Search

Floods are considered one of the most destructive natural hydro-meteorological disasters across the world. The present study attempts to assess flood susceptibility of the Brahmaputra floodplain of Bangladesh using Deep Boost, Deep Learning Neural Network, and Artificial Neural Network. Primarily, flood inventory maps were prepared from fieldworks and satellite image classification. Consequently, the flood locations were segregated into 70% training and 30% validation samples randomly for running the models and validating the models, respectively. The complete procedure is designed to be considered 12 flood conditioning criteria under four relevant components. The efficiency assessment of DLNN, DB, and ANN models using validation data through the area under the curve (AUC) reveals that DB demonstrates higher accuracy (AUC=.917) than DLNN (AUC =.901) and ANN (AUC=.895) approaches. Therefore, proposed susceptibility mapping approaches are efficient in assessing flood susceptibility accurately and can be implemented in other flood-affected regions.

Geohazard risk is high in Arab countries due to ineffective disaster preparedness measures, mismanagement, lack of public awareness, inadequate funding and lack of stakeholder support. One such country is Egypt, which is hit by floods every year that cost lives and bring the economy to a standstill. Moreover, not much has been done to map flood-prone areas. In this paper, flood susceptibility modelling was evaluated in the Ras Gharib region of Egypt using two effective techniques machine learning technique-MLT (Support Vector Machine (SVM)) and deep learning method-DL (Convolutional Neural Networks (CNN)). Thirteen flood related factors and flood inventory layer were prepared to construct these models. Validation was performed with 30% of the flood locations where receiver operating characteristic (ROC) curves showed that the deep learning technique (CNN) gave a prediction accuracy of 86.5% (high performance), while the MLTs (SVM) gave 71.6% (medium performance). The results show that CNN provides 17% better than SVM which indicates a powerful and accurate model in flood susceptibility mapping. Results were confirmed using the Astro Digital images shortly after the 2016 flood, in which the CNN model provides a good agreement.

Globally, the frequency, intensity, and damage rate of floods have increased extensively in the last few decades. The present study proposes a spatial-based multi-criteria approach integrating mitigation capacity to map the degree of flood risk. Flood risk is calculated considering 14 relevant factors under three risk components. Thematic layers were ranked through fuzzy membership functions, and risk components were prepared using fuzzy overlay operation. To make a comparison, first, we calculated risk with mitigation capacity and later without it. Results exhibit, without mitigation capacity around 67% of the study area is exposed to high flood risk, while after integrating mitigation capacity flood risks decreased to 62%. Moreover, validation evaluation suggests risk map integrating mitigation capacity is more accurate (82%) than the risk map without it (79%). Therefore, the developed integrated risk mapping approach is more efficient to assess flood risk, and can be implemented by policymakers in similar environments.

Assessing the extent and level of building damages is crucial to support post-earthquake rescue and relief activities. There is a large body of literature proposing novel frameworks for automating earthquake-induced building damage mapping using high-resolution remote sensing images. Yet, its deployment in real-world scenarios is largely limited to the manual interpretation of images. Although manual interpretation is costly and labor-intensive, it is preferred over automatic and semi-automatic building damage mapping frameworks such as machine learning and deep learning because of its reliability. Therefore, this review paper explores various automatic and semi-automatic building damage mapping techniques with a quest to understand the pros and cons of different methodologies to narrow the gap between research and practice. Further, the research gaps and opportunities are identified for the future development of real-world scenarios earthquake-induced building damage mapping. This review can serve as a guideline for researchers, decision-makers, and practitioners in the emergency management service domain.

Detection of hydrothermal alteration zones (HAZs) associated with porphyry copper systems using remote sensing imagery is a crucial stage for discovering high potential zone of ore mineralization. Statistical model-based clustering methods have great potential for automatic and accurate detection of hydrothermal alteration minerals using hyperspectral remote sensing imagery. In this research, the Dirichlet Process based on Stick-Breaking (DPSB) model-based clustering algorithm was implemented to hyperion remote sensing imagery to discriminate HAZs associated with the Kuh-Panj porphyry copper deposit, south, Iran. The DPSB clustering algorithm was implemented and subsequently compared with the k-means algorithm, CLARA clustering, hierarchical clustering, Gaussian finite mixture model (GFMM), Gaussian model for high-dimensional (GMHD) and spectral clustering as well as spectral angle mapping (SAM). Results derived from the DPSB model-based clustering algorithm show 88.6% accuracy in distinguishing propylitic, argillic, advanced argillic, propylitic-argillic and phyllic alteration zones. The DPSB algorithm can be broadly implemented to hyperspectral remote sensing imagery for detecting alteration zones associated with porphyry systems.

