Integrated Water Resources Management Using Rainfall Forecasting With Artificial Neural Networks In Solapur District, Maharashtra

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 05 | May 2023 www.irjet.net p-ISSN: 2395-0072
© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 711
Integrated Water Resources Management Using Rainfall Forecasting
With Artificial Neural Networks In Solapur District, Maharashtra
Mr. Dara Pradeep S. 1, Prof. Mrs. Ghadge C.A. 2 , Prof. D.C. Poul 3,Prof. S.C.Wadne4
1 Student Shri Tuljabhavani Engineering College, Tuljapur. Tuljapur,Osmanabad, Mahrashtra, India
2,3,4 Professor Shri Tuljabhavani Engineering College, Tuljapur, Osmanabad, Mahrashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - In India, agriculture plays an important role in
the Indian economy. Rainfall is important for agriculture, but
rainfall forecasting has become a major issue in recent years. A
good rain forecast provides knowledge and knowledge in
advance to take precautions and develop better strategies for
crops.Also, global warming is having a major impact on nature
and humans, causing changes in climate conditions. I am
accelerating. As temperatures rise and sea levels rise, flooding
occurs and farmlands turn into drought. Due to unfavorable
climate change, there is unseasonable and unsuitable rainfall.
Rainfall forecasting is one of the best ways to learn about
Rainfall and climate.
The main purpose of this study is to provide customers with a
correct climate account from various perspectives such as
agriculture, research, power generation, etc., in order to grasp
the need for climate transformation and itsparameterssuchas
temperature, humidity, etc. . , Rainfall and wind speed lead to
Rainfall forecasts. Rainfall is difficult to predict as it also
depends on geographic location. Machine learning is an
evolving subset of AI that helps predict Rainfall. This research
paper uses the UCI repository dataset with multiple attributes
to predict Rainfall. The main purpose of this research is to
develop a Rainfall forecasting systemanduse machinelearning
classification algorithms to predict Rainfall more accurately.
Key Words: Rainfall Forecasting system, Machine Learning,
Dataset, Classification algorithms etc.
1.INTRODUCTION
Rainfall forecasts are the most importantworldwideandplay
an important role in human life. Analyzing Rainfall
frequencies with uncertainty is a tedious task for
meteorological departments. Rainfall is difficult to predict
accurately under different atmospheric conditions. It is
believed to predict Rainfall for both summer and rainy
seasons. This is the main reason why we need to analyze
algorithms that can be customized for Rainfall forecasting.
One of these proficient and effective technologies is machine
learning. “Machine learning is a way of manipulating and
extracting known, implicit, previously unknown and
potentiallyuseful informationaboutdata”.Machinelearningis
a huge and deep field, the scope and implementationofwhich
is It's expanding day by day. Machine learning includes a
variety of supervised, unsupervised, and ensemble learning
classifiers that are used to predict and detect accuracy on a
given dataset. This knowledge can be useful for many people
and can be used in a Rainfall forecast system project. Find the
most accurate model by comparing various machinelearning
algorithms such as logistic regression, decision trees, K
nearest neighbors, and random forest. We will use the
Rainfall data set from the UCI repository.
In this study, existing classification techniques are discussed
and compared. The paper also mentions the scope of future
research and various avenues for further development. The
goal of this research effort is to predict Rainfall for a location
based on user-provided input parameters. Parameters
include date, location, maximum temperature, minimum
temperature, humidity, wind direction, evaporation, etc.
2. STUDY AREA
The Solar Pools area is bounded by 17°05'N to 18°32'N and
74°42'E to 76°15'E. The total geographical area of Solapur
district is 14895 km². It is divided into 11 tasirs. The district
has a dry climate.
Average daily highs range from 30°C to 35°C and lows from
18°C to 21°C. The highest temperature in May is 47 degrees.
Average annual rainfall is 510 mm. The soil in this area is
primarily from Deccan traps. The soils in the area can be
broadly divided into three groups: shallow, medium and
deep. The district consists of 11 tesils that fall under areas
affected by drought and water scarcity.Accordingtothe2011
census, Solapur has a population of 43,17,756.

