Cognitive Computational Approaches for Weather Forecasting: An

Overview and Progress

Kaushlendra Yadav, Arvind Kumar Tiwari

Kamla Nehru Institute of Technology, Sultanpur, Uttar Pradesh

Department of Computer Science & Engineering

Keywords: Cognitive

computing (CC), ISMR (Indian Summer Monsoon Rainfall), numerical weather

prediction (NWP), Big Data Assimilation (BDA), Deep Learning (DL). ARIMA (Auto-

Regressive Integrated Moving Average) Model.

Abstract: From the beginning human always willing to predict the things accurately so that he can be ready for the

consequences of things in advance. Prediction of weather is one of the few tasks that drastically affect

human life. Weather forecasting is an effort to find out the expected weather conditions in advance

(Kothapalli, 2018). In this paper, A Real-time weather forecasting and analysis has been done using the

parameters temperature and humidity. Here correlation analysis is used as a key for prediction in an ARIMA

(Auto-Regressive Integrated Moving Average) Model. In the past, we have seen old physical prediction

models that were not much appropriate for the forecast due to the random nature of weather over a long

period. In the current scenario, we see Techniques like Machine learning, IoT, ANN are more robust in

prediction with more accurately and for a longer period. But these things are limited to machines, we want

to make a more advancement by making machine think like a human So that natural intelligence of human

can govern over the machine and we go for prediction in a much realistic way. We can determine new class

of problems using Cognitive computing (CC). it deals with complex problems same way as human tackle

the unknown problems (Sarma, 2016). The purpose of this paper is to analyze weather forecasting using

different computing techniques and design a more efficient prediction model using cognitive computing.

INTRODUCTION

The weather forecasting is a task in which human

indulge themselves from the beginning either

scientifically or verbally but accurate weather

prediction always being a challenging task for them

due to the variable nature of weather affecting

parameters that change very frequently, it may

include wind speed, sea surface temperature,

atmospheric pressure, etc.

In the past when people don’t have the luxury of

today’s modern technology they were used to predict

the weather using relative phenomena like if its

cloudy” it will rain” or may be its already raining

nearby. They simply try to understand the behavior

of nature from things like wind, sky, moon, clouds,

aroma of air etc. (Refonaa, 2018) In this paper, the

author stated that cognitive computing techniques

give better results compared to statistical techniques.

The ever-changing nature of the atmosphere expects

a high and refined computation to arrive at accurate

results. It turns out to be an indispensable activity

nowadays as most sectors including agriculture,

industries, aviation, etc. are getting highly reliant

upon it. (Goswami, 2014). In this paper, the author

used a REGCM (Regional Climate Model) open-

source Model for predicting the weather parameters

as a dynamic prediction.

We can say that Cognitive computing techniques

can be used to generate solutions for “vague,

ambiguous, qualitative, incomplete, or imprecise

information. This technique also yields a lower

percentage of error in prediction rate. And also it is

more appropriate for subjective and qualitative data.

Cognitive computing studies the development of

self-study programs that naturally interact with

people in complex and adaptable contexts and

changes in language and meaning. These programs

mimic the processes of the human mind, define a

large number of details, discover complexity, test

ideas, make predictions and clues, come to

conclusions, and so on. This is a field of emerging

140

Yadav, K. and Tiwari, A.

Cognitive Computational Approaches for Weather Forecasting: An Overview and Progress.

DOI: 10.5220/0010564200003161

In Proceedings of the 3rd International Conference on Advanced Computing and Software Engineering (ICACSE 2021), pages 140-146

ISBN: 978-989-758-544-9

multidisciplinary research, the backbone of artificial

intelligence, integrating and entertaining scientific

results from a variety of fields, such as natural

language analysis, information representation and

consultation, audio and video analysis, neuroscience,

computer-human communication.