Geohazard risk is high in Arab countries due to ineffective disaster preparedness measures, mismanagement, lack of public awareness, inadequate funding and lack of stakeholder support. One such country is Egypt, which is hit by floods every year that cost lives and bring the economy to a standstill. Moreover, not much has been done to map flood-prone areas. In this paper, flood susceptibility modelling was evaluated in the Ras Gharib region of Egypt using two effective techniques machine learning technique-MLT (Support Vector Machine (SVM)) and deep learning method-DL (Convolutional Neural Networks (CNN)). Thirteen flood related factors and flood inventory layer were prepared to construct these models. Validation was performed with 30% of the flood locations where receiver operating characteristic (ROC) curves showed that the deep learning technique (CNN) gave a prediction accuracy of 86.5% (high performance), while the MLTs (SVM) gave 71.6% (medium performance). The results show that CNN provides 17% better than SVM which indicates a powerful and accurate model in flood susceptibility mapping. Results were confirmed using the Astro Digital images shortly after the 2016 flood, in which the CNN model provides a good agreement.

Drought, a natural and very complex climatic hazard, causes impacts on natural and socio-economic environments. This study aims to produce the drought vulnerability map (DVM) considering novel ensemble machine learning algorithms (MLAs) in Jharkhand, India. Forty, drought vulnerability determining factors under the categories of exposure, sensitivity, and adaptive capacity were used. Then, four machine learning and four novel ensemble approaches of particle swarm optimized (PSO) algorithms, named random forest (RF), PSO-RF, multi-layer perceptron (MLP), PSO-MLP, support vector regression (SVM), PSO-MLP, Bagging, and PSO-Bagging, were established for DVMs. The receiver operating characteristic curve (ROC), mean-absolute-error (MAE), root-mean-square-error (RMSE), precision, and K-index were utilized for judging the performance of novel ensemble MLAs. The obtained results show that the PSO-RF had the highest performance with an AUC of 0.874, followed by RF, PSO-MLP, PSO-Bagging, Bagging, MLP, PSO-SVM and SVM, respectively. Produced DVMs would be helpful for policy intervention to minimize drought vulnerability.

Dengue Fever (DF) is a common vector-borne disease with catastrophic health implications. DF prediction modelling is a challenging task, although technologies such as Geographical Information Systems (GIS) and spatial statistics have improved our understanding of dengue dynamics. In this paper, we create a robust data analysis model to (i) provide a better understanding of confirmed dengue fever cases despite missing data, (ii) obtain better insights into risk factors associated with confirmed cases, and (iii) by means of machine learning, create clusters of patients with comparable characteristics. The last was accomplished with a self-organizing feature map (SOFM) and the density-based spatial clustering of applications with noise (DBSCAN). The approaches used to classify confirmed cases were: Decision Tree, k-nearest neighbours, Random Forest, AdaBoost, Support Vector Classification (SVC), CatBoost, and Naive Bayes. The CatBoost classifier achieved the best accuracy for the analysis of confirmed cases. Spatial analysis was conducted using the ordinary least square (OLS) and geographically weighted regression (GWR) models to identify high-risk areas. SOM can group patients with similar features into clusters, then DBSCAN detects and retrieves six clusters from this data. The clustering of confirmed cases increases CatBoost’s modelling prediction accuracy and reveals complex factors that influence prediction accuracy. Because confirmed cases in each cluster have different features, CatBoost is applied to each cluster individually to improve the prediction accuracy. Variable values in each cluster are analysed to clarify the confirmed cases of a specific subset of DF incidents. Overall, OLS outperforms GWR when identifying hotspot areas. The proposed novel, data-driven and machine-learning-based strategy facilitates the understanding and identification of patterns associated with confirmed DF cases. The study's findings can be utilized to cluster historical patient

Globally, the frequency, intensity, and damage rate of floods have increased extensively in the last few decades. The present study proposes a spatial-based multi-criteria approach integrating mitigation capacity to map the degree of flood risk. Flood risk is calculated considering 14 relevant factors under three risk components. Thematic layers were ranked through fuzzy membership functions, and risk components were prepared using fuzzy overlay operation. To make a comparison, first, we calculated risk with mitigation capacity and later without it. Results exhibit, without mitigation capacity around 67% of the study area is exposed to high flood risk, while after integrating mitigation capacity flood risks decreased to 62%. Moreover, validation evaluation suggests risk map integrating mitigation capacity is more accurate (82%) than the risk map without it (79%). Therefore, the developed integrated risk mapping approach is more efficient to assess flood risk, and can be implemented by policymakers in similar environments.