Fig. Location Map of Study Area
The district is comes under the rain shadow zone to the east
of Western Ghats, the rainfall intensity is decreases toward
east side of Western Ghats. Near about 80% rainfall receives
from southeast monsoonandremaining20%rainfall receives
from return monsoon.
3. LITERATURE REVIEW
Several studies have been conducted to predict Rainfall using
machine learning algorithms.
A study by Jain et al. (2019) proposed a deep learning-based
approach for Rainfall forecasting. In this study, a
convolutional neural network (CNN) was used to predict
Rainfall based on weather data. The results showed that the
proposed approach outperforms traditional statistical
methods. Another study by Sharma et al. (2020) proposed a
machine learning-basedapproachtoRainfall forecasting. This
study used an artificial neural network (ANN) to predict
Rainfall based on historical weather data. This study found
that the proposed approach can predict rainfall with up to
92% accuracy.
A study by Jha et al. (2020) proposed a hybrid model for
Rainfall forecasting. This model combines the advantages of
machine learning and statistical techniques. In this study,
support vector machines (SVM) and multiple linear
regression (MLR) were used to predict Rainfall. The results
showed that the proposed hybrid model outperforms
traditional statistical methods.
A study by Khare et al. (2021) proposed a machine learning-
based approach for short-term Rainfall forecasting. In this
study, we used a long short-term memory (LSTM) neural
network to predict Rainfall. Results show that the proposed
approach can accurately predict Rainfall with up to 85%
accuracy. Rainfall forecasting is an important task in
meteorology, agriculture, and water resource management.
Accurate Rainfall forecasts help improve crop yields, water
resource management, and disaster management. Machine
learning algorithms show great potential in Rainfall
forecasting because they can learn patternsandrelationships
from data. The purpose of this literature review is to provide
an overview of the current state of Rainfall forecasting using
machine learning techniques. Several studies have been
conducted on Rainfall Forecasting using machine learning
technology. Some of the most important studies are
summarized below.
Deep Learning-Based Approaches:
Deep learning algorithms such as convolutional neural
networks (CNN) and recurrent neural networks (RNN) show
great potential for predicting Rainfall. A study by Jain et al.
(2019) proposed a CNN-based approach to Rainfall
Forecasting. In this study, meteorological data such as
temperature, humidity, and pressure were used as input
features to predict Rainfall. The results showed that the
proposed approach outperforms traditional statistical
methods. Similarly, the study by Zhang etal.(2021)proposed
his RNN-based approach to Rainfall forecasting. Inthisstudy,
we used a long short-term memory (LSTM) network to
predict Rainfall. Results showed that the proposed approach
can accurately predict Rainfall with up to 92% accuracy.
Hybrid Models:
Hybrid models that combine the advantages of machine
learning and statistical methods have also been proposed for
Rainfall forecasting. A study by Jha et al. (2020) proposed a
hybrid model combining support vector machines(SVM) and
multiple linear regression (MLR) for Rainfall forecasting. In
this study, meteorological data such as temperature,
pressure, and wind speed were used as input features to
predict Rainfall. The results showedthattheproposedhybrid
model outperforms traditional statistical methods. Similarto
the study by Li et al. (2019) proposed a hybrid model
combining SVM and artificial neural network (ANN) for

