Abstract: Abstract Email has become one of the most widely used forms of communication, resulting in an exponential increase in emails received and creating an immense burden on existing approaches to email classification. Applying the classification method on the raw data may worsen the performance of classifier algorithms. Hence, the data have to be prepared for better performance of the machine learning classifiers. This paper proposes an enhanced data preprocessing approach for multi-category email classification. The proposed model removes the signature of the email. Further, special characters and unwanted words are removed using various preprocessing methods such as stop-word removal, enhanced stop-word removal, and stemming. The proposed model is evaluated using various classifiers such as Multi-Nominal Naïve Bayes, Linear Support Vector Classifier, Logistic Regression, and Random Forest. The results showed that the proposed data preprocessing to email classification is superior to the existing approach. PubDate: 2021-01-16
Abstract: Abstract This study attempts to analyze and simulate urban growth pattern of Colombo city in Sri Lanka which is a dynamic and rapid urbanizing region. The spatiotemporal urban growth patterns during 1997–2019 were first analyzed by comparing Land Cover (LC) maps for time intervals between 1997–2008 and 2008–2019 using intensity and growth pattern analysis. Urban lands in Colombo have grown in a faster rate during 1997–2008 as compared to 2008–2019 period. The prominent spatial expansion pattern during 1997–2008 is outlying, as opposed to edge expansion which is predominant during 2008–2019. These major urban expansion patterns were modeled to predict the future urban structure of Colombo in 2030 using FUTURES (FUTure Urban-Regional Environment Simulation) model. FUTURES is a patch-based, multilevel modeling framework for simulating the emergence of landscape spatial structure in urbanizing regions. Simulated result generated from the model reveals substantial agreement with real ground urban changes showing a kappa value of 0.78. The model allows to predict three different scenarios, namely Business as Usual, Infill Growth and Sprawl showing over 100 km2 increase in urban lands by 2030. Predicted urban structure was then compared with proposed development plan. With certain limitations arising from available data, the model is effective in predicting possible urban scenarios and providing valuable inputs to support better decision making for sustainable development of Colombo city. The results demonstrated in this study would be useful in modelling urban growth in other cities and further validate the efficacy of the proposed workflow. PubDate: 2021-01-09
Abstract: Abstract The world has now facing a health crisis due to outbreak of novel coronavirus 2019 (COVID-19). The numbers of infection and death have been rapidly increasing which result in a serious threat to the social and economic crisis. India as the second most populous nation of the world has also running with a serious health crisis, where more than 8,300,500 people have been infected and 123,500 deaths due to this deadly pandemic. Therefore, it is urgent to highlight the spatial vulnerability to identify the area under risk. Taking India as a study area, a geospatial analysis was conducted to identify the hotspot areas of the COVID-19. In the present study, four factors naming total population, population density, foreign tourist arrivals to India and reported confirmed cases of the COVID-19 were taken as responsible factors for detecting hotspot of the novel coronavirus. The result of spatial autocorrelation showed that all four factors considered for hotspot analysis were clustered and the results were statistically significant (p value < 0.01). The result of Getis-Ord Gi* statistics revealed that the total population and reported COVID-19 cases have got high priority for considering hotspot with greater z-score (> 3 and > 0.7295 respectively). The present analysis reveals that the reported cases of COVID-19 are higher in Maharashtra, followed by Tamil Nadu, Gujarat, Delhi, Uttar Pradesh, and West Bengal. The spatial result and geospatial methodology adopted for detecting COVID-19 hotspot in the Indian subcontinent can help implement strategies both at the macro and micro level. In this regard, social distancing, avoiding social meet, staying at home, avoiding public transport, self-quarantine and isolation are suggested in hotspot zones; together with, the international support is also required in the country to work jointly for mitigating the spread of COVID-19. PubDate: 2021-01-04
Abstract: Abstract The works explores the possibilities of using GIS for the government health facility centres in Murarai-I C.D.Block of Birbhum district in India. The empirical data were processed in GIS environment and principal component analysis has been carried out for quantitative inferences. The GIS application is created cover three main areas of maternal health care services which are identification of physical accessibility of each health-care units, assessment of influence zones or health service area of the government facility centre and finally, quantification of underserved scenario in service provision. Each of the issues is covered using several GIS functions including road network analysis, overlay analysis, euclidian distance, buffer and thiessen polygon analysis. ASTER-digital elevation model has been used to identify the topographical aspects of the study area. A sample of 229 cohorts and 28 health centres have been drawn through systematic random and stratified procedures on the basis of cross-sectional retrospective survey. The survey has established three principal findings. First, distance shows a strong inverse relationship with the utilization of health services in the study area. Second, comparatively higher elevated areas are characterized by smaller influence zone and under utilisation of services. Finally, the underserved score is higher in the northern part of study area. Recommendations for the location based modelling of health service provision and reduction of underserved areas at deprived periphery is depend on equity-based provision of services and proportionate distribution of health personnel along with essential transportation system. PubDate: 2020-12-01