Assessing the extent and level of building damages is crucial to support post-earthquake rescue and relief activities. There is a large body of literature proposing novel frameworks for automating earthquake-induced building damage mapping using high-resolution remote sensing images. Yet, its deployment in real-world scenarios is largely limited to the manual interpretation of images. Although manual interpretation is costly and labor-intensive, it is preferred over automatic and semi-automatic building damage mapping frameworks such as machine learning and deep learning because of its reliability. Therefore, this review paper explores various automatic and semi-automatic building damage mapping techniques with a quest to understand the pros and cons of different methodologies to narrow the gap between research and practice. Further, the research gaps and opportunities are identified for the future development of real-world scenarios earthquake-induced building damage mapping. This review can serve as a guideline for researchers, decision-makers, and practitioners in the emergency management service domain.

This study develops an Adaboost-GIS model for flood susceptibility mapping and evaluates its relative performance by undertaking a comparative assessment of the machine learning model with Multi-Criteria Decision Making (MCDM) and soft computing models integrated with GIS. An Analytic Hierarchy Process (AHP), Analytic Network Process (ANP), Fuzzy-AHP, Fuzzy-ANP and AdaBoost machine learning models were developed and integrated with GIS to classify the susceptibility of the study area. Out of 70 sample validation locations, Adaboost’s performance was the best with a 95.72% similarity match with very high and high susceptibility locations followed by F-ANP, ANP, F-AHP and AHP with 95.65%, 92.75%, 81.42% and 77.14% similarity matches, respectively. It also had the highest AUC (0.864). Thus, the Adaboost machine learning, Fuzzy computing and conventional MCDM models can be adopted by stakeholders for accurately assessing flood susceptibility, thereby fostering safe and resilient cities.

Detection of hydrothermal alteration zones (HAZs) associated with porphyry copper systems using remote sensing imagery is a crucial stage for discovering high potential zone of ore mineralization. Statistical model-based clustering methods have great potential for automatic and accurate detection of hydrothermal alteration minerals using hyperspectral remote sensing imagery. In this research, the Dirichlet Process based on Stick-Breaking (DPSB) model-based clustering algorithm was implemented to hyperion remote sensing imagery to discriminate HAZs associated with the Kuh-Panj porphyry copper deposit, south, Iran. The DPSB clustering algorithm was implemented and subsequently compared with the k-means algorithm, CLARA clustering, hierarchical clustering, Gaussian finite mixture model (GFMM), Gaussian model for high-dimensional (GMHD) and spectral clustering as well as spectral angle mapping (SAM). Results derived from the DPSB model-based clustering algorithm show 88.6% accuracy in distinguishing propylitic, argillic, advanced argillic, propylitic-argillic and phyllic alteration zones. The DPSB algorithm can be broadly implemented to hyperspectral remote sensing imagery for detecting alteration zones associated with porphyry systems.

Governments worldwide have rapidly deployed non-pharmaceutical interventions (NPIs) to mitigate the COVID- 19 pandemic. However, the effect of these individual NPI measures across space and time has yet to be sufficiently assessed, especially with the increase of policy fatigue and the urge for NPI relaxation in the vaccination era. Using the decay ratio in the suppression of COVID-19 infections and multi-source big data, we investigated the changing performance of different NPIs across waves from global and regional levels (in 133 countries) to national and subnational (in the United States of America [USA]) scales before the implementation of mass vaccination. The synergistic effectiveness of all NPIs for reducing COVID-19 infections declined along waves, from 95.4% in the first wave to 56.0% in the third wave recently at the global level and similarly from 83.3% to 58.7% at the USA national level, while it had fluctuating performance across waves on regional and subnational scales. Regardless of geographical scale, gathering restrictions and facial coverings played significant roles in epidemic mitigation before the vaccine rollout. Our findings have important implications for continued tailoring and implementation of NPI strategies, together with vaccination, to mitigate future COVID-19 waves, caused by new variants, and other emerging respiratory infectious diseases.

