Soil and Crop Recommendation Using Machine Learning
Soil and Crop Recommendation Using Machine Learning
Volume 9, Issue 6, June – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24JUN068
Soil and Crop Recommendation Using
Machine Learning
S.Harini[1]; M.Hariprakash[2]
[1][2]
MCA Student
[1][2]
Department of Computer Applications
[1][2]
Karpagam Academy of Higher Education, Coimbatore, Tamil Nadu, India
Abstract:- In the current scenario the major that is II. RELATED WORKS
played in every life of human is food which could only be
brought through agriculture. In this economic world the There research based on smart prediction using IoT
development of agriculture has been reduced in day by which helps to monitor the data and collect every data. The
day. The growth of every vegetables, rice etc are depends data set will be trained for the further prediction that is
upon the soil and also the weather changes. If the soil which crop will be better suited for yielding the crop. This is
condition is appropriate to grow the crop then there done with the service of wireless sensor network. The
must be correct condition of weather to the better growth records that is collected by using sensor will be stored in the
of crop. In this paper we are recommending the growth cloud. This shares the information through as SMS for the
of crop which will be best suitable for the appropriate crop rotation about the soikl condition and crop condition.
soil. For this we are using the technology that is known
to be IoT for the analysis of soil. By using this the major They done the research about using the sensing
issue might be resolved in yielding the crop with better technology in which the data conquers with the information
production. of PH, sensor, temperature etc. Hence these data set are
collected only by using the sensors within the soil to
Keywords:- Agriculture, Crop Yielding, Prediction, IOT. calculate the better growth of crop in the appropriate soil
along with the weather conditions. Thus they did the
I. INTRODUCTION research for calculating the soil moisture condition in order
to yield the crop. This also helps to detect the soil condition
The vital role played in this economic world is the to know the better growth of crop.
challenges that appear in the agriculture sector. By the
changes that are made in the agriculture that is the yield of III. METHODOLOGY
crop according to the soil sector is most important to
develop agriculture. There are few crops that could be The technologies that are used here is IoT which helps
grown only with the certain conditions in that case only the to predict every soil will most accurate range. Along with
specified crop could be grown. There are many farming IoT we have used machine learning algorithms with the real
techniques used by farmers for maintaining the crops in time for performing the field area for prediction of soil. The
order to increase the rate of production. By using the certain data that are used for prediction is collected by using IoT
condition only the crops could be yielded by meeting few system. Later then the data will be trained for the
disadvantages. The disadvantages could be overcome by calculations.
using IoT and through this the major problems could be
solved. The information that are collected through IoT will Implementation
be collected and stored in the data set. By using these data Here in this paper, we have managed Machine learning
set only the production of crop will be suggested for the for designing and IoT for collecting the data. The collected
farmers to yield in the proper soil. This information might be data is trained and pre-processed to reducte the error rate
collected using the sensors that will be enclosed within the and increase the accuracy.
soil to predict the nature of soil. Here this lecture we need
used little machine learning algorithms to predict the soil Architecture
nature and which crop will yield the best. This methodology conquers with the data that are
collected in the real time. Later these data will be predicted
and built a user interface that assists the user to provide the
input information. As the initial stage the records will be
pre-processed using Machine learning algorithm for
prediction. The data is trained to generate the appropriate
prediction. As the result this produces the random input
values which has the capability of accurate rate. This
reduces the error rate and improves the process by using IoT.
IJISRT24JUN068 www.ijisrt.com 599
Volume 9, Issue 6, June – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24JUN068
Fig 1: Block Diagram of Crop Idea Method
IOT for Records Collected Works
As the initial step we need to collect the data from the IoT. For this data set the attributes that are included here are Moisture,
Humidity, Temperature etc. All the data that are collected will be directly stored in the data set and processed for further
information. The data that are collected will be provided as the input using GUI. Through this the data might be used for
calculating the crop yield along with the weather forecasting.
