Surface temperature is one of the first ocean variables investigated. Ocean temperature is a key indicator of global climate
change. The anomalies in ocean temperature have caused significant deterioration of marine systems. Existing works on
surface temperature anomaly considered a suite of other remote sensing measurements such as wave height, salinity and
models such as support vector machine, self-organizing maps and convolutional neural networks. Neural networks are used
for predicting the surface temperature. This paper proposes use of long short-term memory, a recurrent neural network
method to the estimate sea surface temperature anomalies based on previous year?s sea surface temperature anomalies.
NOAA OI SST V2 dataset with 40 years of data is used in the experimentation. Auto-regression is used during data
preprocessing. The basic LSTM method with 3 blocks of size 2 is enhanced to 50 neurons. This proposed LSTM model has
been assessed for performance on time series data, yearly wise and for the entire dataset and found that the model has been
able to predict the anomalies with a reasonably good precision. The model produced error of 0.036 indicating that the
model is feasible for predicting the temperature anomaly and mean absolute error of 0.14 on the testing data.
Paper No
2
Publication ID : 776 & Year : 2020
Title
Testing purpose only
Authors
SP
Source
Test
Abstract
TestTest
Paper No
3
Publication ID : 763 & Year : 2017
Title
Development of a WebGIS Application for IIOE-2
Endorsed Projects
Authors
N. Kiran Kumar, S. P. Vighneshwar, J. Ramanjaneyulu, L. Sushmitha
Source
The Indian Ocean Bubble 2, Issue no 7, August 2017.
Abstract
Designed to better serve the end-users, the INCOIS Web Team has recently developed
a new WebGIS application for the scientific projects endorsed under IIOE-2 (http://
www.iioe-2.incois.gov.in/IIOE-2/Endorsed_Projects.jsp).
Paper No
4
Publication ID : 414 & Year : 2017
Title
PSNM: An Algorithm for Detecting Duplicates in Oceanographic Data
Authors
L. Srinivasa Reddy, S. P. Vighneshwar, B. Ravikiran
Source
Computer Communication, Networking and Internet Security. Springer, Singapore, 2017. 291-297.
Abstract
This work discusses a new method of identifying duplicates in surface meteorology data using PSNM (Progressive Sorted Neighborhood Method) Algorithm. Duplicate detection is the process of identifying the same representations of the real world entities in the data. This method needs to process a large amount of ocean data sets in shorter time. PSNM algorithm increases the efficiency of finding duplicates with lesser execution time and get the efficient results much earlier than traditional approaches. It is observed that all possible duplicates associated with the data can be identified using this method, and also this work proposes a new way to access the resulted (Duplicate eliminated) data using authorization restrictions based on the type of user and their need with different file conversion formats.
Time Series Analysis of Oceanographic Data Using Clustering Algorithms
Authors
D. J. Santosh Kumar, S. P. Vighneshwar, Tusar Kanti Mishra, Satya V. Jampana
Source
Computer Communication, Networking and Internet Security. Springer, Singapore, 2017. 245-252.
Abstract
With the availability of huge data sets in device fields like finances to weather, it becomes very important to quality analysis and interprets the results. In such scenario K-Means and DBSCAN clustering algorithms are used for effective data grouping to get insight into the hidden structure in the data. In this paper focus on the application of clustering to ocean data observations. An attempt is made to correlate the resulting clusters to the variability focused during cyclones.
In Situ Data Assessment: An Offline Tool for
viewing Argo Data and Data Products
Authors
Vighneshwar S P, Keerthi Lingam, Mercy Monica Marisarla
Source
International Journal of Advanced Research in Computer and Communication Engineering
ISO 3297:2007 Certified
Vol. 6, Issue 12, December 2017
Abstract
In this paper, we focus on implementation of research, and the efficient management of resulting Indian
ocean data. Data management and integration consider the careful collection, management and dissemination of
research data is taken to provide vast ocean information integration. In order to develop robust ocean information
system, the data from in-situ ocean observing systems such as Argo floats, drifting buoys, moored buoys, XBT surveys,
tide gauges, coastal radars, current meter mooring array, bottom pressure recorders has been considered to design by
implementing data acquisition, processing, quality control, and database generation. The diverse data sets has been
acquired from in-situ platforms needs to be quality controlled, organized and disseminated in real time to data users.
This paper on ODIS provides ocean data management and web-based ocean information system and its visualization
functions for oceanographic data. An integrated observing system will also require improved combination of data from
in-situ platforms which observations depends on their parameters and data types.
