Browsing by Author "Hassan, Quazi"
Now showing 1 - 16 of 16
Results Per Page
Sort Options
Item Open Access 3D Reconstruction of Building Interiors Using Point Clouds(2018-04-24) Xie, Lei; Wang, Ruisheng; Shahbazi, Mozhdeh; Hassan, QuaziThe automatic modeling of as-built building interiors, known as indoor building reconstruction, is gaining increasing attention because of its widespread applications. With the development of sensors to acquire high-quality point clouds, a new modeling scheme called scan-to-BIM (building information modeling) emerged. However, the traditional scan-to-BIM process is time tedious and labor intensive. Most existing automatic indoor building reconstruction solutions can only fit the specific data or lack of detailed model representation. In this thesis, we propose two automatic reconstruction methods from 2D linear primitives and 3D planar primitives respectively, to create 2D floor plans and 3D building models. The approach using 2D primitives is well suited for large-scale point clouds through a decomposition-and-reconstruction strategy. Moreover, it can retrieve semantic information of rooms and doors simultaneously. Another method using 3D primitives can deal with different types of point clouds and retain as much as structural details with respect to protruding structures, complicated ceilings, and fine corners. The experimental results indicate the effectiveness of proposed methods and the robustness against noises and downsampling.Item Open Access Automated Recognition of Electrical Substation Components from 3D LiDAR Point Clouds(2017) Arastounia, Mostafa; Lichti, Derek; Hassan, Quazi; Wang, RuishengThis study presents an innovative automated methodology for identification of electrical substations’ key elements from 3D LiDAR point clouds acquired by terrestrial laser scanners. The developed methodology is composed of nine algorithms that identify objects of interest with respect to their physical shape and topological relationships among them. The objects of interest in this contribution are ground, fence, cables, circuit breakers, bushings, bus pipes, insulators, and three types of poles with circular, octagonal, and square cross sectional shape. The developed methodology incorporates a computationally-efficient algorithm for detection of ground within electrical substations; two separate algorithms for identifying well-sampled and poorly-sampled fences; robust algorithms for detecting cables, circuit breakers, and bushings with respect to their unique physical shape and the topological relationships among them; and a novel method for simultaneous identification, modeling, and registration-refinement of poles with circular and regular polygonal cross sectional shapes. The proposed methods in this study work quite robustly despite the challenges introduced by non-uniform point sampling, registration error, occlusion, attached objects, gap, dense configuration of neighboring objects, and outliers. Five datasets with quite different volume and configuration were employed in this work. The first three datasets contain point clouds of two different electrical substations. The fourth and fifth datasets contain point clouds of an urban roadway and a pole-like monument with a regular dodecagonal cross section, respectively. The obtained results indicate that 367 out of 382 objects of interest (96.1%) in the first dataset; 354 out of 382 objects of interest (92.7%) in the second dataset; and 255 out of 264 objects of interest (96.6%) in the third dataset were successfully recognized. At point cloud level, it achieved greater than 99%, 96%, and 97% average recognition precision and accuracy in the first, second, and third dataset, respectively. Furthermore, the poles in the fourth and fifth datasets were successfully identified and the registration-refined version and as-built model of poles in all five datasets were automatically generated. The center and size standard deviation of the constructed models was less than 3 mm and the rotation angle standard deviation was less than 0.3° for all identified poles.Item Open Access Development of a New Daily-Scale Forest Fire Danger Forecasting System Using Remote Sensing Data(MDPI, 2015-03-02) Chowdhury, Ehsan; Hassan, QuaziForest fires are a critical natural disturbance in most of the forested ecosystems around the globe, including the Canadian boreal forest where fires are recurrent. Here, our goal was to develop a new daily-scale forest fire danger forecasting system (FFDFS) using remote sensing data and implement it over the northern part of Canadian province of Alberta during 2009–2011 fire seasons. The daily-scale FFDFS was comprised of Moderate Resolution Imaging Spectroradiometer (MODIS)-derived four-input variables, i.e., 8-day composite of surface temperature (TS), normalized difference vegetation index (NDVI), and normalized multiband drought index (NMDI); and daily precipitable water (PW). The TS, NMDI, and NDVI variables were calculated during i period and PW during j day and then integrated to forecast fire danger conditions in five categories (i.e., extremely high, very high, high, moderate, and low) during j + 1 day. Our findings revealed that overall 95.51% of the fires fell under “extremely high” to “moderate” danger