Sudipta K. Mishra

Bio: Sudipta K. Mishra is an academic researcher from GD Goenka University. The author has contributed to research in topics: Built environment & Time series. The author has an hindex of 2, co-authored 5 publications receiving 24 citations.

Review of Concepts, Tools and Indices for the Assessment of Urban Quality of Life

Abstract: The rapid urban growth poses a huge challenge in sustaining the quality of local environment and life characteristics in contemporary cities. There is a growing body of literature on sustainable cities, QoL, livability; yet a transparent and verifiable knowledge on its assessment at the urban scale is both limited and disparate. Very recently, the use of computational models, tools and indices has seen a sudden upsurge in QoL assessment at the city and sub-city level. This research, through an exhaustive review of scientific and policy literature postulates that despite promulgation of numerous and comprehensive indices and tools, yet these demonstrate a great deal of inconsistency and incomparability. This necessitates an investigation into what ought to be the preferred attributes/features of an ideal model, thereby demanding a systematic, transparent and objective appraisal of urban QoL assessment tools used worldwide. Addressing to the above objective, the research examines peer-reviewed papers to derive eight fundamental study criteria (type of dataset, scope or parameters, sample- coverage and unit, approach, technique, model type, interphase and application) that could typically characterizes such tool. It then reviews scientific and policy literature, open-access webpages on the internet to identify a first of its kind, exhaustive inventory of 26 urban QoL models and then critically evaluates these on the basis of the eight study criteria. The ensuing results bring to the fore a plethora of new, interesting and some inconvenient findings, most importantly that not even a single tool captures all the seven theoretical dimensions of QoL. Despite meant to evaluate quality in cities, only few tools conduct qualitative, subjective, bottom-up, GIS based simulation modeling that could effectively be put to use for more public and policy oriented applications. Lastly, the research demonstrates with credible evidence that a majority of tools/index continue to understand the city as a homogenous entity, with limited know-how on the variability of QoL at the neighbourhood level.

Rainfall Forecasting Using Backpropagation Neural Network

Abstract: Rainfall is an important hydro-climatic variable on which crop productivity, aridness etc. depend. Different time series analysis techniques, e.g. ARIMA, HWES etc. are typically used to predict rainfall. In this paper, authors applied different neural network techniques (ANN) for studying the rainfall time series in Burdwan district of West Bengal, India, by using past 15 years’ data. Then, efficiency of different ANN schemes to predict the rainfall was compared and best scheme was selected. All the calculation works were done using ANN model in MATLAB R2013a.

Image based disaster assessment using fractal dimension

Abstract: It has been proven that geological objects such as mountains, river patterns, green cover distribution, human settlements have the characteristics of fractals Fractals can be used to describe complex geometric shapes which makes them a suitable choice to characterize terrains with convoluted features and irregularity In this paper, simple fractal dimension along with its merits and demerits for fractal characterization are discussed Also, indices of simple fractal dimension of satellite images of areas before and after earthquakes have been compared, in an attempt to give a mathematical representation to the natural phenomenon

Evaluation of QoL in cities of diverse neighbourhood typologies: A scientific study of New Delhi

Abstract: Quality of life (QoL) in urban areas is increasingly finding prominence in practice. There are numerous studies interlinking residential built environment and QoL at the city level but very few at ...

Farmers’ Perception, Adaptation to Groundwater Salinity, and Climate Change Vulnerability: Insights from North India

Abstract: Groundwater salinity, caused by over-extraction and aggravated by climate change, negatively affects crop productivity and threatens global food security. Poor farmers are vulnerable due to low adaptive capacity. A better understanding of their perceptions and adaptation is important to inform policies for successful adaptation. This paper represents an important study by exploring the same in Mewat, a salinity-affected socioeconomically backward district of northern India. The study uses a mixed-method approach with both secondary data and a primary survey of 250 farmers. A large number of farmers perceived negative impacts on water, crop, income, and assets; and adapt in various ways like water management, crop, and land management, livelihood diversification, and shift towards surface water irrigation. Perceived impacts differed between richer and poorer farmers, whereas adaptation measures varied across the educational, social, and economic backgrounds of farmers. Lack of awareness, education, skill development, and livelihood-opportunities are found to be hindrances, whereas institutional and infrastructural support as facilitators of adaptation. Comparing the findings with global experiences we argued that developed countries intervene more in the policy level and infrastructure, whereas in developing countries, adaptation strategies are local, context-specific, and low-cost. The insights from our study will be useful for intervention in Mewat and similar areas across the developing world. We further argue that farmers take adaptation decisions based on perceived impacts and cost-benefit analysis. Therefore, future research work on quantifying the negative impacts and cost-benefit analysis of various adaptation measures will be useful to ensure successful adaptation in the region and beyond.

Analyzing trend and forecasting of rainfall changes in India using non-parametrical and machine learning approaches.

