) aerial remote sensing (RS) images is a well-established research area in the remote sensing community as it provides valuable spatial information for decision-making. Existing works on VHR aerial RS image classification produce an excellent classification performance; nevertheless, they have a limited ca...

Fire authorities have started widely using operational fire simulations for effective wildfire management. The aggregation of the simulation outputs on a massive scale creates an opportunity to apply the evolving data-driven approach to closely estimate wildfire risks even without running computationally expensive simulations. In one of our previou...

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...

Earth observation data including very high-resolution (VHR) imagery from satellites and unmanned aerial vehicles (UAVs) are the primary sources for highly accurate building footprint segmentation and extraction. However, with the increase in spatial resolution, smaller objects are prominently visible in the images, and using intelligent approaches...

Bushfires have always been an inherent phenomenon of the Australian environment. However, climate change is linked with increased bushfire frequency and severity, which may have altered the course of the post‐fire vegetation recovery process. In this study, we examined the severity of bushfires and assessed the post‐fire recovery process by using s...

Resource management is the principal factor to fully utilize the potential of Edge/Fog computing to execute real-time and critical IoT applications. Although some resource management frameworks exist, the majority are not designed based on distributed containerized components. Hence, they are not suitable for highly distributed and heterogeneous co...

Wildfires are not only a natural part of many ecosystems, but they can also have disastrous consequences for humans, including in Australia. Rugged terrain adds to the difficulty of predicting fire behavior and fire spread, as fires often propagate contrary to expectations. Even though fire models generally incorporate weather, fuels, and topograph...

Dear Colleagues, Remote sensing technology is indispensable for high level land use, land management and sustainable infrastructure design. In recent years, multi-source and multi-temporal remote sensing big data, from optical to microwave, from low to very high spatial resolution, from multispectral to hyperspectral, and LiDAR data are available...

The world faces the threat of an energy crisis that is exacerbated by the dominance of fossil energy sources that negatively impact the sustainability of the earth's ecosystem. Currently, efforts to increase the supply of renewable energy have become a global agenda, including using solar energy which is one of the rapidly developing clean energies...

Accurate vehicle classification and tracking are increasingly important subjects for intelligent transport systems (ITSs) and for planning that utilizes precise location intelligence. Deep learning (DL) and computer vision are intelligent methods; however, accurate real-time classification and tracking come with problems. We tackle three prominent...

The extent and severity of bushfires in a landscape are largely governed by meteorological conditions. An accurate understanding of the interactions of meteorological variables and fire behaviour in the landscape is very complex, yet possible. In exploring such understanding, we used 2693 high-confidence active fire points recorded by a Moderate Re...

Edge computing places cloudlets with high computational capabilities near mobile devices to reduce the latency and network congestion encountered in cloud server-based task offloading. However, large number of cloudlets needed in such an edge computing network and a tremendous increase in carbon emissions of computing networks globally envisages th...

Resource management is the principal factor to fully utilize the potential of Edge/Fog computing to execute real-time and critical IoT applications. Although some resource management frameworks exist, the majority are not designed based on distributed containerized components. Hence, they are not suitable for highly distributed and heterogeneous co...

A distinct greening trend is evident in Asia, especially on the Loess Plateau (LP) of China, which is driven by climate change and large‐scale land‐use‐related ecological projects, especially the “Grain for Green” project (GFGP). However, the specific contributions of the GFGP to vegetation greening and their variation characteristics at a large sp...

Obtaining accurate, precise and timely spatial information on the distribution and dynamics of urban green space is crucial in understanding livability of the cities and urban dwellers. Inspired from the importance of spatial information in planning urban lives, and availability of state-of-the-art remote sensing data and technologies in open acces...

The aim of the current study is to apply multivariate singular spectrum analysis (M-SSA) techniques and investigate both shallow and intermediate depth earthquake characteristics in eastern Nepal and the southern Tibetan Himalaya. Space-time-depth-magnitude (STDM) domain time-series were computed for a time window of 776 events, using a complete ca...

With the advancement in scientific understanding and computing technologies, fire practitioners have started relying on operational fire simulation tools to make better-informed decisions during wildfire emergencies. This increased use has created an opportunity to employ an emerging data-driven approach for wildfire risk esti-mation as an alternat...

Leaf biochemical traits indicating early symptoms of plant stress can be assessed using imaging spectroscopy combined with radiative transfer modelling (RTM). In this study, we assessed the potential applicability of the leaf radiative transfer model Fluspect-Cx to simulate optical properties and estimate leaf biochemical traits through inversion o...