classes. Therefore, FFDFS has potential to supplement operational meteorological-based forecasting systems in between the observed meteorological stations and remote parts of the landscape.Item Open Access Development of a Remote Sensing-Based Agriculture Monitoring Drought Index and Its Application Over Semi-Arid Region(2016) Hazaymeh, Khaled; Hassan, Quazi; Islam, Tanvir; Blais, Rodrigue; He, Jianxun; Nowicki, EdwinAgricultural drought is a natural disaster that usually occurs when the available water content goes below the optimal needs of the proper growth of plants during its growing season. It has enormous impacts on economic, environmental, and social sectors. In this study, our overall objective was to develop a fully remote sensing-based method for monitoring agricultural drought conditions and evaluate its performance over a semi-arid heterogeneous rainfed agricultural dominant landscape in Jordan. In general, remote sensing data having both high spatial and temporal resolutions would be required for evaluating agricultural drought conditions, as usually agriculture land cover would be relatively heterogeneous and small in size, while drought could occur during critical short time periods i.e., few days or weeks during the growing season. However, due to different technical and cost issues such high spatio-temporal remote sensing data are still unavailable. Thus, we opted to develop a spatio-temporal image-fusion model (STI-FM) to generate synthetic Landsat-8 like data with 30 m spatial and 8 day temporal resolutions upon combining regular Landsat-8 (having 30 m spatial with 16 day temporal resolutions) with moderate-resolution imaging spectroradiometer (MODIS)-based 8-day composite data having 250-1000 m spatial resolutions. Then, we used these fused data in developing the agricultural drought monitoring index (ADI) as a combination of three uncorrelated remote sensing-based agricultural drought related variables [i.e., normalized difference water index (NDWI), visible and shortwave drought index (VSDI), and land surface temperature (LST)]. Results showed that the proposed STI-FM was able to produce synthetic Landsat-8 data with strong accuracy (i.e., r2 were in the range 0.71 to 0.90). The evaluation of agricultural drought conditions over the study area using the proposed remote sensing-based agricultural drought index showed high agreements such as 85% overall accuracy and 78% Kappa-values, when compared to ground based 8-day standardised precipitation index (SPI) values. These strong results demonstrated that the proposed methods would be great in monitoring agricultural drought conditions at agricultural field scale (i.e., high spatial resolution) and short time periods (i.e., high temporal resolution).Item Open Access Evaluation and Optimization of Weather Networks in Athabasca Oil Sands Region(2023-01-26) Deshmukh, Dhananjay; Hassan, Quazi; Gupta, Anil; Achari, GopalThe monitoring of weather is required for climate studies, research, and forecasting. For the monitoring purpose, three networks of 19 stations i.e., Water Quantity Program (WQP), Meteorological Towers (MT), and Edge Sites (ES) were operational in Athabasca oil sands region. The overall objective of the study was to identify similarities/redundancies in meteorological observations for the optimization of weather networks. For this, firstly similarity among meteorological parameters have been quantified for air temperature (AT), relative humidity (RH), solar radiation (SR), barometric pressure (BP), precipitation (PR), and snow depth (SD) among station-pairs of each network. In this process, Pearson’s correlation coefficient (r) and average absolute error (AAE) were the best representative measures from the methods of association and coincidence while proposed percentage of similarity (PS%) was the best in comparison to r and AAE to quantify the similarity. Further, RH found to be the least variable with strong and acceptable similarity in each network while similarity was decreased in order of SD, BP, AT, SR, and PR respectively. Secondly, Wind data has been analyzed for these three networks to find the optimal network. Here, it has been revealed that wind rose diagram only appropriate for visual comparison of wind characteristics while r, AAE and PS measures were suitable for similarity analysis of wind. Later, it has been found that all station from these three networks were required to represent wind variability in the region due to very low and unacceptable PS values. Thirdly, influence of land cover and topography have been evaluated on meteorological parameters of these 19 stations where they categorised under seven groups based on similar kind of land cover and topography. In this evaluation, parameters AT and SR were shown strong correlation but limited similarity while RH exhibit the least variability in each group. Moreover, BP and SD have some similarities while PR and WSD were highly variable due to various locational factors other than similar land cover and topography.Item Open Access Hydrological Modelling of River Flow Forecasting in Cold Regions and Its Application over the Athabasca River(2023-03-23) Belvederesi, Chiara; Hassan, Quazi; Achari, Gopal; Rangelova, Elena; Gupta, AnilFloods are disasters that represent