Fig 2: IOT System Design
IJISRT24JUN068 www.ijisrt.com 600
Volume 9, Issue 6, June – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24JUN068
Fig 3: Proposed system
IV. FEATURE DESCRIPTION completion of every statistics because the algorithm that is
used for prediction is machine learning algorithm which
The major and foremost key factor in this research is could not handle noisy data.[10] By doing so we might able
the growth of crop. By this the farmers could able to know to reduce the error rate and the lack of data could be cleared.
the growth of crop in the appropriate soil. There are many
kinds of soil in which the crop could be yielded. Even Encode Categorical Data Using Tag Coding
though the crop yielding may vary the retaining of water Numerical and categorical data are considered to be
also required. By using the sensor, this helps to collect the two categories in the data set. The data set which holds the
data. numerical values is known to be numerical data and the data
which holds the string value is known to be categorical data.
V. DATA PREPROCESSING Every categorical data need to be converted to numerical
value for prediction.
The information that are collected through IoT sensor
will be open source. The data need to be cleared after
Fig 4: Output Suggesting Suitable Crop
IJISRT24JUN068 www.ijisrt.com 601
Volume 9, Issue 6, June – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24JUN068
Support Vector Machine the correct cluster in the future. This well-defined edge is
Support Vector Machine or SVM is one of the most called a hyperplane.
popular learning systems used in classification and
regression. However, in machine learning it is used only in SVM pick out high points/vectors that help create an
classification problems. complete plane. These conditions are called support vectors,
so the algorithm is called a vector machine. There are two
The point of the SVM algorithm is to create an optimal different groups divided into decision boundaries or general
line or decision boundary that can divide the n-dimensional planes.
space into clusters so that we can easily place new data into
z=x2 +y2
Fig 5: Soil and Crop Detection
Data Exploration later we own to collect the prediction rate to about 96% of
Data mining is a data mining process that users use to accuracy.
create accurate analyzes based on the data they collect. Data
analysis is used to analyze the data and information in the REFERENCES
data to make an actual analysis. After viewing the data set,
some information about the data was searched. While the [1]. Gupta, A., Nagda, D., Nikhare, P., Sandbhor, A. (2021).
data set is written here, the data set is not singular. In this Smart Crop Prediction using IoT and Machine
module you can create a unique dataset. Learning. International Journal of Engineering
Research and Technology, 9(3).
Data Cleaning [2]. B Thiyaneswaran, K Anguraj, M Sindhu, N. S
It is used to check and correct data errors in the data Yoganathan, J Jayanthi. (2020). Development of Iris
maintenance element. It is used to eliminate repetition of Biological Features Extraction for Biometric Based
behaviour. Data cleaning is used to clean dirty files Authentication to Prevent Covid Spread. International
containing missing or outdated data and to detect erroneous Journal of Advanced Science and Technology, 29(3),
data from various systems. It plays an important role in 8266–8275.
design. [3]. Thiyaneswaran, B., Anguraj, K., Kumarganesh, S.,
Thangaraj, K. (2020). Early detection of melanoma
VI. RESULT AND DISCUSSION images using gray level co‐occurrence matrix features
and machine learning techniques for effective clinical
In our daily life without food no one could able to diagnosis. International Journal of Imaging Systems
sustain in this world. As per that situation the data is and Technology, (ima.22514). doi:10.1002/ima.22514
collected from various sensors which tends to be open [4]. Biradar, H. B., Shabadi, L. (2021). Review on IOT
source and it could be classified for training and testing. All based multidisciplinary models for smart farming.
the data that has been collected by using the sensor will be [5]. Mehta, P., Shah, H., Kori, V., Vikani, V., Shukla, S.,
calculated using machine learning algorithm for the accurate Shenoy, M. (2019). Survey of unsupervised machine
prediction of harvesting. By doing so we may able to learning algorithms on precision agricultural data.