Abstract: Abstract Air quality disturbance zones of the Greater Cochin region (Kerala, India) for the years 2014, 2015, 2016 and 2017 along with air quality assessment and dispersion modelling using in situ measurements and mathematical models, have been investigated in this report. Landsat-8 satellite with OLI and TIRS sensors on board were used for the analysis. The ground based in situ measurements (pollutant parameters) were also obtained from the Kerala state pollution control board. Zonal statistics analysis was performed in various combinations especially air quality disturbance zones with respect to land use/land cover and administrative units for various years. The air quality disturbance zone index (AQDZI) values observed indicated that 38.16% of the study area in 2014 belonged to very good category, 22.94% to good category, 32.37% to moderate category and 6.53% to poor category. In 2015, 56.78% of study area belonged to very good category and 43.221% to good category while in the year 2016 very good category of AQDZI values occupied an area of 45.284% and good category AQDZI values occupied an area of 54.72%. In 2017, 99.834% of the study area belonged to good category and 1.233% to moderate category. Results obtained from zonal statistics revealed that the poor air quality was observed in built up area and good air quality at rubber plantation in all the four selected years. In the case of administrative units, Kochi Corporation experienced poor air quality during all the years studied and Mulanthuruthy grama-panchayath experienced good air quality during most of the years except in 2016. PubDate: 2020-12-01
Abstract: Abstract This study examined four Regional Climate Models (RCMs) from Coordinated Regional Climate Downscaling Experiment-Africa which are widely used in Africa researches, to select the best performing model against gridded observational dataset over the Kpong Irrigation Scheme area with data from 1964 to 2005. Statistical tools such as correlation coefficient (r), RMSE, and standardized deviations (σ), and Mann–Kendall trend analysis were used to determine model performance. The capability of the models to reproduce measured yearly cycles and inter-annual variability for both precipitation and temperature were also assessed. The average precipitation and temperature biases for all the models are located in the ± 0.8 mm range with temporal correlations below 0.3. The Mann–Kendall trend analysis revealed the existence of predominant decreasing trends. On the other hand, all the models were able to reproduce the inter-annual variability, but were unable to capture the long and short rainfall range and deviations accurately. In general, the RCA4-CanESM2 of the four RCMs reproduces the precipitation and temperature climatology with reasonable skill and suggested as the most efficient for climate impact assessment researches over the study area. Overall, our results provide a systematic diagnosis of the strengths and weaknesses of the four models over a wide range of temporal scale. PubDate: 2020-12-01
Abstract: Abstract The present work intends to predict char area in river Ganga from Rajmahal to Farakka barrage using advance machine learning models for justifying the sustainable habitability of the charland. Artificial neural network (ANN), end point rate and linear regression for spatial and ANN, radial basis function, random forest, support vector machine (SVM) models for numerical charland prediction are used. Historical charland study since 1990 to 2018 exhibits 34.32% increase 46.86% decrease of total charland and river flow areas respectively. Amongst the spatial prediction models ANN has effective predictability with acceptable performance level. In coming 20 years no significant change will happen in case of Bhutni and Piarpur charland. Amongst the numerical models by 2038 charland area is likely to be expanded as predicted by ANN and SVM models with statistical significance. Based on the findings it can be recommended that for predicting dynamic charland area ANN model could be used both at spatial and numerical scales. The findings also exhibits that charland area is expected to be enhanced and it has immense planning importance specially for finding habitability in charlands. PubDate: 2020-12-01
Abstract: Abstract High accuracy land use/land cover (LULC) mapping of Yamuna Chambal ravines for reclamation and conservation of these degraded/badlands is indispensable. Integration of freely available SAR datasets along with medium to high resolution optical data is one of the best approach for high accuracy LULC mapping. The objective of the presented study is to evaluate the fusion technique for Sentinel-1 SAR data and Sentinel-2 optical data for high accuracy LULC mapping in order to assess the area occupied by these negative landforms i.e., ravines. The VH-polarization fused image with Sentinel-2 optical data gives the best accuracy of 85% followed by VV-polarization fused image with same datasets of 84% accuracy whereas Sentinel-1 and Sentinel-2 provides the accuracy of 60 and 80%, respectively. The prepared LULC maps shown that bad land (Ravine class) occupied an area in the range of 600–700 km2 using combinations of different datasets as the wastelands in the area required immediate reclamation and conservation measures to be adopted. However, asymptotic performance of fusion technique for SAR and optical data further elucidate its successful implementation and dominancy over other datasets for improved LULC mapping. PubDate: 2020-12-01