Governments worldwide have rapidly deployed non-pharmaceutical interventions (NPIs) to mitigate the COVID- 19 pandemic. However, the effect of these individual NPI measures across space and time has yet to be sufficiently assessed, especially with the increase of policy fatigue and the urge for NPI relaxation in the vaccination era. Using the decay ratio in the suppression of COVID-19 infections and multi-source big data, we investigated the changing performance of different NPIs across waves from global and regional levels (in 133 countries) to national and subnational (in the United States of America [USA]) scales before the implementation of mass vaccination. The synergistic effectiveness of all NPIs for reducing COVID-19 infections declined along waves, from 95.4% in the first wave to 56.0% in the third wave recently at the global level and similarly from 83.3% to 58.7% at the USA national level, while it had fluctuating performance across waves on regional and subnational scales. Regardless of geographical scale, gathering restrictions and facial coverings played significant roles in epidemic mitigation before the vaccine rollout. Our findings have important implications for continued tailoring and implementation of NPI strategies, together with vaccination, to mitigate future COVID-19 waves, caused by new variants, and other emerging respiratory infectious diseases.

Governments worldwide have rapidly deployed non-pharmaceutical interventions (NPIs) to mitigate the COVID- 19 pandemic. However, the effect of these individual NPI measures across space and time has yet to be sufficiently assessed, especially with the increase of policy fatigue and the urge for NPI relaxation in the vaccination era. Using the decay ratio in the suppression of COVID-19 infections and multi-source big data, we investigated the changing performance of different NPIs across waves from global and regional levels (in 133 countries) to national and subnational (in the United States of America [USA]) scales before the implementation of mass vaccination. The synergistic effectiveness of all NPIs for reducing COVID-19 infections declined along waves, from 95.4% in the first wave to 56.0% in the third wave recently at the global level and similarly from 83.3% to 58.7% at the USA national level, while it had fluctuating performance across waves on regional and subnational scales. Regardless of geographical scale, gathering restrictions and facial coverings played significant roles in epidemic mitigation before the vaccine rollout. Our findings have important implications for continued tailoring and implementation of NPI strategies, together with vaccination, to mitigate future COVID-19 waves, caused by new variants, and other emerging respiratory infectious diseases.

Most previous studies of landslide susceptibility mapping (LSM) have not contemplated spatial heterogeneity and the commonly used models for LSM are aspatial, which could reduce model performance. Therefore, aiming to evaluate the applicability of spatial algorithms to predict landslide susceptibility, the performance of geographical random forest (GRF) was evaluated, in comparison to random forest (RF) and extreme gradient boosting (XGBoost). Based on the results, GRF presented the better performance (AUC = 0.876), followed by RF (AUC = 0.748) and XGBoost (AUC = 0.745). GRF also provided the most suitable susceptibility map. While RF and XGBoost presented almost 50% of the study area as susceptible, the GRF presented more concentrated susceptibility areas spatially, with a reasonable area for moderate (15.55%), high (8.73%) and very-high (2.59%) susceptibility classes. Finally, it can be inferred that spatial assessment may improve model performance, and that spatial models have a great potential for LSM.

In this study, the multi-criteria decision-making method was used to estimate the weights of several input factors such as slope, curvature, elevation, proximity to road, road density, proximity to land use, land use density, proximity to water bodies, river density, rail density, distance from rail, groundwater variation, lithology with amplification factors, peak ground acceleration (PGA) variation, and population density. An integrated analytic hierarchy process (AHP) and a probabilistic neural network (PNN) were applied for the Earthquake vulnerability assessment (EVA). The PNN model successfully explored the relationship between variables and weights obtained from the AHP approach. Validation results indicate that 92.5% accuracy was attained by the PNN model. According to the results, 24.26%, 15.26%, and 20.58% of the area fall under very-high, high, and moderate vulnerability category, respectively. The EVA map illustrates that high to very-high impact could be observed in coastal Odisha and few districts in the Mahanadi Graven.

