SlideShare a Scribd company logo
A6024
Product
Realization
06/08/2022 DEPT. OF CSE(AI&ML) 1
VARDHAMAN COLLEGE OF ENGINEERING, HYDERABAD
Autonomous institute, affiliated to JNTUH
Fertilizer Recommendation
System
By
20881A6627 – K. Anuhya
20881A6660 – V. SiriChandana
21885A6603 –K. Sai Kishore
Under the guidance of
P.Swetha
Dr. Prakash Kumar Sarangi
18
Outline
• Introduction
• Literature Review
• Need Statement and Community Partner details
• Objectives
• Existing System vs Proposed System
• Software and Hardware Requirements
• Proposed Methods and Algorithms
• Construction of a model with a Picture
• Result Analysis
• Conclusion
• References
8/25/2022 DEPT. OF ELECTRONICS AND COMMUNICATION ENGINEERING 2
Introduction
•Soil testing has been accepted as a unique tool for rational fertilizer use.
•There are three main nutrients in the soil that play a major role in farming:
Nitrogen (N), Phosphorous (P), and Potassium (K) collectively known as
NPK.
•The best possible recognition of these nutrients at starting stage is essential
for the successful development of the harvest.
•Effectively estimating these nutrients in the soil and characterizing them to
recommend the fertilizer for the crop.
06/08/2022
COMPUTER SCIENCE AND ENGINEERING(AIML) 3
Literature Survey
•In a research carried out by Zaminur Rahman a comparative study of several
machine learning techniques has been carried out.
•They have carried out the classification using the data of Telangana. Considered the
six district soil data and used the geographical features for classification.
• They have used k Nearest Neighbor, Bagged tree, and SVM finally compared the
results of three algorithms and brought out a model for recommending fertilizers.
•The accuracy obtained by these models is around 80%.
06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
4
NEED STATEMENT
•Farming part has a vital job in the Indian economy for GDP development in India.
•But in recent years due to multiple fertilizers present in the market, farmers get confused
and apply the fertilizer famous around their locality without a second thought.
•This leads to two major problems low yield and soil pollution. Due to insufficient
nutrients after applying fertilizers the yield of a crop is reduced.
• Due to over-fertilization, the land, and food produced from the land will be polluted.
•Fertilizer plays a major role in farming and contributes around 55% of the yield
enhancement.
06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 5
Community Partner Details
Soil Testing Centres:
• Soil tests are performed on the soil to determine the amount of Nitrogen(N),
Phosphorus(P), and Potassium(K).
•pH of the soil can also be determined by a soil test.
•Soil test centers/laboratories are present in every district of Telangana in
regional KVKs(Krishi Vigyan Kendras) offering free services.
• The test results are then examined and certain conclusions and
recommendations are made.
06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
6
OBJECTIVES
•To create an efficient recommendation system for fertilizers based on the
NPK values of the soil.
•To help the farmers to maximize the yield for the given crop cycle
without affecting the land and soil properties.
To ensure that healthy crops have been cultivated by reducing the
chances of over-fertilization.
•To create a user-friendly web application.
06/08/2022
COMPUTER SCIENCE AND ENGINEERING(AIML) 7
Existing System vs Proposed System
EXISTING SYSTEM
•Does not incorporate a web interface that
makes it easier for users to access the
system.
•Only a few parameters are considered for
prediction.
•Not scalable to larger datasets.
•Less accurate when compared to other
similar systems.
PROPOSED SYSTEM
•We provide a web interface that makes it
easier for users to access the system.
•We considered 9 parameters of soil for
prediction.
•Scalable for large datasets.
•Accuracy of the model is high when
compared to other models.
6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
8
Requirements
Hardware
• System with processor i3 or above.
•RAM(4 GB).
•Window OS
Software
•Flask
•Heroku
•Libraries like NumPy, pandas,
matplotlib, seaborn, sci-kit learn.
•HTML,CSS.
8/25/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
9
Proposed Model
• The data set contains 8 attributes Nitrogen, Phosphorus, Potassium, Temperature, Humidity,
Moisture, crop type, soil type, and Fertilizer.
•The data set is cleaned at this stage using the scikit-learn module. Any null values, Redundant