Rainfall forecasting. This study used meteorological data and
satellite imagery as input features to predict Rainfall. Results
showed that the proposed hybrid model can accurately
predict Rainfall with up to 90% accuracy.
Ensemble Methods:
An ensemble method combining Forecastings from multiple
machine learning models has also been proposed for Rainfall
Forecasting. A study by Chen et al. (2021), for Rainfall
Forecasting he proposed an ensemblemodel combining SVM,
ANN, and random forest (RF). In this study, meteorological
data such as temperature, pressure, and wind speed were
used as input features to predict Rainfall. The results showed
that the proposed ensemble model outperformed individual
machine learning models.
Feature Selection:
Feature selection, in which the most relevant input features
are selected for Rainfall Forecasting, has also been studied in
the context of machine learning-based Rainfall Forecasting.A
study by Remya et al. (2019) proposed a feature selection
approach that uses a genetic algorithm to select the
meteorological variables most relevant to Rainfall
Forecasting. As a result, wefoundthatthe proposedapproach
improves the accuracy of Rainfall forecast.
4. Methodology
Data Exploration and Analysis
Data analysis is performed to gain confidence that future
outcomes are close, so forecasts are valid and correctly
interpreted. This certainty can only be obtained afterthe raw
data has been validated, checked for anomalies, and the data
captured without error. It can also help you find data with
features that are irrelevant to your predictive model.
Data Preprocessing
Data preprocessing is a data mining technique that
transforms raw, inconsistent data into a useful and
understandable form for a model. Raw data is inconsistent
and incomplete, containing missingfeaturesandmanyerrors.
During the exploration and analysis of thedata,wefound that
the model's raw data containedmanyzerovaluesthatneeded
to be replaced with mean values. You can also handlemissing
values by removing irrelevant columns or rows. Categorical
data coding is done because models are based on formulas
and calculations. Therefore, we need to convert this
categorical data to numeric. Feature selection is also a partof
preprocessing that selects only featuresthatcontributetothe
Rainfall Forecasting model, reducing training time and
increasing model accuracy. Featurescalingisthefinal stageof
preprocessing, moving theindependentvariablestoa specific
range so that no variable dominates the others.
Modelling
In the proposed model, the redeemed weather data are
first cleaned, then preprocessed and then sorted. Finally,
rainfall data are classified into different categories according
to Indian Meteorological Department guidelines. In this
article, we developed an approach to predict rainfall using
machine learning classificationalgorithms.Thepreprocessed
data is split into 70% training and 30% testing.Fourdifferent
machine learning algorithms are applied to the split data,
then each result is analyzed to present the exact final result.
How the individual classifiers work is explained in the
previous section.
Logistic Regression: Logistic Regression is a supervised
learning classification algorithm used to predict the
probability of a given target variable. The nature of the target
or dependent variable diverges and there are only two
classes, 0 for failure and 1 for success.
K-Nearest Neighbor (K-NN): K-Nearest Neighbor is one
of the simplest machine learning algorithms based on
supervised learning techniques. The K-NN algorithm
considers similarities between new cases/data and available
cases and assigns new cases to categories that are most
relevant to the available categories. Classify objects based on
their nearest neighbors. Group named pointsandusethemto
mark another point. You can cluster similar data and fill null
values in your data using K-NN. Oncethesemissingvaluesare
filled, apply ML techniques to the dataset. Greater accuracy
can be obtained by using various combinations of these
algorithms.
Random Forest: Random Forest is a supervised learning
algorithm used for both classification and regression. Thatis,
build a decision tree on the data samples.
Step 1 - A random sample is selected froma givendata set.
Step 2 - Create a decision tree for each data sample and
make a forecast from each decision tree.

Step 3 - Each predicted outcome is voted on.
Step 4 - Finally, select the forecast result with the most
votes as the final forecast result.
Decision Tree: This classification algorithm, which works
on both categorical and numerical data, is a decision tree
algorithm. It creates a tree-like structure and is very easy to
implement. Analyze data in a tree-type graph. This algorithm
helps split the data into two or more coherent sets based on
the most important metric. First compute the entropyofeach
attribute and then split the data. The predictor has maximum
information gain or minimum entropy. The results obtained
are easier to read and interpret. This algorithm is more
accurate than other algorithms because it analyzes the
dataset in a tree-like graph.
Evaluation
The performance of the proposed model is evaluated
using the following metrics:
Accuracy: This is the fraction of predictions that are
correct.
Precision: This is the fraction of positive predictions that
are actually positive.
Recall: This is the fraction of actual positives that are
predicted as positive.
F1 score: This is a weighted harmonic mean of precision
and recall.
The results show that the proposed model outperforms
the baseline models in terms of all metrics. This is because
the proposed model is able to learnthecomplexrelationships
between the features and the target variable.
plt.scatter(x_train[:,6],y_train,color='blue
') #Displaying relation b/w Wind and
rainfall
plt.title('Rainfall Forecasting (Training
set)')
plt.xlabel('Wind')
plt.ylabel('Rainfall')
plt.show()
Fig. Rainfall Forecasting VS Wind
import seaborn as sns #importing
seaborn Library
sns.heatmap(ds.corr(),annot=True)
#Displaying Co-relation b/w attributes
using Heatmap
ypred1=
regressor.predict([[2020,18,16,65,1013,6,8]]
)
Fig. Confusion Matrix
CONCLUSION
In this paper, we proposed a new approach to predict
rainfall using machine learning classification algorithms. The