calculate the better crop yielding in the appropriate soil. As IEEE Xplore.
we provide various inputs that are collected by sensors and
IJISRT24JUN068 www.ijisrt.com 602
Volume 9, Issue 6, June – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24JUN068
[6]. Sandhiya, D., Thiyaneswaran, B. (2020). Extraction of [22]. Athani, S., Tejeshwar, C. H., Patil, M. M., Patil, P.,
dorsal palm basilic and cephalic hand vein features for Kulkarni, R. (2021, February 1). Soil moisture
human authentication system. 2017 International monitoring using IoT enabled arduino sensors with
Conference on Wireless Communications, Signal neural networks for improving soil management for
Processing and Networking (WiSPNET). IEEE. farmers and predict seasonal rainfall for planning
[7]. Radhika, Y., Shashi, M. (2021). Atmospheric future harvest in North Karnataka — India
Temperature Prediction using Support Vector
Machines. International Journal of Computer Theory
and Engineering, 55–58.
[8]. Ahmad, S., Kalra, A., & Stephen, H. (2019).
Estimating soil moisture using remote sensing data: A
machine learning approach. Advances in Water
Resources, 33(1), 69–80.
[9]. Kumar, R., Singh, M. P., Kumar, P., & Singh, J. P.
(2022). Crop Selection Method to maximize crop yield
rate using machine learning technique. IEEE Xplore.
[10]. Shah, N. P., Bhatt, P. (2023). Greenhouse Automation
And Monitoring System Design And Implementation.
International Journal of Advanced Research in
Computer Science, 8(9), 468–471
[11]. Jayanthi, J., and J. Selvakumar. A novel framework to
facilitate personalized web search in a dual mode
Cluster Computing 20.4 (2022): 3527-3535.
[12]. Parker, C. (2022). Unexpected challenges in large scale
machine learning. Proceedings of the 1st International
Workshop on Big Data, Streams and Heterogeneous
Source Mining Algorithms, Systems, Programming
Models and Applications - BigMine ’12.
[13]. Pudumalar, S., Ramanujam, E., Rajashree, R. H.,
Kavya, C., Kiruthika, T., & Nisha, J. (2020). Crop
recommendation system for precision agriculture.
IEEE Xplore.
[14]. Anitha, P., Chakravarthy, T. (2021). Agricultural Crop
Yield Prediction using Artificial Neural Network with
Feed Forward Algorithm. International Journal of
Computer Sciences and Engineering, 6(11),178–181.
[15]. B Thiyaneswaran, V Bhuvaneshwaran, M.S Dharun, K
Gopu, T Gowsikan (Ed.). (2020). Breathing level
monitoring and alerting by using embedded IOT (Vol.
10). Journal of Green Engineering.
[16]. Rekha, P., Rangan, V. P., Ramesh, M. V., Nibi, K. V.
(2021). High yield groundnut agronomy: An IoT based
precision farming framework. IEEE Xplore.
[17]. Biradar, H. B.,Shabadi, L. (2021). Review on IOT
based multidisciplinary models for smart farming.
IEEE Xplore.
[18]. Jayanthi, J., and J. Selvakumar. A novel framework to
facilitate personalized web search in a dual mode.
Cluster Computing 20.4 (2022): 3527-3535.
[19]. Priya, P. K., Yuvaraj, N. (2019). An IoT Based
Gradient Descent Approach for Precision Crop
Suggestion using MLP. Journal of Physics: Conference
Series, 1362, 012038.
[20]. Thiyaneswaran, B., Saravanakumar, A.,& Kandiban, R.
(2020). Extraction of mole from sclera using object
area detection algorithm. 2016 International
Conference on Wireless Communications, Signal
Processing and Networking (WiSPNET). IEEE.
[21]. Patil, A., Beldar, M., Naik, A., & Deshpande, S.
(2022). Smart farming using Arduino and data mining.
IEEE Xplore.