COGNITIVE COMPUTATIONAL

APPROACHES

In Cognitive computing we try to mimic the human

way of thinking for finding the solutions of complex

ambiguous scenarios. When we are not certain about

the events, then we try to solve things by our own

vision. This thing we can see in IBM’s cognitive

computer system, known as Watson. In this

Technique we see lower chances of prediction error

and produces a better qualitative and subjective data.

2.1

Theory of Cognitive Computing

This paper describes how can we process

information after learning. We can say that learner

has to become an active member in the process.

Learner has to use his skills, wisdom, consciousness,

clues that they have accomplished prior. It is

necessary that learner build his forgiving while

going through different situations on behalf of his

prior experience and intelligence.

2.2

Learner-centered Approach

Learning is a process that depends upon the capacity

of individuals, when we read anything then we relate

this with our existing knowledge data base and try to

figure out the outcome based upon the reasoning.

We can see this cognitive learning approach

while teaching students. Here location, information

and Balance are key parameters for learning

• Housing - We see the transformation from what we

already know to what we are looking for new.

Information – how new details are arranged in our

heads next to what we already know.

• Balance – here we see the balance between what

we already know and what we are learning now

According to Piaget, learning is an association

between the information we already know with new

information. For this we have to create a safe

learning environment. It is a place where inquiring

mind is supported and forbearing is accepted. It is

very important to know how to plan a course or

stream for learning and growth.

• We have to create a fresh insertion of record on the

existing information

• Study stuff should be branched into correct parts

and should follow a sequence.

• Thoughts of interns should be taken seriously and

their suggestions should be implemented.

2.3

Data Mining Technique

Prediction of weather can be taken by many Data

Mining techniques, Clustering, Decision Trees and

Neural Networks are few of them.

This method is based on the hidden patterns and

relations among them and validate our results by

verification on the input parameters.

Data Mining includes following stages -

1. Assemblage of Data

2. Purification of Data

3. Selection of Data

4. Conversion of Data

5. Tapping of Data

2.4

Fuzzy Logic Technique

Fuzzy logic deals with the sectional truth where

truth vale may differ from completely false to

completely truth. We can say Fuzzy logic find the

degree of truth. It is resemblance to human

reasoning. It is applicable when values are between

absolute true and false. Here we see a membership

function that tells how a variable relates with a Set

to the interval [0,1]

2.5

Genetic Algorithm Technique

It is a heuristic Search Technique and is based on

Darwin’s theory of evolution. It is a searching

process in which most powerful individual are

selected and fittest individual get chance of

reproduction to generate the candidate for upcoming

generation. We can see a famous way to train Neural

Networks is hybrid backpropagation using genetic

algorithm. The shortcoming of this method is that

we assume that weather parameters are not

correlated with each other, so we can’t get the

benefit of correlation analysis. To eliminate this few

authors proposed a modified time series based

weather prediction.

Cognitive Computational Approaches for Weather Forecasting: An Overview and Progress

141

2.6

Deep Learning Technique

Mostly people are confused among Artificial

Intelligence, Machine learning and Deep learning. In

Artificial Intelligence we try to simulate human

inelegancy in machines, that includes all human way

of thinking and working. Machine learning can be

considered as a subset of Artificial Intelligence that

can be used for prediction without explicitly

programmed. It uses past data for prediction.

Machine learning is not much useful when we go for

fields like natural language processing or image

processing that includes a large number of

parameters needed for prediction.

Deep Learning is a subset of Machine Learning

Where we see multiple hidden layers. Deep Learning

can deal with multiple predictors while prediction.

Deep Learning can generate new prediction

predictors besides the input parameters. It is effective

when we have large amount data to deal with.

Deep learning is a subset of machine learning in

artificial intelligence that has networks capable of

learning unsupervised from data that is unstructured

or unlabeled. Also known as deep neural learning or

deep neural network. The objective of our

investigations is to explore the potential of deep

learning techniques for weather forecasting using

rich hierarchical weather representations which are

learned from massive weather time series data.