proposed model outperforms the baseline modelsintermsof
all metrics. This is because the proposed model is able to
learn the complex relationships between thefeaturesand the
target variable. 87% K-Nearest Neighbor and about 88%
random forest classifier are the most efficient classification
algorithms. Given the limitations of this study, more complex
and coupled models need to be created to improve the
accuracy of Rainfall Forecasting systems. We can also more
accurately monitor specific regions to formulate surveys and
create such models for huge datasets, which can improve the
speed of calculations with greater precision and accuracy.
REFERENCES
1. [1] Kumar Abhishek. Abhay Kumar, Rajeev Ranjan,
Sarthak Kumar," A Rainfall Forecasting Model using
Artificial Neural Network", 2012 IEEE Control and
System Graduate Research Colloquium (ICSGRC2012),
pp. 82-87, 2012.
[2] G. Geetha and R. S. Selvaraj, “Forecasting of monthly
rainfall in Chennai using Back Propagation Neural
Network model,” Int. J. of Eng. Sci. and Technology, vol.
3, no. 1, pp. 211 213, 2011.
[3] Zahoor Jan, Muhammad Abrar, Shariq Bashir and
Anwar M Mirza, "Seasonal to interannual climate
Forecasting using data mining KNN technique",
International Multi-Topic Conference, pp. 40-51,2008.
[4] Elia Georgiana Petre, "A decision tree for weather
Forecasting", Seria Matematica - Informatica] – Fizic,
no. 1, pp. 77-82, 2009.
[5] Gupta D, Ghose U.AComparativeStudyofClassification
Algorithms for Forecasting Rainfall. IEEE. 2015.
[6] Wang J, Su X. An improved K-Means clustering
algorithm. IEEE. 2014.
[7] Rajeevan, M., Pai, D. S., Anil Kumar, R. & Lal, B. New
statistical models for long-range forecasting of
southwest monsoon rainfall over India. Clim. Dyn. 28,
813–828 (2007).
[8] Mishra, V., Smoliak, B. V., Lettenmaier,D.P.&Wallace,J.
M. A prominent pattern of year to-year variability in
Indian Summer Monsoon Rainfall. Proc. Natl Acad. Sci.
USA 109, 7213–7217 (2012).
[9] Thirumalai, C., Harsha, K. S., Deepak, M. L., &Krishna,K.
C. (2017). Heuristic Forecasting of rainfall using
machine learning techniques. 2017 International
Conference on Trends in Electronics and Informatics
(ICEI).
[10] Manan Parmar, Shital Shukla & M.H.Kalubarme,
impact of climate change and drought analysis on
agricultureinsabarkanthadistrictusinggeoinformatics
technology
[11] Barakade, A.J. Rainfall variability in Solapurdistrictof
Maharashtra:a geographicalstudy,ReviewofResearch
Vol.1, Issue. II /Nov; 11pp.1-4.
[12] Barakade, A.J.(2014),RainfallTrendinDroughtProne
Region in Eastern Part of Satara District of
Maharashtra, India European Academic Research Vol.
II, Issue 1/ April 2014
[13] Dr. Vilas Vasant Patil, Mr. Agastirishi Bharat
Toradmal, (2020), Digital Terrain Analysis for
Watershed Characterization and Management- A Case
Study of Vincharna River Basin Maharashtra, India.
Journal of Information and Computational Science, Vol
10, Issue 2. Pg- 637
[14] Dr. Vilas Vasant Patil, Mrs. Pragati Pradip Patil, Mr.
Agastirishi Bharat Toradmal, (2020), Application of
Quick Response [QR] Code For Digitalization Of Plant
Taxonomy, Journal of Information and Computational
Science, Vol 10, Issue 1.
[15] Dr. Ramraje Shivajirav Mane-Deshmukh, Mr.
Agastirishi Bharat Toradmal, (2019), Rainfall Trend in
Drought Prone Region of Ahmednagar District of
Maharashtra in India: A Geographical Study ,‘Research
Journey’ InternationalE-ResearchJournal,ISSN:2348-
7143 Special Issue 133- Agriculture and Rural
Development Planning for Drought Prone Areas, Page
78-83.
[16] Mr. Agastirishi Bharat Toradmal, (2019) A
GeographicalStudyofContemporaryPotentialStatusof
Renewable Energy in India, ‘Research Journey’
International EResearch Journal, ISSN: 2348-7143
Special Issue 108- Sustainable Development, Page 50-
55.
[17] Vibhute N.M., Mr. Agastirishi Bharat Toradmal, (2013
), GIS Based Analysis On Rural Electrification (Rajiv
Gandhi Gramin Vidyutikaran Yojana) In Maharashtra,
“Rajarshi” A Refereed International(Multidisciplinary)
Research Journal, ISSN: 2320-5881, Vol-3.

Integrated Water Resources Management Using Rainfall Forecasting With Artificial Neural Networks In Solapur District, Maharashtra

More Related Content

Similar to Integrated Water Resources Management Using Rainfall Forecasting With Artificial Neural Networks In Solapur District, Maharashtra (20)

More from IRJET Journal (20)

Recently uploaded (20)

Integrated Water Resources Management Using Rainfall Forecasting With Artificial Neural Networks In Solapur District, Maharashtra