Development of deep learning architecture for automatic classification of outdoor mobile LiDAR data

This paper proposes a deep convolutional neural network (CNN) architecture for automatic classification of mobile laser scanning (MLS) data obtained for outdoor environment, which are characterized by noise, clutter, large size and larger quantum of information. The developed architecture introduces a look up table (LUT) based approach, which retains the geometry of the input MLS point cloud while rescaling. Further, with the voxelisation of the input MLS sample, the ambiguity of selecting one out of multiple point values within a voxel is resolved. The performance of the architecture is evaluated on MLS data of outdoor environment in two instances, first using tree and non-tree classes (non-tree class has objects like electric pole, wire, low vegetation, wall, house and ground) and then with tree and electric pole classes. Additional testing is carried out by mixing the outdoor MLS data of tree and electric pole classes with three classes of indoor objects, taken from Modelnet dataset, thereby assessing the architecture efficacy over an ensemble of three-dimensional (3D) datasets. Classification of tree and non-tree classes, followed by tree and electric pole classes from MLS samples result in total accuracies of 86.0%, 90.0% respectively and kappa values of 72.0%, 78.7% respectively. Moreover, for the combinations of MLS and Modelnet classes, the classification results are promising, reaching a total accuracy of 95.2% and kappa of 92.5%. The LUT based approach has shown better classification over the traditional rescaling approach for the MLS dataset, resulting in an enhancement up to 9.0% and 18.0% in total accuracy and kappa, respectively. With different varieties of tree, non-tree and electric pole samples, the proposed architecture has shown its potential for automatic classification of MLS data with high accuracy. This study further reveals that the accuracy of classification is improved by introducing more spatial features in the input layer. The accuracies produced in this work can be further improved with the availability of better hardware resources.     

Fuzzy AHP Based Multi Crteria Decision Support for Watershed Prioritization

Water Resources Management - The article presents an efficient multi-criteria decision support model (MCDSM) to prioritize susceptible areas in a watershed for soil conservation measures based on...     

Development of a Management Model for a Surface Waterlogged and Drainage Congested Area

Inadequate drainage outlet causing surface waterlogging every year mainly during monsoon period (June through October) over a depressed land of 1062 km² in Mokama group of tals, India, led to a loss of one crop rotation. A management model aiming at minimization of the waterlogged area under constraints of control monsoon runoffs from tributaries discharge water to the depressed land has been developed. Magnitudes of regulated flows are guided by irrigation water requirement of crops grown in commands of different tributaries joined to the depressed land. A nonlinear optimization model has been envisaged and solved setting a total of 160 constraints satisfying conditions of water requirement for crops grown in two seasons and their time-dependent storage requirement. The optimization model has been solved using the Quantitative Systems for Business (QSB) software, which considers a line search methodology for unconstrained problems, and a sequential unconstrained minimization technique (SUMT) with penalty function methodology for constrained problems. The management model provides a solution for strategic water resources development and management in a basin having problems of scarcity, surplus and non-uniform distribution of surface water.     

From landscapes to waterscapes: A PSE for landuse change analysis

We describe the design and implementation of L2W – a Problem Solving Environment (PSE) for landuse change analysis. L2W organizes and unifies the diverse collection of software typically associated with ecosystem models (hydrological, economic and biological). It provides a web-based interface for potential watershed managers and other users to explore meaningful alternative land development and management scenarios and view their hydrological, ecological, and economic impacts. A prototype implementation for the Upper Roanoke River Watershed in Southwest Virginia, USA is described.     

Comparison of Ethyl Acetate with Hexane for Oil Extraction from Various Oilseeds

The aim of the current research was to determine a less hazardous, cheaper and less toxic alternative solvent for hexane for extraction of oil from different oilseeds showing equivalent oil yield and oil quality. A full factorial design with three levels of extraction temperature (80, 100 and 120 °C) and three levels of extraction time (40, 65 and 90 min) with constant solvent to seed ratio value of 4:1 was used to extract the oil. Maximum oil was recovered from canola followed by flax, mustard and camelina. The oil content of canola was found in range of 21.08–36.44, and 25.12–40.38 % for hexane and ethyl acetate, respectively. The heating values of oil extracted from all oilseeds using hexane and ethyl acetate were found in the range of 38.04–39.98 and 37.98–39.37 MJ/kg, respectively. Least viscosity was found for flax seed using hexane followed by camelina, canola and mustard as compared to ethyl acetate. Viscosity of flax oil ranged from 27.23–37.19, and 31.16–55.52 cP for hexane and ethyl acetate solvents, respectively. Considering human safety, less environmental impact, comparable oil yield and quality parameters, ethyl acetate can be a promising alternative to hexane.     

