Название: Geospatial Data Analytics and Urban Applications
Автор: Sandeep Narayan Kundu
Издательство: Springer
Год: 2022
Страниц: 197
Язык: английский
Формат: pdf (true)
Размер: 10.0 MB

This book highlights advanced applications of geospatial data analytics to address real-world issues in urban society. With a connected world, we are generating spatial at unprecedented rates which can be harnessed for insightful analytics which define the way we analyze past events and define the future directions. This book is an anthology of applications of spatial data and analytics performed on them for gaining insights which can be used for problem solving in an urban setting. Each chapter is contributed by spatially aware data scientists in the making who present spatial perspectives drawn on spatial Big Data. The book shall benefit mature researchers and student alike to discourse a variety of urban applications which display the use of Machine Learning algorithms on spatial Big Data for real-world problem solving.

In today’s digital world, human activities are more interconnected and impact the way we use our limited resources. In dense urban setups, it is more imperative that resource utilization is optimized, and sustainable. Conventional paradigms have limitations in connecting the missing links between the cascading effects of unsustainable means of resource utilization. As more and more data are being recorded for every activity and made publicly available for data scientists, insights can now be drawn with multiple perspectives to identify patterns and trends. However, there are several challenges. The first one is the selection of the right dataset from the myriad volume of Big Data available to us today. Next challenge is the selection of the right algorithm on which the analytics are to be founded on top of this data. The final challenge lies in the interpretation of the results and this defines the insights and the actions to be taken by authorities for solving problems. These three challenges constitute the essential components of a discipline which is now known as Data Science.