Professional Documents
Culture Documents
Project Synopsis
<Version 1.0>
DEC, 2022
Table of Contents
1 Project Title.........................................................................................................................................3
2 Domain................................................................................................................................................3
3 Problem Statement.............................................................................................................................3
4 Project Description..............................................................................................................................3
4.1 Scope of the Work.......................................................................................................................3
4.2 Project Modules...........................................................................................................................3
5 Implementation Methodology............................................................................................................3
6 Technologies to be used......................................................................................................................4
6.1 Software Platform........................................................................................................................4
6.2 Hardware Platform......................................................................................................................4
6.3 Tools............................................................................................................................................4
7 Advantages of this Project...................................................................................................................4
8 Future Scope and further enhancement of the Project.......................................................................4
9 Team Details........................................................................................................................................4
10 Conclusion.......................................................................................................................................5
11 References.......................................................................................................................................5
1 Project Title
Harvestify
2 Domain
The domain of this project is to creating a web application using HTML, CSS JavaScript, and
Machine Learning for model building. The dataset is taken from authorized website Kaggle. We
are also using Python Flask Server which basically work between our web application and the
machine learning model. For Deployment of this website, we basically use Amazon AWS (EC2
Instance) which basically give a temporary URL to access it over the internet.
3 Problem Statement
The aim of this project is to determine the quality of crops, which fertilizer is used and
determine the environment condition and irrigation. It also determines which disease is caught
by a crop. It is a simple machine learning model. Also, it is beneficial in minimizing the overall
loses in production.
4 Project Description
Currently, agriculture is facing a hideous problem. Where in spite of all right knowledge
consumed, an agriculture sector is facing a huge loss. Why? To put simply the crops aren’t
supervised properly. classification analysis can help you with finding the right area for your
crop, further resulting to control damage and more revenue generation. To be able to
successfully yield crops, foremost and major key role is proper irrigation functionality. Machine
learning algorithm can help with better irrigation resulting in following ways – maintain a
desired soil water range in the root zone that is optimal for plant growth, low labor input for
irrigation process management.
Farming is about risk calculation – But what if the risk can be calculated and cured beforehand.
Anomaly analysis can help you with identifying the weakness and strength of the soil, resulting
in more revenue generation and saving ample amount of time.
“Climate is now a data problem,” says Claire Monteleoni. Earlier, Improper weather predictions
lead to many crops lost- resulting in loss of money and time invested. But technology has
evolved over years leading businesses to higher stable growth. Regression analysis will help you
with better production forecasting using weather conditions.
Harvestify is a machine learning model is used to predict which crop should be suitable for
harvesting, which fertilizer should be beneficial for the crop and in this we select a crop and
determine which disease is caught by this crop. As we know soil is combination of nitrogen,
Project Title: Page 3 of 8
TMU-FOE&CS Version 5.0 T001A-Project Synopsis
phosphorous and potassium, by knowing their quantity we can actually determine which
fertilizer is best suited for the crop. This project is very beneficial for the farmers as it saves the
most of the time of them by predicting three factors. If farmer get recommendation of what
quantity of nitrogen, phosphorus and potassium is used, then they save a lot of time and able
to guess what fertilizer will be used for good harvesting.
In this we use a python, anaconda, flask for backend and we use a HTML, CSS and Javascript for
the frontend. We take a dataset for prediction from Kaggle.
2. CROP:
This module gives the recommendation of type of crops to be cultivated which is best
suited for the respective conditions. There are several parameters from which we can
determine best crop used like – nitrogren, phosphorous, potassium, ph level, rainfall
and state. The use of coginitive technologies in agriculture could help determine the
best crop choice or the best hybrid seed choice for the a crop mix adapted to various
objectives, conditions and better suited for farm need.
This problem requires the use of several datasets since crop yield depends on many
different factors such as climate, weather, soil, use of fertilizer and seed variety.
3. FERTILIZER:
This module gives the recommendation of type of fertilizer best suited for the particular
soil and the recommended crop. After recommending a crop now we have to select
which fertilizer is suitable for that crop. This is the main task as this decide that the
fertilizer is suitable or not.
As we know that soil is the combination of nitrogen, potassium and phosphorous.
There proper quantity makes the soil fertile. So, by knowing the exact quantity of these
three components the farmer can easily predict which fertilizer will be beneficial for
them. As this saves a lot of time of farmers and make their work easy.
To determine the fertilizer, we should have a data of these three components and also
the data of crop type, soil type, temperature and moisture. Using these data machine
learning model is created and model is trained.
4. DISEASE:
Crop disease are a major threat to food security, but their rapid identification remains
difficult in many parts of the world due to the lack of necessary infrastructure.
This module predicts the name and causes of crop diseases and give suggestions to cure
it. In this we take data from dataset where different aspects and solution will be given to
cure the disease which is caused by crop.
Most of the farmer are unable to determine the cause of disease in the crop because of
that they may get huge amount of loss.
The machine learning approaches such as SVM, K-NN and CNN are used to distinguish
diseased or non-diseased leaf. The analysis of the proposed model is well suited for CNN
machine learning classification technique with a desired accuracy compared to other
state of the art method.
5 Implementation Methodology
In this firstly we determine the crop which is suited for harvesting and then we find the fertilizer that
best suited for the crop and we find the any disease caught by the crop. We find the solution to cure the
disease.
List of Crops
Data
store
Input from
Acquiring input from
farmers
farmers
Mapping of data
6 Technologies to be used
6.1 Software Platform
a) Front-end
Html
CSS
Javascript
Bootstap
b) Back-end
Python
Flask
Machine learning model
6.3 Tools
9 Team Details
10 Conclusion
<Guidelines: The write-up must end with the concluding remarks-briefly describing innovations
in the approach for implementing the Project, main achievements and also any other important
feature that makes the system stands out from the rest. >
11 References
<Guidelines: Give references. Example: Books referred, website URL, any other >