Abstract: Abstract We have analyzed the geospatial datasets such as precipitation, runoff, soil moisture, aridity, soil degradation, and future (2050) climate of India and investigated the spatial distribution pattern at the watershed level. Furthermore, we have investigated the long-term TerraClimate present decadal (2006–2015) trend with 20 years back decadal (1976–1985) data for evaluating temporal change in precipitation, runoff, and soil moisture at the watershed level of India. The long term decadal precipitations, as well as soil moisture deficit trend, are found very significant in the watersheds of the Ganga and Brahmaputra basin. The decadal runoff increase (%), when compared with 20 years back decadal runoff showed a high percent (> 50%) increase in the majority of Sabarmati river basin in Gujarat state of India. The three villages Milkipur, Bikapur, and Bantikalan (Faizabad district of Uttar Pradesh) have shown a maximum reduction of soil moisture. The analysis of predicted (2050) temperature and precipitation anomaly showed the precipitation deficit in the majority of watersheds of Indus river basin and their sub-basin. Similarly, the temperature increase in the year 2050 is found very significant in almost all watersheds of India with a range of 0.8 to 1.9 °C but it is more crucial for some of the northern parts of Indus river basin and Brahmaputra basin. Such analysis highlights the need for an adequate management plan with robust soil and water conservation at a watershed level for achieving sustainable development goals (SDGs). PubDate: 2020-12-01
Abstract: Abstract Drainage congestion induced waterlogging problem is a major issue for coastal agriculture in Sundarban. The mismanagement of drainage system, saucer shape appearance of the delta and erratic rainfalls in monsoon season (June–September) have been aggravated the problem of waterlogging. Therefore, the main objective of this study is to find out the root causes of waterlogging in agricultural field and its implications to the coastal agriculture. This work is based on primary data, directly collected from farmers through questionnaire and face to face interview to understand the issues and challenges of waterlogging in coastal agriculture. In addition to this, the Instrumental surveying has also been conducted to identify the minute changes in slope direction with relation to land use pattern of the delta. Remote sensing and GIS techniques help to detect the spatio-temporal change of drainage network and resulted drainage congestion through overlay analysis of multi-temporal vector layers. This study revealed that there are 70% farmers engaged in monocropping mainly rice farming but a few farmers treated waterlogging as an opportunity for integrated farming such as rice + fish farming, rice + fish + on dyke horticulture. The farmers who are engaged in monocropping intend to shift from monocropping to integrated farming system but monetary constrains and lacks of skills are the major barriers for adaptation of integrated farming. A comparative economic assessment has been done to calculate the relative economic efficiency of different types of farming system and better utilization of land use potentiality. This study is a way direction towards better management of agricultural system in this island. PubDate: 2020-12-01
Abstract: Abstract An Open Source Web-GIS platform for Geologic Voxel (Geo-Vox) modeling and visualization, has been developed. Geo-Vox provides a comprehensive framework by integrating GIS, relational database, open geospatial standards-compliant web mapping engine, 2-D and 3-D rendering libraries for geologic modeling. Free and Open Source Software for Geoinformatics (FOSS4G) stack comprising of GRASS GIS, PostgreSQL, MapServer, OpenLayers and three.js JavaScript 3-D library have been used to implement the system. Geo-Vox overcomes several limitations of solid modeling by construction of model based on an intuitive logical relation between geologic units and boundary surfaces. Two-dimensional visualization allows rendering of horizontal and vertical sections at user-defined planes. The voxel model can also be exported in a format amenable for rendering as 3-D solid model. Geo-Vox is unique, in that, (a) logics used to create the model are easily comprehensible to geologist (b) offers high degree of interoperability (c) leverages FOSS4G stack to implement a comprehensive geologic modeling tool that is hitherto unavailable. The functionality of Geo-Vox is demonstrated using data derived from published geologic map. The results confirm the potential of Geo-Vox to provide an interoperable and scalable framework for delivery of value-added geological information for a variety technical and societal needs. PubDate: 2020-12-01