values, or Missing values are eliminated at this stage.
•Necessary steps like Label Encoding and Feature extraction and checking for the relationship
between attributes, and outliers are done at this stage.
•Random Forest, Naïve Bayes, and K-Nearest Neighbour are used to build a machine learning
model.
•The input is taken from the users/farmers and the prediction is using these algorithms and a
suitable fertilizer is recommended.
6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
10
Proposed Model
6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
11
Proposed Model
•Figure 2 shows the flow diagram of the fertilizer recommendation system. At first, the data sets
are collected from Kaggle.
•The dataset consists of 8 attributes Nitrogen, Phosphorus, Potassium, Temperature, Humidity,
Moisture, crop type, soil type, and Fertilizer.
•The dataset is then pre-processed by handling missing values and outliers. The data is fed to
machine learning algorithms with different training and testing ratios.
•The trained model is introduced to the users using a web interface where the user can give inputs
to the model.
•The model predicts the best fertilizer based on the given soil nutrient values. The inputs here are
soil nutrients and environmental conditions.
6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
12
Construction of the product
•Flask is a web application framework written in python.
•Heroku is a cloud hosting platform that uses AWS infrastructure with rapid scaling
capabilities, offering flexible deployment services for all kinds of applications.
•The website is constructed using Flask and it is deployed using Heroku.
•The web application consists of fields such as attributes Nitrogen, Phosphorus,
Potassium, Temperature, Humidity, Moisture, crop type, soil type, and Fertilizer.
•The model is trained with different machine learning algorithms and it predicts the
best fertilizer suitable for the soil and recommends it to the farmer through the web
application.
6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
13
Construction of the product
8/25/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
14
Results and Analysis
•The dataset is collected from Kaggle. The data is preprocessed and applied to the
random forest, Naive Bayes, and k nearest neighbor classification algorithms.
• In multiclass classification, the elements are classified into multiple classes. The
random forest algorithm uses trees for classification.
•The k-NN algorithms group the data based on the given number of neighbors.
•The naïve Bayes algorithm separates the data into different classes according to the
Bayes theorem.
•These classification algorithms are trained and tested with the large datasets collected
and the accuracies are noted in the below table.
6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
15
Results and Analysis
6/8/2022
COMPUTER SCIENCE AND ENGINEERING(AIML) 16
Conclusion
• Fertilizers used in agriculture contribute around 55% to the enhancement of crop
yield. The fertilizer recommendation system will help farmers to choose the best
fertilizer based on their properties.
•This recommendation system will consider all these properties of soil along with
the weather conditions such as temperature, humidity, soil type, and crop type and
recommends the best fertilizer.
• Datasets are collected and pre-processed in a python environment and different
ML algorithms such as Naive Bayes, k-NN, and Random Forest are employed.
• The Random Forest algorithm is functioning with the best accuracy of 98%.
6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML)
17
References
1. Silpa, C., RamPrakash Reddy Arava, and K. K. Baseer. "AGRI FARM: CROP AND
FERTILIZER RECOMMENDATION SYSTEM FOR HIGH YIELD FARMING USING
MACHINE LEARNING ALGORITHMS.“
2. Subramanian, Kanaga Suba. (2020). Design and Implementation of Fertilizer
Recommendation System for Farmers.
3. Hernández Moreno, Rafael, Olmer Garcia, and Luis Alejandro Arias. "Model of neural
networks for fertilizer recommendation and amendments in pasture crops." (2018).
4. Shinde, Mansi, Kimaya Ekbote, Sonali Ghorpade, Sanket Pawar, and Shubhada Mone.
"Crop recommendation and fertilizer purchase system." International Journal of Computer
Science and Information Technologies 7, no. 2 (2016): 665-667.
06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 18
8/25/2022
COMPUTER SCIENCE AND ENGINEERING(AIML)
19
THANK YOU