RELATED WORK

We have seen so many weather prediction models in

the past and also see comparative study among the

models for analyzing the performance. (Saima,

2011) In this paper, the author has done a review on

intelligent methods for weather forecasting and

concludes that no existing model is perfect by which

we can predict the weather conditions accurately.

In paper (Echevarría, 2011) Author has described

rainfall prediction through deep learning. Here

Prediction of next day has been done on the basis of

previous day data. The data used for prediction

contains 47 parameters containing temperature,

humidity, wind speed etc. We see author has used a

deep learning based forecasting model. Author

claims better result on behalf of MSE and RMSE.

Heavy Rain conditions are used for testing and

forecasting of light rain is considered as a future

work. Deep Belief Network based on Restricted

Boltz-Mann Machines setup has been used by

analyzing neighboring geographic proximity and

altitude.

In paper (Miyoshi, 2016) Author has shown how

Big Data Assimilation with next generation sensors

and high end computing can improve the numerical

weather prediction. As BDA updates the system

every 30 seconds and with 100-m resolution it can

do precise prediction. In paper (Jain, 2017) Author

has presented how time series data is key component

in prediction of weather.

In paper (Ghosh, 2016)) topic of Fuzzy Logic as

a decision making technique has been introduced. It

was suggested that applications of this technique

could be effectively applied in the area of

operational meteorology. An instance of such an

application, the forecast of the probability of

temperature, was discussed and examples of the

method were presented.

In paper (Vaščák, 2015) Author presented a

compact weather prediction system basically for

industry need that can be used for other fields,

mainly in weather research, transport and firewall

system etc. In paper (Navadia, 2017) Author used

Hadoop based prediction analysis of weather.

Proposed system takes large rainfall data as input

and went for prediction on behalf of day, quantity

etc. to predict accurately. Predictable types of

analysis hold relationship between multiple items in

a risk assessment data set with specific set of criteria

for allocation of points on weight. In paper (Babu,

2017) Author prepared a Wi-Fi based set up for

prediction. It is tried to cut the cost using light part

in terms of cost. In paper (Chen, 2018) Author has

discussed Cognitive Computing while aiming on

three terms, i.e., IoT, big data and cloud computing.

In paper (Abrahamsen, 2018) Author predicted

the temperature using ANN and mainly describe

Python API for data collection. It was explained that

how this data can be used in Machine Learning. In

paper ( Mohammadi, 2015) Author did a survey on

features of IoT Data and difficulty for Deep

Learning Method. We saw several Deep Learning

model based on two main features-IoT Big Data and

IoT Fast Streaming data. In paper (Kunjumon,2018)

Author mentioned different data mining algorithms

for the prediction of weather and concluded that

Support Vector Machines can give batter result with

almost 90% accuracy. In paper (Huang, 2019)

Author describe show in recent years, computer

technology for understanding has grown with

maturity, and programs such as in-depth learning has

provide great performance. It is about designing and

implementing a comprehension model that focuses

on the similarity of sentence questionnaires for

individual Institutions. In paper (Scher, 2019)

Author presented the broadcasting model for

ICACSE 2021 - International Conference on Advanced Computing and Software Engineering

142

training the Deep Neural Networks. This Model

produces few days ahead forecasting results. Author

also give thought about how neural network model

is dependent on the timing of training period and

concluded that a seasonal cycle is more effective

compare to the model that having outside of the

season cycle.

In paper (Zantalis, 2019) Author Described how

things vary with the growth of the Internet of Things

(IoT), apps have become more sophisticated and

connected devices are starting to exploit all aspects

of the modern city. We see if we use large set of data

collection, Machine Learning (ML) techniques are

used to further ingenuity and strength of the

application. The field of intelligent transport has

impressed many researchers and has influenced both

the ML and the IoT. In this case, smart transport is

considered to be an umbrella term that includes

route design, parking, traffic lights,

prevention/detection, road maintenance, and the use

of infrastructure. Here Author mainly focuses on

Machine Learning Algorithms and IoT System for

Intelligent transportation system. In paper

(Samsonovich, 2020) Author used eBICA based

structure to simulate emotional and social

intelligence of human. A brief review was done on

making a virtual assistant that will act as a partner of

human in day to day life.