Abstract: Abstract The main objective of the present study is to enhance the accessibility facilities for local public to educational centers in Tiruchirappalli City. For this approach, the existing K-12 schools, Census tracts and road network were spatially plotted using the techniques of geospatial system. Spatial accessibility index is computed using Three-step floating catchment area (3SFCA) method. The findings indicate (39%) of catchment area has been shortage of education facilities. The index of 3SFCA and its spatial pattern has been compared, validated using enhanced two-step floating catchment area (E2SFCA) method. The incorporated Gaussian weight of 3SFCA clearly reduces the high estimate of demand problem of the study area. Through 3SFCA and E2SFCA, the number of wards observed to be shortage is 14 and 26 respectively. Overall, the analysis concludes that 3SFCA is an effective method in spatial planning of educational facilities. In future, this study enables the urban planners and decision makers to maximize spatial accessibility by establishing a new facility and improve the existing facilities in shortage region. PubDate: 2020-12-01
Abstract: Abstract Tuberculosis disease burden remains a fundamental global public health concern for decades. The disease may not uniformly distributed with certain geographical areas recording higher notification rate than others. However, the Ethiopian national TB control program does not provide services based on those areas with the greatest notifications but rather on a uniform strategy. Therefore, this study aimed to assess the spatial distribution and presence of the spatio-temporal clustering of the disease in different geographic settings over 8 years in the East Hararge Zone. A retrospective space-time and spatial analysis were carried out at districts of East Hararghe zone based on a total of 34,564 notified TB cases during the study period. The study identified different case notification rate over districts and clustering effects for the purely spatial and spatiotemporal with different estimated relative risks. The study recommends national tuberculosis control program to give attention to highly observed case notification rates specially Babile, Haramaya and Jarso districs of East Hararge Zone to have effective TB intervention in the study area. PubDate: 2020-12-01
Abstract: Abstract Rice is one of the most important food crop in India covering about one-fourth of the total cropped area. India is the second largest producer and consumer of rice and accounts for 21% of the world’s total rice production. Rice is fundamentally a kharif season crop and grown in mainly rainfed areas. Recently there is a considerable increase in production, area and yield of rice crop in India. Temporal monitoring of crop area under cultivation is essential for the sustainable management of agricultural activities on both national and global levels. The present study is envisaged to estimate area under kharif rice using multi-temporal Sentinel-1 Synthetic Aperture Radar (SAR) data with dual polarization (VH and VV) in Bhandara district of Maharashtra. The geographical area of Bhandara district is 4087 square kilometres and lies in between 20°64′03′' to 21°60′18′' N latitude and 79°44′93′' to 80°08′70′' E longitude. The rice area is extracted using Random Forest (RF) classification techniques available in SNAP tool and validated using the ground observation collected from the field. An area of 1760 square kilometres was found under kharif rice out of 4087 square kilometres area of entire Bhandara district. The rice is predominant crop and covered around 43% of the total geographical area of Bhandara district during kharif season. The user accuracy (omission error), producer accuracy (commission error) for rice crop, overall accuracy and Kappa coefficients were 82.7, 90.0, 91% and 0.80, respectively. The study found that SAR data can be successfully used for acreage estimation with RF classifier. PubDate: 2020-11-23
Abstract: Abstract To understand the natural processes of planform change, meandering and formation of braid bars, satellite sensor data of few decades play a significant role. The present research focuses on the planform dynamics of Ganga River from Sahibganj (Jharkhand) to Jalangi in West Bengal, India. This study is based on the sequential river planform maps. These maps were prepared using Landsat 1, Landsat 3, Landsat 4, Landsat 5 and Landsat 7 data for the period 1975–2015 at an interval of 5 years. The sinuosity index, braiding index and spatial analysis of maps were used to assess and classify the river into straight, braided and meander categories. This was observed that braiding index is continuously increasing and the meandering index has decreased from 1.6 to 1.24 during 1975 to 2015. The results showed the changes in channel migration with time and space. From the analysis, it is observed that the factors causing shifting of the Ganga River in some areas are natural and anthropogenic. Landsat images were found to be effective in determining the meandering index, braiding index and planform change of a river. PubDate: 2020-11-17
Abstract: Abstract The COVID-19 pandemic and related lockdown reduced the pollution level in the major megacities worldwide. The air pollution level of the city directly influences the air temperature and also land surface temperature (LST). In this paper, authors analyzed the impact of lockdown due to COVID-19 pandemic on the pollution level of the city and resulted LST. Single channel algorithm has been used to retrieve LST from Landsat Thematic Mapper satellite data. Pre-lockdown and post-lockdown satellite data has been used to show the changes in LST due to lockdown. The air quality index of pre-lockdown and post-lockdown period of the city estimated based on seven pollutants such as PM2.5, PM10, NO2, NH3, SO2, CO and Ozone. The pollution level of the city and LST significantly decreased after lockdown is enforced. The pollution level of the major portion of the city before lockdown is moderately polluted (95–153 µm) and after lockdown the satisfactory level of pollution level observed (33–45 µm). The mean LST before lockdown is 28.76 °C (13 March, 2020) and it decreased down to 26.56 °C after lockdown (30 April, 2020). There is a sharp decrease of low value of LST observed (23.6–17.35 °C) in the city. PubDate: 2020-11-13