Most previous studies of landslide susceptibility mapping (LSM) have not contemplated spatial heterogeneity and the commonly used models for LSM are aspatial, which could reduce model performance. Therefore, aiming to evaluate the applicability of spatial algorithms to predict landslide susceptibility, the performance of geographical random forest (GRF) was evaluated, in comparison to random forest (RF) and extreme gradient boosting (XGBoost). Based on the results, GRF presented the better performance (AUC = 0.876), followed by RF (AUC = 0.748) and XGBoost (AUC = 0.745). GRF also provided the most suitable susceptibility map. While RF and XGBoost presented almost 50% of the study area as susceptible, the GRF presented more concentrated susceptibility areas spatially, with a reasonable area for moderate (15.55%), high (8.73%) and very-high (2.59%) susceptibility classes. Finally, it can be inferred that spatial assessment may improve model performance, and that spatial models have a great potential for LSM.

In this study, the multi-criteria decision-making method was used to estimate the weights of several input factors such as slope, curvature, elevation, proximity to road, road density, proximity to land use, land use density, proximity to water bodies, river density, rail density, distance from rail, groundwater variation, lithology with amplification factors, peak ground acceleration (PGA) variation, and population density. An integrated analytic hierarchy process (AHP) and a probabilistic neural network (PNN) were applied for the Earthquake vulnerability assessment (EVA). The PNN model successfully explored the relationship between variables and weights obtained from the AHP approach. Validation results indicate that 92.5% accuracy was attained by the PNN model. According to the results, 24.26%, 15.26%, and 20.58% of the area fall under very-high, high, and moderate vulnerability category, respectively. The EVA map illustrates that high to very-high impact could be observed in coastal Odisha and few districts in the Mahanadi Graven.

Western boundary current (WBC) extensions such as the East Australian Current (EAC) southern extension are warming 2-3 times faster than the global average. However, there are nuances in the spatial and temporal variability of the warming that are not well resolved in climate models. In addition, the physical drivers of ocean heat content (OHC) extremes are not well understood. Here, using a high-resolution ocean model run for multiple decades, we show nonuniform warming trends in OHC in the EAC, with strong positive trends in the southern extension region (∼368-388S) but negative OHC trends equatorward of 338S. The OHC variability in the EAC is associated with the formation of anticyclonic eddies, which is modulated by transport ∼880 km upstream (EAC mode) and the westward propagation of Rossby waves (eddy mode). Diagnosing the drivers of temperature extremes has implications for predictability both in the EAC and inWBCs more broadly, where ocean warming is already having considerable ecological impacts.

Over the last decade, the emergence and significant growth of home-sharing platforms, such as Airbnb, has coincided with rising housing unaffordability in many global cities. It is in this context that we look to empirically assess the impact of Airbnb on housing prices in Sydney—one of the least affordable cities in the world. Employing a hedonic property valuation model, our results indicate that Airbnb’s overall effect is positive. A 1% increase in Airbnb density is associated with approximately a 2% increase in property sales price. However, recognizing that Airbnb’s effect is geographically uneven and given the fragmented nature of Sydney’s housing market, we also employ a GWR to account for the spatial variation in Airbnb activity. The findings confirm that Airbnb’s influence on housing prices is varied across the city. Sydney’s northern beaches and parts of western Sydney experience a statistically significant value uplift attributable to Airbnb activity. However, traditional tourist locations focused around Sydney’s CBD and the eastern suburbs experience insignificant or negative property price impacts. The results highlight the need for policymakers to consider local Airbnb and housing market contexts when deciding the appropriate level and design of Airbnb regulation.

The study involves an object-based segmentation method to extract feature changes in tropical rainforest cover using Landsat image and airborne LiDAR (ALS). Disturbance event that are represents the changes are examined by the classification of multisensor data; that is a highly accurate ALS with different resolutions of multispectral Landsat image. Disturbance Index (DI) derived from Tasseled Cap Transformation, Normalized Difference Vegetation Index (NDVI), and the ALS height are the variables for object-based segmentation process. The classification is categorized into two classes; disturbed and non-disturbed forest cover using Nearest Neighbor (NN), Random Forest (RF) and Support Vector Machine (SVM). The overall accuracy ranging from 88% to 96% and kappa ranging from 0.79 to 0.91. Mcnemar’s test p-value (<0.05) is applied to check the classification for each method used which is RF 0.03 and SVM 0.01. The accuracy increases when the integration of ALS in Landsat image (Spectral ; and Spectral + Height ). Landsat Landsat ALS