More Related Content

Similar to PR 18 final ppt.pptx

FAO NextGen Policy Brief Webinar_Christen.pptx
FAO NextGen Policy Brief Webinar_Christen.pptxFAO NextGen Policy Brief Webinar_Christen.pptx
FAO NextGen Policy Brief Webinar_Christen.pptx
evanwchristen
 
FiPaaS proposal - environment meeting 6-may-2018
FiPaaS proposal - environment meeting 6-may-2018FiPaaS proposal - environment meeting 6-may-2018
FiPaaS proposal - environment meeting 6-may-2018
Mohamed_Bahnassy
 
BTech-Midterm_Template_2022.pptx
BTech-Midterm_Template_2022.pptxBTech-Midterm_Template_2022.pptx
BTech-Midterm_Template_2022.pptx
PoojaG86
 

Similar to PR 18 final ppt.pptx (20)

IRJET- IOT in Agriculture
IRJET- IOT in AgricultureIRJET- IOT in Agriculture
IRJET- IOT in Agriculture
 
soil_sample.pptx
soil_sample.pptxsoil_sample.pptx
soil_sample.pptx
 
A COMPREHENSIVE SURVEY ON AGRICULTURE ADVISORY SYSTEM
A COMPREHENSIVE SURVEY ON AGRICULTURE ADVISORY SYSTEMA COMPREHENSIVE SURVEY ON AGRICULTURE ADVISORY SYSTEM
A COMPREHENSIVE SURVEY ON AGRICULTURE ADVISORY SYSTEM
 
““Smart Crop Prediction System and Farm Monitoring System for Smart Farming””
““Smart Crop Prediction System and Farm Monitoring System for Smart Farming””““Smart Crop Prediction System and Farm Monitoring System for Smart Farming””
““Smart Crop Prediction System and Farm Monitoring System for Smart Farming””
 
Agricultural Integrated Survey (AGRIS): Rationale and Methodology
Agricultural Integrated Survey (AGRIS):  Rationale and MethodologyAgricultural Integrated Survey (AGRIS):  Rationale and Methodology
Agricultural Integrated Survey (AGRIS): Rationale and Methodology
 
FAO NextGen Policy Brief Webinar_Christen.pptx
FAO NextGen Policy Brief Webinar_Christen.pptxFAO NextGen Policy Brief Webinar_Christen.pptx
FAO NextGen Policy Brief Webinar_Christen.pptx
 
Agricultural Integrated Survey (AGRIS): Rationale and Methodology
Agricultural Integrated Survey (AGRIS):  Rationale and MethodologyAgricultural Integrated Survey (AGRIS):  Rationale and Methodology
Agricultural Integrated Survey (AGRIS): Rationale and Methodology
 
BHARATH KISAN HELPLINE
BHARATH KISAN HELPLINEBHARATH KISAN HELPLINE
BHARATH KISAN HELPLINE
 
FiPaaS proposal - environment meeting 6-may-2018
FiPaaS proposal - environment meeting 6-may-2018FiPaaS proposal - environment meeting 6-may-2018
FiPaaS proposal - environment meeting 6-may-2018
 
Smart Irrigation System using Machine Learning and IoT
Smart Irrigation System using Machine Learning and IoTSmart Irrigation System using Machine Learning and IoT
Smart Irrigation System using Machine Learning and IoT
 
Core Training Presentations- 6 IMPACT Data-Model Philosophy
Core Training Presentations- 6 IMPACT Data-Model PhilosophyCore Training Presentations- 6 IMPACT Data-Model Philosophy
Core Training Presentations- 6 IMPACT Data-Model Philosophy
 
DESIGN OF SOFTWARE BASED WATER DISTRIBUTION SYSTEM FOR A VILLAGE
DESIGN OF SOFTWARE BASED WATER DISTRIBUTION SYSTEM FOR A VILLAGEDESIGN OF SOFTWARE BASED WATER DISTRIBUTION SYSTEM FOR A VILLAGE
DESIGN OF SOFTWARE BASED WATER DISTRIBUTION SYSTEM FOR A VILLAGE
 
BTech-Midterm_Template_2022.pptx
BTech-Midterm_Template_2022.pptxBTech-Midterm_Template_2022.pptx
BTech-Midterm_Template_2022.pptx
 
IRJET - Agrotech: Soil Analysis and Crop Prediction
IRJET - Agrotech: Soil Analysis and Crop PredictionIRJET - Agrotech: Soil Analysis and Crop Prediction
IRJET - Agrotech: Soil Analysis and Crop Prediction
 
UDM (Unified Data Model) - Enabling Exchange of Comprehensive Reaction Inform...
UDM (Unified Data Model) - Enabling Exchange of Comprehensive Reaction Inform...UDM (Unified Data Model) - Enabling Exchange of Comprehensive Reaction Inform...
UDM (Unified Data Model) - Enabling Exchange of Comprehensive Reaction Inform...
 