Abstract: Abstract Nigeria is currently the worst COVID-19 affected country in West Africa in terms of morbidity and mortality amid ECOWAS’s recent proclamation of the country as the region’s COVID-19 Response Champion. It is against this background that this paper analysed the geographical distribution of confirmed COVID-19 cases and fatalities in West Africa, with a view to understanding why Nigeria is at the heart of the pandemic in the sub-continent. The research relied on COVID-19 data and other health, demographic, transport, economic indicators from published sources. Pearson correlation technique and simple linear regressions were useful in discerning associations between COVID-19 and explanatory factors in West Africa. In order of importance, Nigeria, Ghana and Senegal were the top three on the morbidity list while Nigeria, Mali and Niger had the largest number of fatalities as at June 11, 2020. Results show that the population size and air traffic had significant impact on both COVID-19 morbidity and mortality in West Africa. In addition, Nigeria’s large population size and high air traffic volume did not only increase its susceptibility to the viral infection but also accounted for its being an outlier in the sub-continent. The study recommends that a cautious and gradual reopening of the borders should be considered by member states of the sub-region while behavioural avoidance measures are being enforced till a vaccine is found. PubDate: 2020-11-08
Abstract: Abstract Due to a lack of assets and high improbability, developing an information system for every disaster situation is a challenging task. Consequently, building an information system for such a situation is essential, and the latest research direction has emphasized on development of such a system which varies due to the irregular nature of environments. This work emphasizes the data mining technique based on available disaster data or the earlier prediction of such occurrences to combat damages. The data mining technique is applied to the clustering of data for smooth processes of the obtained data. K-means clustering and analytic network process (ANP) are implemented as unsupervised learning for initial data and to find groups in the data, clustered based on feature similarity. The proposed approach implies an effective tool for predicting impacts in terms of hazards and this paper also evaluates its effectiveness. This study offers important insights into the disaster recovery practitioner to select the best disaster recovery solution and prioritize them for their enterprise. PubDate: 2020-11-04
Abstract: Abstract Training under realistic combat conditions is a prerequisite for maintaining a strong and effective defence force. For training to be effective, militaries rely on the availability and accessibility of suitable training areas to conduct training activities that ensure preparation for executing missions with maximum effectiveness and fewer casualties. Training activities that ensure combat-ready soldiers often cause vegetation degradation through vegetation cover alteration, resultant soil erosion, and increased soil compaction. Ultimately, these activities might compromise the continued availability and accessibility of realistic training conditions. Therefore, it is imperative to early detect, monitor and mitigate vegetation change in military training areas, and to secure sound environmental practices to ensure the sustainable use of training areas. Determining vegetation change by conducting fieldwork is often both time-consuming and expensive. As an expedited, inexpensive way to investigate vegetation change at the South African Army Combat Training Centre (SA Army CTC) Lohatla, the Normalized Difference Vegetation Index (NDVI) was used to determine changes in vegetation after military training exercises. The NDVI results indicate the impact of military exercises on vegetation and shows that exercises with a long duration can indeed lead to vegetation degradation, but short term, light exercises have limited impact on vegetation. PubDate: 2020-11-03
Abstract: Abstract The rapid increase of woody biomass power plants has given rise to concerns about the balance of supply and demand. The purpose of this study was to explore forests vulnerable to over-logging and show them visually in Mie Prefecture, central Japan when supplying woody biomass to power plants based on transportation distance and the time using a non-commercial road network. The destinations were the three biomass power plants and the origins were artificial forests divided by watersheds. Transportation distances and time between destinations and origins were estimated using the route-search function in Google Maps. Forests vulnerable to over-logging were explored based on two thresholds: a one-way distance of 50 km and a travel time of 2.5 h. Our results show that many of the artificial forests in Mie Prefecture might be subject to high harvesting competition. In all, 55.07% of the forest plantations in Mie Prefecture were within 50 km of two or three biomass power plants and 87.11% were within 2.5 h one-way. It might be necessary to supply woody biomass from southern Mie Prefecture. The stakeholder should share logging plans and monitor over-logging while planning for the efficient use of woody biomass in the southern part of Mie Prefecture. PubDate: 2020-10-22
Hybrid journal (It can contain Open Access articles)
