Novel Approach for Spatiotemporal Weather Data Analysis

Journal of Scientific Research

Rainfall and temperature are two key factors to examine while assessing climate change. Bangladesh has witnessed extremes in rainfall and temperature during the previous few decades, affecting both the environment and the agricultural economy. In this study, the ARIMA model is used to predict and forecast rainfall and temperature in Chattogram, Bangladesh from 1953 to 2070 considering seasonal variations. Analyzed data indicated a substantial to a fairly significant upward trend in December, with a slight increase in rainfall between years 2021-2050 and 2050-2070. Rainfall reflects a more dominant rising trend in later parts of the selected four-time series, indicating more rainfall during the Monsoon season. Temperature follows an upward trend with time, the most significant positive trend occurring between 2021 and 2050, and a large negative trend occurring between 2050 and 2070. In the years 2021-2050, the yearly average temperature is expected to drop during the Rabi season. In ...

TEST Engineering & Management, 2020

Meteorological data is generated on day to day basis through various techniques. Hadoop distributed file system is used to handle such a rapid growth of data by storing data in distributed system. There are many architecture exist which uses Hive and pig query tools to extract data from HDFS and then apply Mapreduce for analyzing data. Apache spark is also used for faster analysis. To further improve time efficiency for large datasets, data mining algorithms are also used in distributed manner. All work has been done on traditional framework with the lack of any user interface and effective visualization. We will propose a framework which is more efficient to handle meteorological data with user interface and effective visualization.

Big data has described an enormous quantity of data which needs new technologies to make potential to obtain value from it by analysis and capturing method. Data Analytics often includes scrutinizing past traditional data to research potential trends. Weather prognostication has been one of the most fascinating and exciting domain, and it performs an essential role in aerography. The weather situation is the state of the atmosphere at a given time regarding weather variables like wind direction, rainfall, cloud conditions, pressure, temperature, thunderstorm, etc. The Big data obtained by NCDC (National Climatic Data Center) has received over more than 116 weather locations and more than 1000 observations centers. The data produced by them is unstructured which grows a challenging job to explain it. In this paper, these enormous amounts of data have loaded onto the Apache Pig, Hadoop Distributed File System, Apache Hive is to process the data, which utilizes mappers and reducers to process the data. The above dataset has explained by using given methods and the final output of this project in the form of maximum, minimum and average temperature according to the given time and date.

Hadoop an apache product which is an open-source, Java based programming framework is used to support large data sets in a distributed environment. Hadoop has maximum advantage over scalable and fault-tolerant distributed processing technologies. Also,(HDFS)Hadoop Distributed File System is highly fault tolerant and used for applications that have large data sets. Hence HDFS file system using name node, data node and task tracker will perform distribution of job in Hadoop environment .Since Hadoop has overwhelming advantage in optimizing big data , we prefer to use Hadoop to analyze large datasets of weather processing.

2018

Big data Analytics is used in the study of developing forecasting models for prediction of runoff in Narmada river basin. Big data and data mining used as an advanced technique for storing and managing the large data set of runoff. Hadoop technique is used for storing and processing the large data. A new concept of big data processing is known as MapReduce it is a programming model. MapReduce is emerging as an important programming model for large-scale data-parallel applications such as web indexing, data mining, and scientific simulation. Autoregressive Integrated Moving Average (ARIMA) modelling is used for the prediction of time series runoff. Historical runoff data, which is large in size is stored in big database. The main objective of the time series modelling is to carefully collect and rigorously study the past observation of time series and to develop an appropriate model that predict the future runoff in hydrological time series.

International Journal of Advanced Research in Computer Science, 2018

IJCSMC, 2019

Weather is the most critical for human in many aspects of life. The study and knowledge of how weather Temperature evolves over time in some location or country in the world can be beneficial for several purposes. Processing, Collecting and storing of huge amounts of weather data is necessary for accurate prediction of weather. Meteorological departments use different types of sensors such as temperature, humidity etc. to get the data. The sensors volume and velocity of data in each of the sensor make the data processing time consuming and complex. This project aims to build analytical Big Data prediction framework for weather temperature based on MapReduce algorithm. Information Mining Package, can perform administered grouping methodology on immense measures of information, normally alluded as large information, on a conveyed framework utilizing Hadoop MapReduce. The instrument has arrangement calculations actualized, taken from Support Vector Machines (SVM). The aftereffects of an exploratory examination utilizing a SVM classifier on informational collections of various sizes for various bunch designs like K-Means shows the capability of the apparatus, just as perspectives that influence its execution.

2019

Meteorological data is required to evaluate the long term effect of proposed man made hydrological changes. Such evaluations are often hydrologic processes which use weather data as input. The meteorological variables required for most of hydrologic models includes precipitation it is essential to have a sufficient long historic data to achieve an operating mathematical rule. Records which consist of short term data are not suitable for proper planning and arrangement processes and also available of a location of interest. in such circumstances, it become necessary to deterministic as well as stochastic component, but stochastic time series models, such as autoregressive (AR), moving average(MA) autoregressive and moving average (ARMA) are widely used to developed and generate the rainfall and temperature. They apply Seasonal ARIMA models that counted for 92% of the total variability in the monthly means of air temperature. Their forecasted values showed good agreement with the actu...

AIP Conference Proceedings, 2022

The rainfall data analysis and its timely prediction is very important for agricultural practices planning. In case of heavy/scanty rainfall prediction, early forecasting helps to plan for disaster management in areas of high risk. In this article, time series analysis of rainfall for the state of Odisha is carried out. Odisha is a state which is constantly being hit by waves of droughts, floods and cyclones. Thus, it becomes extremely important to analyze and forecast for rainfall in this region so that proper measures to avert disasters can be undertaken. For time series modeling, rainfall data for last 50 years has been analyzed using Auto-Regressive Integrated Moving Average (ARIMA) method. Several suitable ARIMA models are identified based on significant parameters. The variability in prediction and actual provides for the consistency of model. The months of highest and lowest precipitation have been identified. Later on the efforts to identify regions in Odisha for scanty and heavy rainfall has been made and predictions are made for 10 years into the future time period. It can be seen that accurate predictions help for crop planning and adopting better agronomic practices for crops, proper disaster management in risk zones and providing timely relief to those in affected areas.

International journal of engineering research and technology, 2018

Rainfall is important for food production plan, water resource management. India is an agricultural country and its economy is largely based upon productivity. Thus rainfall prediction becomes a significant factor in agricultural countries like India. On the growing importance of Rainfall studies in the climate change scenario and High Performance Computing, different Users starting from a farmer to a scientist to a policy maker needs the rainfall prediction well in advance for their application like crop planning, water storage etc. Data discovery from temporal, spatial and spatiotemporal data is critical for rainfall analysis. However, recent growth in observations and model outputs, combined with the increased availability of geographical data, presents new opportunities for the users to implement new techniques such as predictive analytics for developing a predictor which can be used for multi-scale forecasting of rainfall that is from 24 hour forecast to long-range forecast say...