a growing threat to the communities living close to rivers. To maximize community resilience, the main objective was to formulate a transferable framework for river flow forecasting in cold and poorly gauged/ungauged regions. First, the literature was reviewed, summarizing the recent findings in river flow forecasting in these regions. Here, hydrological processes greatly vary seasonally and annually, translating into increased model uncertainty. Regionalization, spatial calibration, and other methods were implemented into process-based and empirical models. Although process-based models provided a wide understanding of a watershed’s hydrology, they were often complex and computationally demanding. Empirical models produced fewer calibration parameters although generated biased results when insufficient descriptors were available. The results from this review highlighted some efforts necessary to improve river flow forecasting, including: coping with limited data; providing user-friendly interfaces; advancing model structure; developing a universal method for transferring parameters; standardizing calibration and validation; integrating process-based and empirical models. In addition, a machine learning-based model was developed using a single-input sequential adaptive neuro-fuzzy inference system (ANFIS) in the Athabasca River Basin (ARB) in Alberta, Canada. After estimating the optimal lead time between four hydrometric stations, data measured near the source were used to compute flows near the mouth, over approximately 1,000 km. This technique was compared to nonsequential and multi-input ANFIS, which used data from all the four hydrometric stations. The results showed that sequential ANFIS could accurately predict flows (r2 = 0.99, Nash–Sutcliffe = 0.98) with a longer lead time (6 days) using a single input. Finally, a novel simplistic method for short-term (6 days) forecasting called Flow Difference Model (FDM) was developed and compared against existing hydrological models (i.e., Regression Models (RM) and Base Difference Model (BDM)), to demonstrate that simplistic modelling can achieve acceptable accuracy. The results showed that the FDM outperformed the other models (Nash–Sutcliffe = 0.95) using limited inputs and calibration parameters. Moreover, the FDM had similar performance to machine learning techniques, demonstrating the forecasting capability of simplistic methods. These findings could be utilized towards flood prevention and planning, operations, maintenance, and administration of water resource systems.Item Open Access Modeling the Loading and Fate of Estrogen(2015-12-04) Fleming, Michael; Achari, Gopal; Hassan, Quazi; He, Jennifer; Wang, RuishengEndocrine disrupting compounds may produce infertility, nervous system disorders, and improper functioning of the immune system in humans and wildlife. Estrogens are classified as the most potent and common endocrine disrupting compounds, and the major point source for estrogen is municipal wastewater. Monitoring of estrogen is challenging, expensive, and intermittent; and therefore, the focus of this work is modeling estrone, 17β-estradiol, and 17α-ethynylestradiol concentrations from wastewater treatment plants in Calgary and Edmonton, Alberta, and Brandon, Manitoba. Demographic groups, excretion rates, population estimates, average daily flows, calculated estrogen transformation, calibration, calculated influent-to-effluent reduction percentages, and a treatment unit removal matrix are used to determine loading estimations of estrogen. The results demonstrate reasonable accuracy against previous measurements, and findings are consistent with concentrations reported in the literature. Upon further calibration with additional local data, the model may be used as a risk assessment analysis tool for these contaminants of concern.Item Open Access Performance of Actively-Aerated Biofilters Using a Multiple-Level Air Injection System to Enhance Biological Treatment of Methane Emissions(2016) Farrokhzadeh, Hasti; Hettiaratchi, J. Patrick A.; Achari, Gopal; Hassan, QuaziThe present research is intended to remove methane from a gas stream by converting it into carbon dioxide by means of aerobic methane-oxidizing microorganisms. Such technology can be useful when dealing with biogas from landfills, or solution gas from natural gas wells. Taken that methane oxidation is an aerobic process, a major enhancement in efficiency is observed by the active introduction of oxygen throughout the biofilter profile. Thus, with the aim of improving conventional biofilters, in this study a multiple-level aeration biofilter design is proposed. Laboratory column experiments were run to study three different actively-aerated methane biofilter configurations. Columns were aerated at one, two, or three levels along the bed thickness. Inlet methane loading rates were increased at five stages between 6 mL/min to 18 mL/min. A first set of columns were operated introducing air at flow rates calculated based on the oxidation reaction stoichiometry. The effects of methane feeding rate, levels of aeration, and residence time were evaluated. Based on the results obtained from a mixed Analysis of Variances, the response surface, and laboratory observations, it was suggested that