In paper (Krishnaveni, 2020) Author tried to

predict weather using Big Data Analytics. SPRINT

Algorithm has been used for prediction on WEKA

climate Data. Decision tree based approach has been

used for constructing the tree model. In paper

(Holmstrom, 2016) Author presented the application

of Machine Learning for a large period of prediction,

that gives better results over a shorter period of time.

In paper (Bhardwaj, 2019) Author did temperature

prediction and found that Support Vector Machine

gave best result for this compare to other

approaches. He also concluded that for the rainfall

prediction best model was Multi-Layer perceptron.

In paper (Janani,2014) Author Nearly compared

about 10 papers with their problem, and conclude

that Fuzzy Logic and ANN provide better result

compare to others. In paper (Navadia, 2017) Author

did rainfall prediction using HADOOP and predict

min, max and average rainfall in effective way. In

paper (Omary, 2012) Author used Data Mining

Techniques and Artificial Intelligence for upcoming

precipitation based on past data. As climate changes

very often, Statical approaches and Data Mining was

used for better results.

In paper (Vamsi, 2015) Author used ARIMA

Model for weather forecasting that has the quality of

doing appropriate analysis of weather forecasting. In

paper (Reddy, 2017) Author mainly discussed the

various weather predictions models proposed by

different researchers. In paper (Gurung, 2017) A

survey has been done on weather forecasting using

different ANN Architecture of 20 to 30 years. In

paper (Culclasure, 2013) Author discovered the

recent implication of ANN on weather prediction

over a custom Data. In paper (Priya, 2015) Author

told the benefits of Big Data Analytic for weather

prediction. In paper (Kapoor, 2013) Author used a

Sliding Window concept for prediction and this gave

best result except the months where changes take

place very frequently.

In paper (Kumar, 2013) Author effectively

predict maximum and minimum temperature using

ANN and simulation is done using MATLAB. In

paper (Olaiya, 2012) Author forecasted maximum

temperature, rainfall evaporation and wind speed

using ANN and Decision Tree for the city of

Nigeria. In paper (Karunakara, 2019) Author did

weather forecasting on large satellite data and

propose Cumulative Distribution Function (CDA)

for analyzing the complicated weather prediction.

This gives better result in varying climate. In paper

(Muqeem, 2016) Author did a Survey on different

data mining techniques and review these in tabular

format. In paper (Samya, 2016) The main purpose

was to explore various cloudburst forecasting

strategies using Data Mining and Artificial Neural

Network (ANN), in the literature. The most widely

used parameters for analyzing cloudburst forecasts:

temperature, rainfall, evaporation, and wind speed.

From research, know that prediction using big data

analytics is the best solution for obtaining accurate

cloudburst predictions.

In paper (Yonekura, 2019) Author did a short

term prediction on data provided by the network of

private companies. Different Sensors has been used

for collecting the data. In paper (Sheikh, 2016)

discussion was done on various strategies and

algorithms that can be selected to predict the weather

and sheds much light on effective prediction.

Various other integration techniques are used to

maximize application performance. Findings: After

comparing algorithms and the respective integration

process used to maximize performance, a distinction

is attained that will further predict the weather.

In paper (Madan, 2018) Authors have a practice

of checking the continuous decline of the

mathematical line and supporting vector machine

learning strategies that statistical team details of the

groups are consistent and symbolize weather

forecasts or forecasts. Under the proposed system

Cognitive Computational Approaches for Weather Forecasting: An Overview and Progress

143

we tend to focus on the unpopular algorithmic law

that provides close and imminent weather

forecasting results for the next 5 days and finally,

the results are calculated from the mathematical

decision-making tree view and the terms and

conditions vide confusion matrix for accurate and

accurate prediction using Big Data. In paper (Taib,

2015) two data mining techniques Classification and

Clustering has been discussed on time series data.