Abstract: This study analyzes and forecasts the long-term Spatio-temporal changes in rainfall using the data from 1901 to 2015 across India at meteorological divisional level. The Pettitt test was employed to detect the abrupt change point in time frame, while the Mann-Kendall (MK) test and Sen's Innovative trend analysis were performed to analyze the rainfall trend. The Artificial Neural Network-Multilayer Perceptron (ANN-MLP) was employed to forecast the upcoming 15 years rainfall across India. We mapped the rainfall trend pattern for whole country by using the geo-statistical technique like Kriging in ArcGIS environment. Results show that the most of the meteorological divisions exhibited significant negative trend of rainfall in annual and seasonal scales, except seven divisions during. Out of 17 divisions, 11 divisions recorded noteworthy rainfall declining trend for the monsoon season at 0.05% significance level, while the insignificant negative trend of rainfall was detected for the winter and pre-monsoon seasons. Furthermore, the significant negative trend (-8.5) was recorded for overall annual rainfall. Based on the findings of change detection, the most probable year of change detection was occurred primarily after 1960 for most of the meteorological stations. The increasing rainfall trend had observed during the period 1901-1950, while a significant decline rainfall was detected after 1951. The rainfall forecast for upcoming 15 years for all the meteorological divisions' also exhibit a significant decline in the rainfall. The results derived from ECMWF ERA5 reanalysis data exhibit that increasing/decreasing precipitation convective rate, elevated low cloud cover and inadequate vertically integrated moisture divergence might have influenced on change of rainfall in India. Findings of the study have some implications in water resources management considering the limited availability of water resources and increase in the future water demand.

Rainfall prediction methodology with binary multilayer perceptron neural networks

Abstract: Precipitation, in short periods of time, is a phenomenon associated with high levels of uncertainty and variability. Given its nature, traditional forecasting techniques are expensive and computationally demanding. This paper presents a soft computing technique to forecast the occurrence of rainfall in short ranges of time by artificial neural networks (ANNs) in accumulated periods from 3 to 7 days for each climatic season, mitigating the necessity of predicting its amount. With this premise it is intended to reduce the variance, rise the bias of data and lower the responsibility of the model acting as a filter for quantitative models by removing subsequent occurrences of zeros values of rainfall which leads to bias the and reduces its performance. The model were developed with time series from ten agriculturally relevant regions in Brazil, these places are the ones with the longest available weather time series and and more deficient in accurate climate predictions, it was available 60 years of daily mean air temperature and accumulated precipitation which were used to estimate the potential evapotranspiration and water balance; these were the variables used as inputs for the ANNs models. The mean accuracy of the model for all the accumulated periods were 78% on summer, 71% on winter 62% on spring and 56% on autumn, it was identified that the effect of continentality, the effect of altitude and the volume of normal precipitation, have an direct impact on the accuracy of the ANNs. The models have peak performance in well defined seasons, but looses its accuracy in transitional seasons and places under influence of macro-climatic and mesoclimatic effects, which indicates that this technique can be used to indicate the eminence of rainfall with some limitations.

Perbandingan Klasifikasi Antara KNN dan Naive Bayes pada Penentuan Status Gunung Berapi dengan K-Fold Cross Validation

Abstract: Penelitian ini akan membandingkan dua algoritma klasifikasi yaitu K-Nearest Neighbour dan Naive Bayes Classifier pada data-data aktivitas status gunung berapi yang ada di Indonesia. Sedangkan untuk validasi data menggunakan k-fold cross validation. Dalam penentuan status gunung berapi pusat vulkanologi dan mitigasi bencana geologi melakukan dengan dua hal yaitu pengamatan visual dan faktor kegempaan. Pada penelitian ini dalam melakukan klasifikasi aktivitas gunung berapi menggunakan faktor kegempaan. Ada 5 kriteria yang digunakan dalam melakukan klasifikasi yaitu empat faktor kegempaan diantaranya gempa vulkanik dangkal, gempa tektonik jauh, gempa vulkanik dalam, gempa hembusan dan ditambah satu kriteria yaitu status sebelumnya. Ada 3 status yang di yang diklasifikasi yaitu normal, waspada dan siaga. Hasil penelitian yang dibagi kedalam 3 fold disetiap metode klasifikasi didapat perbandingan akurasi sistem rata-rata tertinggi pada k-nn 63,68 % dengan standar deviasi 7,47 %. Sedangkan dengan menggunakan naive bayes didapat rata-rata akurasi sebesar 79,71 % dengan standar deviasi 3,55 %. Selain itu, penggunaan naive bayes jaraknya akurasi lebih dekat dibandingan dengan k-nn. Abstract This research will compare two classification algorithms that are K-Nearest Neighbors and Naive Bayes Classifier on data of volcanic status activity in Indonesia. While for data validation use k-fold cross validation. In determining the status of volcanology center volcanology and geological disaster mitigation to do with two things: visual observation and seismic factors. In this research in doing the classification of volcanic activity using earthquake factor. There are 5 criteria used in the classification of four seismic factors such as shallow volcanic earthquakes, distant tectonic earthquakes, volcanic earthquakes in the earthquake, blast and plus one criterion that is the previous status. There are 3 statuses in which are classified ie normal, alert and alert. The results of the study are divided into 3 fold in each classification method obtained comparison of the highest average system accuracy at 63.68% k -nn with a standard deviation of 7.47%. While using naive bayes obtained an average accuracy of 79. 7 1% with a standard deviation of 3.55%. In addition, the use of naive bayes is closer to the accuracy of k-nn .

Addressing the covid-19 crisis by harnessing internet of things sensors and machine learning algorithms in data-driven smart sustainable cities

Abstract: This paper analyzes the outcomes of an exploratory review of the current research on data-driven smart sustainable cities The data used for this study was obtained and replicated from previous research conducted by Capgemini, ICMA, KPMG, UNESCAP, UNHSP, SCC, The University of Adelaide, and The World Bank We performed analyses and made estimates regarding Internet of Things sensors and machine learning algorithms Data collected from 5,200 respondents are tested against the research model by using structural equation modeling © 2020, Addleton Academic Publishers All rights reserved