Building objects is one of the principal features that are essential for updating the geospatial database. Extracting building features from high-resolution imagery automatically and accurately is challenging because of the existence of some obstacles in these images, such as shadows, trees, and cars. Although deep learning approaches have shown significant improvements in the results of image segmentation in recent years, most deep neural networks still cannot achieve highly accurate results with correct segmentation map when processing high-resolution remote sensing images. Therefore, we implemented a new deep neural network named Seg–Unet method, which is a composition of Segnet and Unet techniques, to exploit building objects from high-resolution aerial imagery. Results obtained 92.73% accuracy carried on the Massachusetts building dataset. The proposed technique improved the performance to 0.44%, 1.17%, and 0.14% compared with fully convolutional neural network (FCN), Segnet, and Unet methods, respectively. Results also confirmed the superiority of the proposed method in building extraction.

This paper discusses the opportunities afforded by novel population sensing technologies in the field of ‘smart’ urban management. In particular, it focuses on the application of these new sources of data in retail analysis. Our goal is to integrate data derived through novel pedestrian counting and point-of-sale systems to build a statistical model that captures the relationship between retail turnover and footfall in the UK. The point-of-sales data are provided by two UK-based food & beverage retailers. To accurately measure the pedestrian activity around retail units, we make use of the data generated by the SmartStreetSensor project: a deployment of a large network of sensors installed across 105 towns and cities in the UK that collect Wi-Fi probe requests generated by mobile devices. We propose and implement novel methods for processing these raw signals into accurate estimates of pedestrian activity without compromising participants' privacy. The resulting data is then integrated into seasonal ARIMA and dynamic regression models that can be used to predict future sales. Our results indicate that the dynamic regression model that accounts for fluctuations in footfall data outperforms seasonal ARIMA model that uses only past values and behaviours of transaction data to predict future sales. Thus, we conclude that footfall does have a strong impact on retail sales and therefore integrating footfall measures into sales forecasting can significantly improve the forecasting results. We also examine differences between the two retailers and observe a stronger correlation at the Fast Food Retailer locations compared to the correlation at Family Restaurant locations.

Over 90% of the buildup of additional heat in the Earth system over recent decades is contained in the ocean. Since 2006, new observational programs have revealed heterogeneous patterns of ocean heat content change. It is unclear how much of this heterogeneity is due to heat being added to and mixed within the ocean leading to material changes in water mass properties or is due to changes in circulation that redistribute existing water masses. Here we present a novel diagnosis of the ''material'' and ''redistributed'' contributions to regional heat content change between 2006 and 2017 that is based on a new ''minimum transformation method'' informed by both water mass transformation and optimal transportation theory. We show that material warming has large spatial coherence. The material change tends to be smaller than the redistributed change at any geographical location; however, it sums globally to the net warming of the ocean, whereas the redistributed component sums, by design, to zero. Material warming is robust over the time period of this analysis, whereas the redistributed signal only emerges from the variability in a few regions. In the North Atlantic Ocean, water mass changes indicate substantial material warming while redistribution cools the subpolar region as a result of a slowdown in the meridional overturning circulation. Warming in the Southern Ocean is explained by material warming and by anomalous southward heat transport of 118 6 50 TW through redistribution. Our results suggest that near-term projections of ocean heat content change and therefore sea level change will hinge on understanding and predicting changes in ocean redistribution.

Mapping of structures, such as discontinuities, in an exposed rock mass is fundamental for slope stability analysis. This study investigates mobile laser scanning technology to identify structural discontinuity in a complex environment where the exposed rock face is partially covered with vegetation. The conventional terrestrial laser scanning and photogrammetry based approaches for structure identification rely solely on coplanarity criteria or point normal vectors and often miss several prominent discontinuity planes in a complex environment with inherent noise. To enhance structural mapping in such environments, this study tests a mobile scanner which has multi-view data collection to reduce blind spots. A new automated and robust algorithm termed clustering on local point descriptors (CLPD) is developed for more accurate discontinuity identification. The algorithm involves a rigorous pre-processing step to remove erroneous and irrelevant points followed by computation of local point descriptors. Five descriptors (i.e. eigenvalue descriptor (EVD), radial surface descriptor (RSD), fast point feature histogram (FPFH), normal and curvature) were generated for each point to capture spatial distribution, geometrical relationships and local surface variations in the point cloud. Finally, a K-Medoids clustering was performed on the computed descriptors using a histogram of normals to identify discontinuity planes. Results indicate that the proposed CLPD algorithm outperforms existing approaches in terms of accuracy in discontinuity orientation estimate (3.50° in dip angle and 4.32° in dip direction) for the study site. The stereonet comparison also validated that the poles distribution from CLPD is on par with the ground truth as well as results from commercially available software. The study presents a comparative evaluation of various approaches for kinematic feasibility of planar, wedge and sliding failures.