the biofilter column with two aeration levels has the most even performance over time, maintaining an average oxidation efficiency of 85.1% over the 195 days of experiments. A second set of columns with the same aeration designs were run for varying air to methane flow rates. Air flow rates were changed inlet air flow rates between ¼ of stoichiometric levels to 1.5 times higher than stoichiometric values. The performance of columns was recorded for 90 days. With air flow rates set at ¼ of the stoichiometric value, an average 13.8% reduction in performance of the biofiltration designs was observed. However, more experiments are required to evaluate the long-term performances of aerated biofilters operated under low air to methane flow rate ratios.Item Open Access A Remote Sensing-Based Approach to Comprehend Local Warming Trends and Its Influencing Factors(2022-06) Ejiagha, Ifeanyi; Hassan, Quazi; Anil, Gupta; Ashraf, Dewan; Elena, Rangelova; Md Golam, Kibria; Mir, MatinOne main consequence of anthropogenic activities on the earth’s surface is an increment of local temperature over a long period, i.e., local warming. Local warming modulates the local climate and increases the urban thermal intensity. My overall objective was to develop a remote sensing-based method for comprehending local warming intensity, trends, and potential influencing factors in the Canadian province of Alberta. To achieve this, I investigated the impact of landscape composition and configuration on land surface temperature (LST) in the city of Edmonton at the neighbourhood level. In addition, I quantified local warming trends and their relationship with large-scale atmospheric oscillation in the natural subregions of Alberta and assessed urban warming trends and their potential influencing factors in the cities of Calgary and Edmonton. I employed Landsat 5 Thematic mapper (TM), Landsat 8 Operational Land Imager (OLI) and Thermal Infrared Sensor (TIRS), and monthly LST composites of moderate resolution imaging spectroradiometer (MODIS) and four indices of atmospheric oscillation from 2001 to 2020. I derived land use land cover (LULC) and LST maps from Landsat images to assess the impact of LULC composition and configuration on Edmonton’s LST. I also determined monthly and annual local warming trends in the natural subregions of Alberta and urban warming in the cities of Calgary and Edmonton using the MODIS data. My results indicated the highest LST in residential and industrial neighbourhoods of Edmonton caused by the proportion and clustered arrangement of landscape patterns, where residential exhibited higher LST than industrial with the same LULC composition. Also, I found significant warming trends in May for most of the natural subregions of the Rocky Mountains and Boreal Forest, and Pacific North America (PNA) was the only atmospheric oscillation with influence from February to April and October to December. Besides, I found a continuous increase in annual day and nighttime surface urban heat island intensity (SUHI) in Calgary and Edmonton over the last 20 years. I deduced that population, built-up expansion, and sea surface temperature (SST) were the main factors that influenced the urban temperature. The findings of this research would be helpful for policymakers and urban planners to develop adaptation and mitigating strategies to curb the impact of local warming, ensuring a sustainable city and environment.Item Open Access Road Safety Issues on Two Major Intercity Highways in Sri Lanka(2017) Senasinghe, Rukunayakage; Wirasinghe, Sumedha; Kattan, Lina; De Barros, Alexandre; Hassan, QuaziAccording to the World Health Organization’s 2015 global status report on road safety, nearly 1.25 million people are killed in road accidents each year, and millions more suffer serious injuries with long-term adverse health consequences. In Sri Lanka, road traffic fatalities have increased alarmingly from 3.0 to 10.8 deaths per million population per year, from 1938 to 2013.In this study, we carried out a micro-level analysis of accidents occurred on two major intercity highways (A001 and A004) in Sri Lanka. This study was mainly focused on analyzing crash-frequency and crash-injury severities on both highways A001 and A004. The traditional negative binomial (NB) regression model was used to predict the frequency of crashes of a specific severity level, as a function of explanatory variables and, multinomial logistic regression (MLR) was used to analyze the factors that prevailed in a specific crash leading to a certain crash severity, including site-specific factors on sections of both highways A001 and A004. Average daily traffic (ADT) and number of lanes were found as significant contributing factors in increasing the crash frequencies on both A001 and A004 highways. Urbanicity, weather and light condition, traffic control, casualty gender and age, protection, element type and collision type were the most vital ten crash injury severity contributors found on both A001 and A004 highways.Item Open Access StructureTransfer: A Scene Parsing Framework via Graph Matching for Images and Point Clouds(2016) Yu, Tianshu; Wang, Ruisheng; Wang, Ruisheng; Wang, Xin; Hassan, QuaziScene parsing is to densely label the pixels in an image with the semantic