These can be prepared using feature based and

instance based. In paper (Kalaiyarasi, 2013)

prediction was done on most common parameters

like rainfall, wind speed, temperature, and cold etc.

using various Data Mining Techniques.

In paper (Lee, 2020) Author used 3 kind of

neural networks, multiple layer perceptron,

repetitive, and convolutional, in predicting daily

measurement, magnitude, and magnitude having

input parameters that are higher in frequency than

the investigators used in past. To incorporate this

neural network into visual data from three locations

with different weather features, the authors present

that predicting result with standard input data is

better than predicting the result of non-standard

daily input. In paper (Hewage, 2020) Authors

proposed a low-cost unpredictable weather

forecasting model by examining short-term memory

modeling methods (LSTM) and temporal

convolutional (TCN) networks and comparing their

result with recent machine learning methods,

mathematical prediction methods, and a powerful

integration method, and a well-established climate

study and forecast (WRF) NWP model. In paper

(Haupt, 2018) Author discussed about many

emerging weather forecasting applications that best

combines our knowledge of physics, numbers, and

non-personal intelligence using smart Big Data and

using the Internet of Things. In paper (Jain, 2020)

Author suggested a method of crop selection to

increase crop yields depending on climatic and soil

parameters. It also shows the right time to plant the

right plants used to predict the weather of the year.

Mechanical learning algorithms such as the

Recurrent Neural Network is used to forecast the

weather, and the random forest planning algorithm is

used to select the appropriate plants. The result of

the proposed weather forecasting method is

compared to standard installation networks, which

show better performance results for each selected

weather parameter.

In paper (Lee, 2004) Authors suggested a smart,

intelligent environment based on multiple elements,

namely the intelligent Java Agent Development

Environment (jade), to provide an integrated and

intelligent platform-based e-commerce platform.

In paper (Wibisono, 2018) weather prediction

was made using a new Artificial Intelligence

technique called the Knowledge Growing System.

The Knowledge Growing System uses weather

forecasting methods as the behalf for weather

forecasts. The result shows that decision-making is

necessary when considering OM-A3S predictions

and learning from A3S to obtain good predictive

results.

In paper (Tajane, 2018) Author discussed how a

chat-bot can be helpful in giving good results in a

variety of situations. This uses features of life -

saving messages as Google (Google Assistant),

Amazon (Alexa), Microsoft (Cortana), and Oracle

use a lot of energy and money to research their

clients. In paper (Muthurasu, 2018) Author provided

an idea of how you can get more information from

accurate agricultural data using a large data method.

Large data sets on agricultural systems provide new

insights into advancing advanced climate decisions,

improving productivity, and avoiding unnecessary

costs associated with harvesting, pesticide use, and

fertilizer.

In paper (Shivaranjani, 2016) Author did a

Survey on various Data Mining approaches that he

used for prediction. The aim was to help farmers by

doing precise weather forecasting so that they

nourish the soil and go for worthy production.

Author used Techniques like ANN, Fuzzy Inference

Systems, Decision Tree Methods to achieve this.

RECOMMENDATION AND

OBSERVATION

It is observed that traditional methods are not

sufficient for effective weather prediction as they

have certain limitations or we can say that is purely

based upon the previous data and finding the

patterns based on the given data, nowadays we need

a more advance way of prediction that not only use

the computation ability of a machine but also use

analysis power of human. So Cognitive Computing

will be an effective solution to handle weather

conditions that change very frequently. So it is

recommended that we build a system that has

thinking capabilities like a human and work

efficiently like a machine.

ICACSE 2021 - International Conference on Advanced Computing and Software Engineering

144

CONCLUSIONS

From the above review, It can be concluded that for

accurate prediction of weather we can’t fully rely on

a statistical method of prediction .if we have to

increase the accuracy then we have to use our

cognitive computing methods because these

cognitive methods not only find the result for

provided predictors but these are also able to self-

generate new predictors that will help us in

predicting complex fields where we see a large

number of attributes i.e. Image Processing, Natural

Language Processing Weather Forecasting, etc.