Fire authorities have started widely using operational fire simulations for effective wildfire management. These fire simulation outputs, when aggregated on a massive scale, create an opportunity to apply the evolving data-driven approach to closely estimate wildfire risks even without running computationally expensive simulations. We explored this...

The importance of Land Cover (LC) classification is recognized by an increasing number of scholars who employ LC information in various applications (i.e., address global climate change and achieve sustainable development). However, studying the roles of balancing data, image integration, and performance of different machine learning algorithms in...

Freely available remote sensing imageries and emerging machine/deep learning techniques have shown significant promise for crop classification. However, in-situ data is crucial for classification, mapping, and regular monitoring of crops. These maps assist farmers and policy makers in better decision making on crop management, food security plannin...

Environmental models involve inherent uncertainties, the understanding of which is required for use by practitioners. One method of uncertainty quantification is global sensitivity analysis (GSA), which has been extensively used in environmental modeling. The suitability GSA methods depends on the model, implementation, and computational complexity...

Urban vegetation management has become an important issue because of rapid urban development and urban green space (UGS) is an important component of sustainable urban planning. Unless we measure and quantify tree cover, we cannot manage it sustainably. The present study aimed at exploring the urban green space of Hobart city between 2003 and 2013...

Rapid estimates of the risk from potential wildfires are necessary for operational management and mitigation efforts. Computational models can provide risk metrics, but are typically deterministic and may neglect uncertainties inherent in factors driving the fire. Modeling these uncertainties can more accurately predict risks associated with a part...

This data set collects the processed simulation data obtained by running fire simulations in the Spark tool all over the Tasmanian region under various meteorological conditions. The fire simulations are run under 500 different fire weather conditions for 68,048 fire start locations within Tasmania over Cloud infrastructure. The weather inputs cons...

Lightning strikes are pervasive, however, their distributions vary both spatially and in time, resulting in a complex pattern of lightning-ignited wildfires. Over the last decades, lightning-ignited wildfires have become an increasing threat in south-east Australia. Lightning in combination with drought conditions preceding the fire season can incr...

Availability of very high-resolution remote sensing images and advancement of deep learning methods have shifted the paradigm of image classification from pixel-based and object-based methods to deep learning-based semantic segmentation. This shift demands a structured analysis and revision of the current status on the research domain of deep learn...

In landslide susceptibility mapping or evaluating slope stability, the shear strength parameters of rocks and soils and their effectiveness are undeniable. However, they have not been studied for all-natural materials, as well as different locations. Therefore, this paper proposes a novel generalized artificial intelligence model for estimating the...

As important node cities in the Belt and Road region, Shenzhen and Bangkok are faced with similar environmental threats posed by the high‐speed social development process. Rapid urbanization leads to changes in vegetation growth and land cover types and then affects ecosystem services. In the current study, we used a time‐series normalized differen...

Urban trees provide social, economic, environmental and ecosystem services benefits that improve the liveability of cities and contribute to individual and community wellbeing. There is thus a need for effective mapping, monitoring and maintenance of urban trees. Remote sensing technologies can effectively map and monitor urban tree coverage and ch...

Gully erosion is a severe form of soil erosion that results in a wide range of environmental problems such as, dams’ sedimentation, destruction of transportation and energy transmission lines, decreasing and losing farmland productivity, and land degradation. The main objective of this study is to accurately map the areas prone to gully erosion, by...

Food security is a longstanding global issue over the last few centuries. Eradicating hunger and all forms of malnutrition by 2030 is still a key challenge. The COVID-19 pandemic has placed additional stress on food production, demand, and supply chain systems; majorly impacting cereal crop producer and importer countries. Short food supply chain b...

Computational models for natural hazards usually require a large number of input parameters that affect the model outcome in a complex manner. The sensitivity of the input parameters to the output variables can be quantified using sensitivity analysis, which provides insight into the key factors driving the model and can guide modeling optimization...

Food security is one of the burning issues in the 21st century, as a tremendous population growth over recent decades has increased demand for food production systems. However, agricultural production is constrained by the limited availability of arable land resources, whereas a significant part of these is already degraded due to overexploitation....

Walking to more distant public transport stops is commonly promoted for physical activity gain. We examined the uptake of, and reasons for, this behaviour and its correlates through a cross-sectional survey (n = 944) and independent interview study (n = 22). Quantitative analysis examined correlates of frequency of walking to more distant bus stops...

Natural hazard models, such as wildfire models, require a large number of input parameters. Consequently, the parameter estimation for such models become a high-dimensional, multi-modal and mostly non-linear problem. Sensitivity Analysis (SA) enables the selection of model parameters during calibration, helps to identify and treat uncertainties and...