categories. In this thesis, we present a scene parsing framework which can work on both images and point clouds. To this end, we develop two separate pipelines for images and point clouds. For point clouds, a coarse segmentation is implemented to obtain an initial distribution for the objects. For images, superpixel segmentation is implemented and StructureTransfer is carried out. StructureTransfer is a model to find similar regions across scenes. The two pipelines converge at the inference step. Several novel potentials, representing point cloud constraints and StructureTransfer scores, are introduced into a traditional Markov Random Field (MRF) for the inference. The parsing accuracy of the proposed method is close to state-of-the-art algorithms on images. With the point clouds, the accuracy is significantly enhanced. The proposed framework shows remarkable prospect in real-world applications.Item Open Access UAV-Based Digital Imaging System for the Derivation of 3D Point Cloud for Landslide Hazard Analysis(2016) Al-Rawabdeh, Abdulla; Habib, Ayman; El-Sheimy, Naser; Hassan, Quazi; Gao, Yang; Kattan, Lina; Shaker, AhmedEmergency disaster response and analysis of landslides depend on accurate, rapid detection and extraction of a landslide area. Terrestrial laser scanning systems (TLS) are highly accurate and provide quick 3D point cloud data with high resolution, but suffer from occlusions, truncation, and orientation bias. This dissertation proposes an augmentation of TLS and an image-based point cloud generated from a semi-global matching (SGM) algorithm on an UAV platform outfitted with a low-cost action camera to overcome these limitations. The experimental results provided high quality measurements for the geotechnical discontinuity plane orientation parameters, increased safety, saved cost and time, and provided more accurate results compared to manual field measurements, TLS data only, and SGM data only. This dissertation developed a comprehensive system using UAVs and SGM techniques to accurately identify and extract landslide scarps within centimeter-scale accuracy through three automated approaches. These approaches accurately detected and extracted landslide scarps based on the ratio of the normalized Eigenvalues derived using principal component analysis, surface roughness index, and slope measurements from the 3D image-based point cloud. Experimental results using the fully automated 3D point-based analysis algorithms confirmed that these approaches can effectively distinguish landslide scarps. The developed algorithms are a flexible and effective tool for monitoring landslide scarps and are acceptable for landslide mapping purposes. A robust image-based registration method also was developed for the simultaneous evaluation and temporal monitoring of landslide dynamics from different epochs. This method includes the camera’s IOPs and EOPs of the involved images from all the available observation epochs via a bundle block adjustment with self-calibration. A SGM technique was implemented to generate 3D point clouds for each epoch using the images captured for each epoch separately. The accuracy of the co-registered surfaces was estimated by comparing the non-active patches within the monitored area of interest. Since non-active sub-areas are stationary, the computed normal distances theoretically should be close to zero. The quality control of the registration results showed an average normal distance of approximately 3.7 cm, which is within the noise level of the reconstructed surfaces. Overall, the registration approach proposed in this dissertation is low level.Item Open Access Use of GIS and Remote Sensing in Mapping Rice Areas and Forecasting Its Production at Large Geographical Extent(2015-06-08) Mosleh, Mostafa; Hassan, QuaziRice is one of the staple foods for more than three billion people worldwide. Here, the overall objective was the development of rice area mapping and forecasting its production using primarily geographic information system (GIS) and remote sensing technology, and its implementation over a large geographical extent. In this thesis, Moderate Resolution Imaging Spectroradiometer (MODIS)-derived 16-day composite of normalized difference vegetation index (NDVI) at 250m spatial resolution was used in conjunction with other GIS datasets during the period 2007-2012. For mapping the rice area during the entire growing season (i.e., January-May), the results demonstrated a reasonable agreements between the proposed method and ground-based estimates at both country level [i.e., relative error (RE) in the range -0.83 to 1.42%] and district-level (i.e., co-efficient of determination, r2 in the range 0.69 to 0.89) during the period 2010-2012. The rice yield forecasting consisted of two methods: (i) the first method was based on images acquired from plantation to the peak greenness stage, that is, six consecutive images during the growing season (i.e., January 1 to April 6/7); and (ii) the development of second method utilized two images during the initial (i.e., January 1 to January 16) and peak greenness (i.e., March 23/24 to April 6/7). In both methods, initially I delineated the rice area and then forecasted the yield before harvesting. The rice area mapping and forecasting its