REFERENCES

A. Culclasure, “Using Neural Networks to Provide Local

Weather Forecasts,” Electron. Theses Diss., 2013.

A. Omary, A. Wedyan, A. Zghoul, A. Banihani, and I.

Alsmadi, “An interactive predictive system for

weather forecasting,” IEEE CITS 2012 - 2012 Int.

Conf. Comput. Inf. Telecommun. Syst., 2012.

A. R. Gurung, “Forecasting Weather System Using

Artificial Neural Network (ANN): A Survey Paper,”

pp. 42–50, 2017.

A. V. Samsonovich, “Socially emotional brain-inspired

cognitive architecture framework for artificial

intelligence,” Cogn. Syst. Res., vol. 60, pp. 57–76,

2020.

C. Kunjumon, S. S. Nair, S. Deepa Rajan, L. Padma

Suresh, and S. L. Preetha, “Survey on Weather

Forecasting Using Data Mining,” Proc. IEEE Conf.

Emerg. Devices Smart Syst. ICEDSS 2018, no. March,

pp. 262–264, 2018.

E. Abrahamsen, O. M. Brastein, and B. Lie, “Machine

Learning in Python for Weather Forecast based on

Freely Available Weather Data,” Proc. 59th Conf.

simulation Model. (SIMS 59), 26-28 Sept. 2018, Oslo

Metrop. Univ. Norw., vol. 153, no. September, pp.

169–176, 2018.

F. Olaiya and A. B. Adeyemo, “Application of Data

Mining Techniques in Weather Prediction and Climate

Change Studies,” Int. J. Inf. Eng. Electron. Bus., vol.

4, no. 1, pp. 51–59, 2012.

F. Sheikh, S. Karthick, D. Malathi, J. S. Sudarsan, and C.

Arun, “Analysis of data mining techniques for weather

prediction,” Indian J. Sci. Technol., vol. 9, no. 38,

2016.

F. Zantalis, G. Koulouras, S. Karabetsos, and D. Kandris,

“A review of machine learning and IoT in smart

transportation,” Futur. Internet, vol. 11, no. 4, pp. 1–

23, 2019.

G. Jain and B. Mallick, “A Review on Weather

Forecasting Techniques,” Ijarcce, vol. 5, no. 12, pp.

177–180, 2017.

G. VamsiKrishna, “An Integrated Approach for Weather

Forecasting based on Data Mining and Forecasting

Analysis,” Int. J. Comput. Appl., vol. 120, no. 11, pp.

26–29, 2015.

H. Saima, J. Jaafar, S. Belhaouari, and T. A. Jillani,

“Intelligent methods for weather forecasting: A

review,” 2011 Natl. Postgrad. Conf. - Energy Sustain.

Explore. Innov. Minds, NPC 2011, pp. 1–5, 2011.

J. Goswami, “Dynamic Modeling Technique for Weather

Prediction,” vol. 5, no. 05, pp. 524–531, 2014.

J. Refonaa and M. Lakshmi, “Cognitive computing

techniques based rainfall prediction - A study,” 6th Int.

Conf. Comput. Power, Energy, Inf. Commun.

ICCPEIC 2017, vol. 2018-Janua, pp. 142–144, 2018.

J. Vaščák, R. Jakša, J. Koščák, and J. Adamčák, “Local

weather prediction system for a heating plant using

cognitive approaches,” Comput. Ind., vol. 74, 2015.

K. J. Sarma, “Prospects of Cognitive Computing

Research,” Int. J. Sci. Eng. Technol. Res., vol. 5, no. 2,

pp. 552–562, 2016.

K. Tajane, S. Dave, P. Jahagirdar, A. Ghadge, and A.

Musale, “AI Based Chat-Bot Using Azure Cognitive

Services,” Proc. - 2018 4th Int. Conf. Comput.

Commun. Control Autom. ICCUBEA 2018, pp. 1–4,

2018.