Machine learning project
Machine learning projectMachine learning project
Machine learning project
 
The Irish Centre for High End Computing and IBM: The role of advanced computi...
The Irish Centre for High End Computing and IBM: The role of advanced computi...The Irish Centre for High End Computing and IBM: The role of advanced computi...
The Irish Centre for High End Computing and IBM: The role of advanced computi...
 
The Irish Centre for High End Computing and IBM - The role of advanced comput...
The Irish Centre for High End Computing and IBM - The role of advanced comput...The Irish Centre for High End Computing and IBM - The role of advanced comput...
The Irish Centre for High End Computing and IBM - The role of advanced comput...
 
diapo_1.pdf
diapo_1.pdfdiapo_1.pdf
diapo_1.pdf
 
Crop Recommendation System to Maximize Crop Yield using Machine Learning Tech...
Crop Recommendation System to Maximize Crop Yield using Machine Learning Tech...Crop Recommendation System to Maximize Crop Yield using Machine Learning Tech...
Crop Recommendation System to Maximize Crop Yield using Machine Learning Tech...
 

Recently uploaded

Fruit shop management system project report.pdf
Fruit shop management system project report.pdfFruit shop management system project report.pdf
Fruit shop management system project report.pdf
Kamal Acharya
 
Automobile Management System Project Report.pdf
Automobile Management System Project Report.pdfAutomobile Management System Project Report.pdf
Automobile Management System Project Report.pdf
Kamal Acharya
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
Neometrix_Engineering_Pvt_Ltd
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdf
Kamal Acharya
 

Recently uploaded (20)

Quality defects in TMT Bars, Possible causes and Potential Solutions.
Quality defects in TMT Bars, Possible causes and Potential Solutions.Quality defects in TMT Bars, Possible causes and Potential Solutions.
Quality defects in TMT Bars, Possible causes and Potential Solutions.
 
A case study of cinema management system project report..pdf
A case study of cinema management system project report..pdfA case study of cinema management system project report..pdf
A case study of cinema management system project report..pdf
 
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWINGBRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
 
Fruit shop management system project report.pdf
Fruit shop management system project report.pdfFruit shop management system project report.pdf
Fruit shop management system project report.pdf
 
Automobile Management System Project Report.pdf
Automobile Management System Project Report.pdfAutomobile Management System Project Report.pdf
Automobile Management System Project Report.pdf
 
The Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdfThe Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdf
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
 
Introduction to Machine Learning Unit-4 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-4 Notes for II-II Mechanical EngineeringIntroduction to Machine Learning Unit-4 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-4 Notes for II-II Mechanical Engineering
 
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
 
Online resume builder management system project report.pdf
Online resume builder management system project report.pdfOnline resume builder management system project report.pdf
Online resume builder management system project report.pdf
 
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data StreamKIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
 
Democratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek AryaDemocratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek Arya
 
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and VisualizationKIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
 
Construction method of steel structure space frame .pptx
Construction method of steel structure space frame .pptxConstruction method of steel structure space frame .pptx
Construction method of steel structure space frame .pptx
 
IT-601 Lecture Notes-UNIT-2.pdf Data Analysis
IT-601 Lecture Notes-UNIT-2.pdf Data AnalysisIT-601 Lecture Notes-UNIT-2.pdf Data Analysis
IT-601 Lecture Notes-UNIT-2.pdf Data Analysis
 
fluid mechanics gate notes . gate all pyqs answer
fluid mechanics gate notes . gate all pyqs answerfluid mechanics gate notes . gate all pyqs answer
fluid mechanics gate notes . gate all pyqs answer
 