production based on the first method demonstrated good agreements between the model and ground-based area estimates during 2010-2012 [i.e., r2 ≥ 0.93; root mean square error (RMSE) in between 32,237 to 36,040 ha at the 23 district-levels; and RE in the range -0.26 to 0.50% at country level]. However, the spatial distribution of rice areas produced very well for all the districts except for six districts (i.e., average relative error of -3-43% using data acquired during the entire growing season and from plantation to the peak greenness). Also, good agreements were found, i.e., r2, RMSE, and RE were in the range of 0.71 to 0.77, 0.25 to 0.59 Mton/ha, and -0.21 to 14.65%, respectively between forecasted and ground-based yields estimates during 2010-2012 period. In addition, strong agreements were also observed using the second method while compared with ground-based area estimates during 2010-2012 [i.e., r2, RMSE, in between 0.93 to 0.95; 30,519 to 37,451 ha respectively at the 23 district-levels, respectively; and RE -2.87 to 3.60%, at the country-level]. The spatial distribution of rice area derived by the model demonstrated well for all 23 districts with the ground-based estimates (i.e., average RE under 13%). I also found good agreements (i.e., r2, RMSE, were in between 0.76 to 0.86; 0.21 to 0.29 Mton/ha at the 23 district-levels, respectively; and RE of 0.81 to 5.41% Mton/ha, at the country-level) between forecasted and ground-based yields during 2010-2012 period. Despite the effectiveness of my proposed methods, I strongly recommend that these methods should thoroughly be evaluated prior to implement in other geographical locations.Item Open Access Use of Remote Sensing and Ground Data in Comprehension of the Flooding in the Bow River Basin, Alberta(2015-06-29) Veiga, Victor Barcante; Hassan, Quazi; He, Jianxun (Jennifer)Flooding is a devastating natural hazard throughout the world. Consequently, a flood management system is vital. Here, the aim was to investigate elements of flood management as it pertains to the Bow River in Alberta. The specific objectives included: (i) river flow forecasting at Calgary, (ii) flood extent estimation at Calgary, and (iii) river planform change detection. Analyses revealed that using a multivariable linear regression (MLR) formulated as a function of upstream gauge stations and the station of interest using antecedent flows demonstrated strong relationships (i.e., r2 = 0.93). Furthermore, the flood extent estimation gave a kappa statistic of 0.6, which is reasonable considering that the image was taken 16 days after peak flood time. Lastly, the Bow River planform change detection showed that the 2013 floods caused a higher erosion in the lower Bow River (i.e., 361.62ha) as compared to the upper Bow River area (i.e., 206.01ha).Item Open Access Use of remote sensing-derived variables in developing a forest fire danger forecasting system(Springer Netherlands, 2013-01-26) Chowdhury, Ehsan; Hassan, QuaziOur aim was to develop a remote sensing-based forest fire danger forecasting system (FFDFS) and its implementation in forecasting 2011 fire season in the Canadian province of Alberta. The FFDFS used Moderate Resolution Imaging Spectroradiometer (MODIS)-derived 8-day composites of surface temperature, normalized multiband drought index, and normalized difference vegetation index as input variables. In order to eliminate the data gaps in the input variables, we propose a gap-filling technique by considering both of the spatial and temporal dimensions. These input variables were calculated during the i period and then integrated to forecast the fire danger conditions into four categories (i.e., very high, high, moderate, and low) during the i ? 1 period. It was observed that 98.19 % of the fire fell under ‘‘very high’’ to ‘‘moderate’’ danger classes. The performance of this system was also demonstrated its ability to forecast the worst fires occurred in Slave Lake and Fort McMurray region during mid-May 2011. For example, 100 and 94.0 % of the fire spots fell under ‘‘very high’’ to ‘‘high’’ danger categories for Slave Lake and Fort McMurray regions, respectively.Item Open Access Well Production Prediction and Visualization Using Data Mining and Web GIS(2016) Wei, Bingjie; Wang, Xin; Liang, Steve; Hassan, QuaziMassive data sets have been accumulated in the oil and gas industry. As strategic assets, voluminous data of different data types should be leveraged and turned into information for agile and accurate decision-making. Three oil and gas data-related studies are covered in this thesis. Firstly, a data-driven model is proposed for predicting well production using time-series production data from analogous and adjacent wells. Secondly, interactive visualization tools are designed and implemented for oil and gas spatial and temporal datasets, following an “Overview first, zoom and filter, then details-on-demand” guideline (Shneiderman, 1996) in order to maximize information delivery in single displays. Thirdly, a web-based Geographic Information System (GIS) application is designed and implemented for a Steam Assisted Gravity Drainage (SAGD) dataset to provide users convenient access to public and proprietary SAGD data, as well as some data analysis and visualization functions.