K. V. Babu, K. A. Reddy, C. M. Vidhyapathi, and B.

Karthikeyan, “Weather forecasting using Raspberry Pi

with Internet of Things (IoT),” ARPN J. Eng. Appl.

Sci., vol. 12, no. 17, pp. 5129–5134, 2017.

K. Yonekura, H. Hattori, and T. Suzuki, “Short-term local

weather forecast using dense weather station by deep

neural network,” Proc. - 2018 IEEE Int. Conf. Big

Data, Big Data 2018, pp. 1683–1690, 2019.

M. Chen, F. Herrera, and K. Hwang, “Cognitive

Computing: Human-Centered Computing with

Cognitive Intelligence on Clouds,” IEEE Access, vol.

6, pp. 1–1, 2018.

M. Holmstrom, D. Liu, and C. Vo, “Machine Learning

Applied to Weather Forecasting,” Meteorol. Appl., p.

5, 2016.

M. Mohammadi, A. Al-Fuqaha, S. Sorour, and M.

Guizani, “Deep learning for IoT big data and

streaming analytics: A survey,” IEEE Commun. Surv.

Tutorials, vol. 20, no. 4, pp. 2923–2960, 2018.

M. Muqeem and N. Javed, “A Critical Review of Data

Mining Techniques in Weather Forecasting,” vol. 5,

no. 4, pp. 1091–1094, 2016.

M. N. Wibisono and A. S. Ahmad, “Weather forecasting

using Knowledge Growing System (KGS),” Proc. -

2017 2nd Int. Conf. Inf. Technol. Inf. Syst. Electr.

Eng. ICITISEE 2017, vol. 2018-January, pp. 35–38,

2018.

M. P. Shivaranjani, “A Review of Weather Forecasting

Using Data Mining Techniques,” Int. J. Eng. Comput.

Sci., vol. 5, no. 12, pp. 19784–19788, 2016.

N. Krishnaveni and A. Padma, “Weather forecast

prediction and analysis using sprint algorithm,” J.

Ambient Intell. Humaniz. Comput., no. 2015, 2020.

N. Kumar and G. K. Jha, “Time Series ANN Approach for

Weather Forecasting,” Int. J. Control Theory Comput.

Model., vol. 3, no. 1, pp. 19–25, 2013.

Cognitive Computational Approaches for Weather Forecasting: An Overview and Progress

145

N. Muthurasu, “a Prediction System for Farmers To

Enhance the Agriculture Yield Using Cognitive Data

Science,” Int. J. Adv. Res. Comput. Sci., vol. 9, no. 2,

pp. 780–784, 2018.

P. C. Reddy and A. S. Babu, “Survey on weather

prediction using big data analystics,” Proc. 2017 2nd

IEEE Int. Conf. Electr. Comput. Commun. Technol.

ICECCT 2017, 2017.

P. H. and B. S. B. Karunakara Rai, J. P. Harshitha,

Radhika S. Kalagudi, B. S. Priyanka Chowdary, and

Texture Features of Chest X-Rays, no. January.

Springer Singapore, 2019.

P. Hewage, M. Trovati, E. Pereira, and A. Behera, “Deep

learning-based effective fine-grained weather

forecasting model,” Pattern Anal. Appl., no.

0123456789, 2020.

P. Janani, B; Sebastian, “Analysis on the weather

forecasting and techniques,” IInternational J. Adv.

Res. Comput. Eng. Technol., vol. 3, no. 1, pp. 59–61,

2014.

P. Kalaiyarasi and M. A. Kalaiselvi, “Data Mining

Techniques Using To Weather Prediction,” Int. J.

Comput. Sci. Trends Technol., vol. 6, no. 3, pp. 249–

254, 2013.

P. Kapoor and S. S. Bedi, “Weather Forecasting Using

Sliding Window Algorithm,” ISRN Signal Process.,

vol. 2013, pp. 1–5, 2013.