Roof bolts are commonly used to provide structural support in underground mines. Frequent and automated assessment of roof bolt is critical to closely monitor any change in the roof conditions while preventing major hazards such as roof fall. However, due to challenging conditions at mine sites such as sub-optimal lighting and restrictive access, it is difficult to routinely assess roof bolts by visual inspection or traditional surveying. To overcome these challenges, this study presents an automated method of roof bolt identification from 3D point cloud data, to assist in spatio-temporal monitoring efforts at mine sites. An artificial neural network was used to classify roof bolts and extract them from 3D point cloud using local point descriptors such as the proportion of variance (POV) over multiple scales, radial surface descriptor (RSD) over multiple scales and fast point feature histogram (FPFH). Accuracy was evaluated in terms ofprecision, recall and quality metric generally used in classification studies. The generated results were compared against other machine learning algorithms such as weighted k-nearest neighbours (k-NN), ensemble subspace k-NN, support vector machine (SVM) and random forest (RF), and was found to be superior by up to 8% in terms of the achieved quality metric.

In 2017, the new generation satellite-based augmentation system (SBAS) test-bed was initiated by Australia and New Zealand, which supports the dual-frequency multi-constellation (DFMC) positioning with both GPS and Galileo signals. This new SBAS DFMC service allows the elimination of the first-order term of the ionospheric delays, and extends the service area to the entire footprint of the geostationary satellite. In addition to the satellite clock and orbital corrections, the integrity information is also broadcast by the SBAS satellite to users, so that protection levels can be computed to bound the positioning errors with a pre-defined probability of hazardous misleading information. Different from the aeronautical applications, the ground-based applications for road transport may suffer from new problems in different measurement environments, e.g. complicated multipath behaviours and frequent filter re-initialisations during positioning in urban areas. A new weighting model allowing different impacts of the elevation angles, the signal-to-noise-ratios and the smoothing time after re-initialisations is proposed and compared with the traditional elevation-dependent weighting model. The model is applied to the carrier-smoothed code measurements in different environments, i.e., the open-sky scenario, the suburban scenario and the urban scenario. It is found that the new weighting model effectively de-weights the large residuals in the suburban and the urban scenarios, where the mean values and the standard deviations of the overbounding excess-mass cumulative density function can be significantly reduced for the combined weighted noise and multipath. Using 1 Hz GNSS observations measured in these three measurement environments, the horizontal positioning errors (HPEs) and the horizontal protection levels (HPLs) are computed for different filter smoothing windows. Applying the new weighting model, significant reduction can be observed in the mean HPLs in the suburban

Merging of multiple satellite datasets is a simple yeteffective way to reduce prediction error. However, most mergingmethods for satellite data today are based on weighted averagingfirst proposed in 1969 for economic forecasting, which does notprovide optimal outcomes when applied to satellite data. If our aimis to produce a merged data product that minimizes the predictionerrors against a prediction target, there is no reason to insist thatthe merged product be an average of the parent datasets. A moredisciplined approach based on mathematical optimization wouldbe to minimize prediction errors. However, formulating mergingas an optimization problem is insufficient by itself as the statisticsneeded for optimization, e.g. signal-to-noise ratio (SNR) of parentproducts, are often unavailable in practice and must be estimatedjointly. In this paper, we address both of these problems for datamerging. We first formulate optimal merging of satellite data as aSNR optimization (SNR-opt), and propose an estimation methodto jointly estimate the required SNRs. This SNR-based approachhas a natural interpretation as a multi-input single-output Wienerfilter. Through extensive experimental validation on three globalscalesatellite-derived soil moisture and land surface temperatureproducts, we demonstrate that our SNR optimization significantlyimproves merging over the existing weighted averaging scheme.