The Ultimate Guide to External Floating Roofs for Oil Storage Tanks.docx
The Ultimate Guide to External Floating Roofs for Oil Storage Tanks.docxThe Ultimate Guide to External Floating Roofs for Oil Storage Tanks.docx
The Ultimate Guide to External Floating Roofs for Oil Storage Tanks.docx
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdf
 
Peek implant persentation - Copy (1).pdf
Peek implant persentation - Copy (1).pdfPeek implant persentation - Copy (1).pdf
Peek implant persentation - Copy (1).pdf
 
Natalia Rutkowska - BIM School Course in Kraków
Natalia Rutkowska - BIM School Course in KrakówNatalia Rutkowska - BIM School Course in Kraków
Natalia Rutkowska - BIM School Course in Kraków
 

PR 18 final ppt.pptx

  • 1. A6024 Product Realization 06/08/2022 DEPT. OF CSE(AI&ML) 1 VARDHAMAN COLLEGE OF ENGINEERING, HYDERABAD Autonomous institute, affiliated to JNTUH Fertilizer Recommendation System By 20881A6627 – K. Anuhya 20881A6660 – V. SiriChandana 21885A6603 –K. Sai Kishore Under the guidance of P.Swetha Dr. Prakash Kumar Sarangi 18
  • 2. Outline • Introduction • Literature Review • Need Statement and Community Partner details • Objectives • Existing System vs Proposed System • Software and Hardware Requirements • Proposed Methods and Algorithms • Construction of a model with a Picture • Result Analysis • Conclusion • References 8/25/2022 DEPT. OF ELECTRONICS AND COMMUNICATION ENGINEERING 2
  • 3. Introduction •Soil testing has been accepted as a unique tool for rational fertilizer use. •There are three main nutrients in the soil that play a major role in farming: Nitrogen (N), Phosphorous (P), and Potassium (K) collectively known as NPK. •The best possible recognition of these nutrients at starting stage is essential for the successful development of the harvest. •Effectively estimating these nutrients in the soil and characterizing them to recommend the fertilizer for the crop. 06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 3
  • 4. Literature Survey •In a research carried out by Zaminur Rahman a comparative study of several machine learning techniques has been carried out. •They have carried out the classification using the data of Telangana. Considered the six district soil data and used the geographical features for classification. • They have used k Nearest Neighbor, Bagged tree, and SVM finally compared the results of three algorithms and brought out a model for recommending fertilizers. •The accuracy obtained by these models is around 80%. 06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 4
  • 5. NEED STATEMENT •Farming part has a vital job in the Indian economy for GDP development in India. •But in recent years due to multiple fertilizers present in the market, farmers get confused and apply the fertilizer famous around their locality without a second thought. •This leads to two major problems low yield and soil pollution. Due to insufficient nutrients after applying fertilizers the yield of a crop is reduced. • Due to over-fertilization, the land, and food produced from the land will be polluted. •Fertilizer plays a major role in farming and contributes around 55% of the yield enhancement. 06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 5
  • 6. Community Partner Details Soil Testing Centres: • Soil tests are performed on the soil to determine the amount of Nitrogen(N), Phosphorus(P), and Potassium(K). •pH of the soil can also be determined by a soil test. •Soil test centers/laboratories are present in every district of Telangana in regional KVKs(Krishi Vigyan Kendras) offering free services. • The test results are then examined and certain conclusions and recommendations are made. 06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 6
  • 7. OBJECTIVES •To create an efficient recommendation system for fertilizers based on the NPK values of the soil. •To help the farmers to maximize the yield for the given crop cycle without affecting the land and soil properties. To ensure that healthy crops have been cultivated by reducing the chances of over-fertilization. •To create a user-friendly web application. 06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 7
  • 8. Existing System vs Proposed System EXISTING SYSTEM •Does not incorporate a web interface that makes it easier for users to access the system. •Only a few parameters are considered for prediction. •Not scalable to larger datasets. •Less accurate when compared to other similar systems. PROPOSED SYSTEM •We provide a web interface that makes it easier for users to access the system. •We considered 9 parameters of soil for prediction. •Scalable for large datasets. •Accuracy of the model is high when compared to other models. 6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 8
  • 9. Requirements Hardware • System with processor i3 or above. •RAM(4 GB). •Window OS Software •Flask •Heroku •Libraries like NumPy, pandas, matplotlib, seaborn, sci-kit learn. •HTML,CSS. 8/25/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 9