R. Bhardwaj and V. Duhoon, “Weather forecasting using

soft computing techniques,” 2018 Int. Conf. Comput.

Power Commun. Technol. GUCON 2018, pp. 1111–

1115, 2019.

R. Lee and J. Liu, “iJADEWeatherMAN: A weather

forecasting system using intelligent multiagent-based

fuzzy neuro network,” IEEE Trans. Syst. Man Cybern.

Part C Appl. Rev., vol. 34, no. 3, pp. 369–377, 2004.

R. Samya and R. Rathipriya, “Predictive Analysis for

Weather Prediction using Data Mining with ANN: A

Study,” vol. 6, no. 2, pp. 150–154, 2016.

S. B. Priya, “A survey on weather forecasting to predict

rainfall using big data analytics,” IJISET-International

J. Innov. Sci. Eng. Technol., vol. 2, no. 10, pp. 879–

886, 2015.

S. E. Haupt, J. Cowie, S. Linden, T. McCandless, B.

Kosovic, and S. Alessandrini, “Machine learning for

applied weather prediction,” Proc. - IEEE 14th Int.

Conf. eScience, e-Science 2018, pp. 276–277, 2018.

S. Ghosh, A. Dutta, S. Roy Chowdhury, and G. Paul,

“Weather Prediction by the use of Fuzzy Logic,” J.

Mech. Contin. Math. Sci., vol. 8, no. 2, pp. 1228–

1241, 2014.

S. Jain and D. Ramesh, “Machine Learning convergence

for weather based crop selection,” 2020 IEEE Int.

Students’ Conf. Electr. Electron. Comput. Sci.

SCEECS 2020, 2020.

S. Kothapalli and S. G. Total, “A real-time weather

forecasting and analysis,” IEEE Int. Conf. Power,

Control. Signals Instrum. Eng. ICPCSI 2017, pp.

1567–1570, 2018.

S. Lee, Y. S. Lee, and Y. Son, “Forecasting daily

temperatures with different time interval data using

deep neural networks,” Appl. Sci., vol. 10, no. 5, 2020.

S. M. Taib, A. A. Bakar, A. R. Hamdan, and S. M. S.

Abdullah, “Classifying weather time series using

feature based approach,” Int. J. Adv. Soft Comput. its

Appl., vol. 7, no. Specialissue3, pp. 56–71, 2015.

S. Madan, P. Kumar, S. Rawat, and T. Choudhury,

“Analysis of Weather Prediction using Machine

Learning Big Data,” Proc. 2018 Int. Conf. Adv.

Comput. Commun. Eng. ICACCE 2018, no. June, pp.

259–264, 2018.

S. Navadia, P. Yadav, and J. Thomas, “Measuring and

Analyzing Weather Data,” pp. 414–417, 2017.

S. Navadia, P. Yadav, and J. Thomas, “Measuring and

Analyzing Weather Data,” pp. 414–417, 2017.

S. Scher and G. Messori, “Weather and climate forecasting

with neural networks: Using general circulation

models (GCMs) with different complexity as a study

ground,” Geosci. Model Dev., vol. 12, no. 7, pp.

2797–2809, 2019.

T. Miyoshi et al., “‘Big Data Assimilation’ Toward Post-

Petascale Severe Weather Prediction: An Overview

and Progress,” Proc. IEEE, vol. 104, no. 11, pp. 2155–

2179, 2016.

W. Huang, X. Xiao, and M. Xu, “Design and

implementation of domain-specific cognitive system

based on question similarity algorithm,” Cogn. Syst.

Res., vol. 57, no. xxxx, pp. 20–24, 2019.

Y. Echevarría, L. Sánchez, and C. Blanco, “Hybrid

Artificial Intelligent Systems,” Lect. Notes Comput.

Sci. (including Subser. Lect. Notes Artif. Intell. Lect.

Notes Bioinformatics), vol. 9648, no. June, pp. 250–

260, 2016.

ICACSE 2021 - International Conference on Advanced Computing and Software Engineering

146