Novel self assembled monolayers of allyl phenyl thiophene ether as potential dielectric material for organic thin film transistors

Allyl phenyl thiophene ether as novel potential dielectric materials for organic thin film transistors have been synthesized by coupling 2-bromothiophene with 4-bromo allyl phenyl ether and was systematically characterized by elemental analysis and NMR. 4-bromo allyl phenyl ether was synthesized by the reaction between 4-bromophenol and allyl bromide. Self assembled mono-layers of these materials have been covalently grafted onto (111) hydrogenated silicon surfaces through thermal hydrosilation with the alkene end by Si-C bonding mechanism. Monolayer formation was carried out using solutions of the alkene in the high boiling point solvent 1,3,5-triethylbenzene and was characterized by X-ray photoelectron spectroscopy (XPS), contact angle, Atomic Force Microscopy(AFM) and Scanning Tunneling Microscopy (STM). We anticipate these monolayers as potential dielectric materials for organic electronics     

Environmental impacts of integrated fisheries development in the Bicol river basin,the Philippines

This article is based on a study conducted from March 15 to August 15, 1983 at the proposed Naga‐Calabanga Integrated Fisheries Development Project in the Bicol region, the Philippines. Baseline studies were conducted on all environmental parameters and impact predictions were made. The Bicol River, the main source of water supply for the proposed fishery estate was found to be polluted in terms of total solids; BOD, phenol, cyanide and bacteria, but these would not be a limiting criteria for fish production since milkfish have a wide tolerance for physical, chemical and biological conditions. The project area was marginal with respect to agricultural activity. Conversion of the site to the proposed fishery project would cause some localized adverse ecological impacts but the net impact would be beneficial and enhance estuarine environment. Some adverse impacts include barriers to migratory fish such as mullet, arid catfish and shrimps, deterioration of water quality downstream, probable increase of vector diseases, destruction of minor agricultural crops and vegetation and change of landform (from terrestrial ecosystems to aquatic ecosystems). Positive impacts include increased fish productivity, job opportunities, revenues, increased wetlands and improvement of health and nutrition. Thus, the aims and purpose of the project shall be achieved without unduly causing much adverse ecological impact on the environment.     

Delineation of Flood-Prone Areas Using Remote Sensing Techniques

Flood problems resulting due to heavy rainfall and drainage congestion are being regularly experienced in plain areas of Bihar, India. Due to this problem, power plant located in Koa catchment, Kahalgaon, Bihar, is faces huge loss at the time of flood. In this paper, the flood-affected areas in Koa catchment have been mapped using remote sensing satellite data (IRS LISS III, 1999 and Landsat TM, 1995). A range of image processing techniques has been used, including simple density slicing, Tasseled Cap Transformation and water-specific index. The results obtained using different approaches have been analysed. Result indicates that a Normalized Difference Water Index (NDWI) based approach produced best results.     

Development of Regional Flood Frequency Relationships Using L-moments for Middle Ganga Plains Subzone 1(f) of India

In this study, screening of the data has been carried out basedon the discordancy measure (D _i) in terms of the L-moments. Homogeneity of the region has been tested using the L-moments based heterogeneity measure, H. For computing the heterogeneity measure H, 500 simulations were carried out using the four parameter Kappa distribution. Based on this test, it has been observed that the data of 8 out of 11 bridge sites constitute ahomogeneous region. Hence, the data of these 8 sites have been used in this study. Catchment areas of these 8 sites vary from 32.89 to 447.76 km² and their mean annual peak floods varyfrom 24.29 to 555.21 m³ s^-1. Comparative regional floodfrequency analysis studies have been carried out using the various L-moments based frequency distributions viz. Extreme value (EV1), General extreme value (GEV), Logistic (LOS), Generalized logistic (GLO), Normal (NOR), Generalized normal (GNO), Uniform (UNF), Pearson Type-III (PE3), Exponential (EXP),Generalized Pareto (GPA), Kappa (KAP), and five parameter Wakeby(WAK). Based on the L-moment ratio diagram and Z _i ^dist –statistic criteria, GEV distribution has been identified as the robust distribution for the study area. For estimation of floods of various return periods for gauged catchments of the study area, regional flood frequency relationship has been developed using the L-moments based GEV distribution. Also, for estimation of floods of desiredreturn periods for ungauged catchments, regional flood frequencyrelationship has been developed by coupling the regional flood frequency relationship with the regional relationship between mean annual maximum peak flood and catchment area.