  • 10. Proposed Model • The data set contains 8 attributes Nitrogen, Phosphorus, Potassium, Temperature, Humidity, Moisture, crop type, soil type, and Fertilizer. •The data set is cleaned at this stage using the scikit-learn module. Any null values, Redundant values, or Missing values are eliminated at this stage. •Necessary steps like Label Encoding and Feature extraction and checking for the relationship between attributes, and outliers are done at this stage. •Random Forest, Naïve Bayes, and K-Nearest Neighbour are used to build a machine learning model. •The input is taken from the users/farmers and the prediction is using these algorithms and a suitable fertilizer is recommended. 6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 10
  • 11. Proposed Model 6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 11
  • 12. Proposed Model •Figure 2 shows the flow diagram of the fertilizer recommendation system. At first, the data sets are collected from Kaggle. •The dataset consists of 8 attributes Nitrogen, Phosphorus, Potassium, Temperature, Humidity, Moisture, crop type, soil type, and Fertilizer. •The dataset is then pre-processed by handling missing values and outliers. The data is fed to machine learning algorithms with different training and testing ratios. •The trained model is introduced to the users using a web interface where the user can give inputs to the model. •The model predicts the best fertilizer based on the given soil nutrient values. The inputs here are soil nutrients and environmental conditions. 6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 12
  • 13. Construction of the product •Flask is a web application framework written in python. •Heroku is a cloud hosting platform that uses AWS infrastructure with rapid scaling capabilities, offering flexible deployment services for all kinds of applications. •The website is constructed using Flask and it is deployed using Heroku. •The web application consists of fields such as attributes Nitrogen, Phosphorus, Potassium, Temperature, Humidity, Moisture, crop type, soil type, and Fertilizer. •The model is trained with different machine learning algorithms and it predicts the best fertilizer suitable for the soil and recommends it to the farmer through the web application. 6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 13
  • 14. Construction of the product 8/25/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 14
  • 15. Results and Analysis •The dataset is collected from Kaggle. The data is preprocessed and applied to the random forest, Naive Bayes, and k nearest neighbor classification algorithms. • In multiclass classification, the elements are classified into multiple classes. The random forest algorithm uses trees for classification. •The k-NN algorithms group the data based on the given number of neighbors. •The naïve Bayes algorithm separates the data into different classes according to the Bayes theorem. •These classification algorithms are trained and tested with the large datasets collected and the accuracies are noted in the below table. 6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 15
  • 16. Results and Analysis 6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 16
  • 17. Conclusion • Fertilizers used in agriculture contribute around 55% to the enhancement of crop yield. The fertilizer recommendation system will help farmers to choose the best fertilizer based on their properties. •This recommendation system will consider all these properties of soil along with the weather conditions such as temperature, humidity, soil type, and crop type and recommends the best fertilizer. • Datasets are collected and pre-processed in a python environment and different ML algorithms such as Naive Bayes, k-NN, and Random Forest are employed. • The Random Forest algorithm is functioning with the best accuracy of 98%. 6/8/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 17
  • 18. References 1. Silpa, C., RamPrakash Reddy Arava, and K. K. Baseer. "AGRI FARM: CROP AND FERTILIZER RECOMMENDATION SYSTEM FOR HIGH YIELD FARMING USING MACHINE LEARNING ALGORITHMS.“ 2. Subramanian, Kanaga Suba. (2020). Design and Implementation of Fertilizer Recommendation System for Farmers. 3. Hernández Moreno, Rafael, Olmer Garcia, and Luis Alejandro Arias. "Model of neural networks for fertilizer recommendation and amendments in pasture crops." (2018). 4. Shinde, Mansi, Kimaya Ekbote, Sonali Ghorpade, Sanket Pawar, and Shubhada Mone. "Crop recommendation and fertilizer purchase system." International Journal of Computer Science and Information Technologies 7, no. 2 (2016): 665-667. 06/08/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 18
  • 19. 8/25/2022 COMPUTER SCIENCE AND ENGINEERING(AIML) 19 THANK YOU