Authors: Ayushi Kumari Singh, Charu Patidar, Anjali Mukati, Siddhi Singh, Aayushi Gurjar, Aditya Medatwal, Priyanshu Singh
Certificate: View Certificate
The objective of this study is to design a recommendation system which will be based on previous weather data by applying machine learning algorithms which will provide the Idea about what kind of weather will be in upcoming days and with this prediction it will also suggest suitable kind of vegetation (crops/flowers/vegetables) they can grow in that particular condition.
In Today’s world each and every industrial and business sectors are connected with the modern technologies but the agriculture sector is the only one which is very slowly getting connected to these despite of being the occupation of most of the Indian people. Our project’s idea mainly focuses to bring the technologies in the field of agriculture in order to help farmers excel in their field of occupation which will ultimately increase their profits and productivity. Automating agricultural aspects is a mechanical process with or without human intervention in agriculture. Due to less space of domestic lands, it has become an important area of choosing the most suitable crops based on prevailing factors in the selected area. Even though there are enough knowledge, techniques, and methods which are done manually available in agriculture, there is not any system in which the environmental factors are detected and suggests the user which crop type is best for farming. It has been a major problem to identify what to grow, any man has adequate space in the owner’s land. Not only domestic lands but also for farming lands. Why it has become a problem is that environmental factors such as temperature, water levels, and soil conditions are uncertain as they change from time to time. Due to these problems, this solution of crop recommendation system predicts the user, what crop type would be the most suitable for the selected area by collecting the environmental factors for plant growth and processing them with the trained sub-models of the main of the system. Unlike earlier days modern farms and agricultural operations are now taking place totally differently than those many decades ago, primarily due to advancements in technology. Using these technologies and the data of previous methods of agriculture and farming we can help farmers excel in their field of occupation which will ultimately increase their profits and productivity. This data that is gathered are processed by algorithms and statistical data which will be understood and helpful to farmers for decision makings and keep track of their farms. The more inputs and statistical data collected, and higher the algorithmic rule is at predicting the outcomes. And the aim is that farmers will use these technologies to attain their goal of improved harvest by creating better selections within the field. Recommender systems are software agents that elicit the interests and preferences of individual consumers and make recommendations accordingly. These are basically the systems that recommend things like music, videos, books, shopping items, and even people. They have the potential to support and improve the quality of the decisions users make while searching for and selecting things. They have become overly popular in the recent times with their presence and increase in their use on almost every platform. We are trying to apply this technology in agricultural field also so that choices in this occupation also increase.
II. LITERATURE SURVEY
Agriculture and farming are mostly dependent on weather and climatic conditions. For each and every activity involved in agriculture, the present and the future climatic conditions play a major role in the yields and production of that particular field. With the rapid climatic changes occurring now like extreme heat and cold weather conditions are damaging and ruining the crops and any other vegetation present in the field.
But with the advent of technologies this problem of unpredictable, erratic and harsh weather can be reduced to an extent if machine learning and its algorithms are utilized properly in the field of agriculture so that the unpredictable weather now becomes predictable and now farmers can take decisions more accurately based on the climatic and weather factors. Also the farmers are blindly following the old traditional methods of farming where they use the same methodology which was in trend years ago. For example: They have limited knowledge about what all kind of vegetations they can grow in their fields the same which was used by their forefathers. This limits their profits and production of their yields to a certain extent. For solving these problems our team has finded a solution which will not only introduce them to predictable weather conditions based on their location but also will pave the way of having knowledge about different kind of vegetations they can sow based on weather conditions for a specific location. For this solution to come to existence, doing research about such kind of projects that provide the same solution are necessary so that we can get an idea what others have done on this issue, what kind of technologies and implementations have been done by the people earlier regarding this same topic so that we can get help in our project and also one more benefit is that we could avoid repeating same mistakes which have been done by them in their projects.
B. Related Work
India is a country having the second largest population in the world and majority of people in India have agriculture as their occupation. Indian Farmers despite having the responsibility of feeding 1.3 billion people are still using the older, traditional, unproductive methods of farming. But now the weather and climatic conditions are not the same as they were in previous decades. Because of contionously changing weather and its unpredictable nature and also farmers still sticking to the older methods, they are the ones who are mostly affected and are facing huge losses like their crops getting ruined etc. A solution is needed for solving this issue. Our project can be the solution for this problem as it aims at selection of vegetation for a particular area based on the weather and climatic conditons of that area. So now with the help of our system farmers can be on a safer side and can take decisions independently based on the facts and figures which will ultimately reduce their losses and increase their productions and profits. For this project our team has sought out and studied various research papers, documents, and newspapers and magazine articles from various scenes which were similar to our project. The ultimate goal of the previous all research papers is the same as ours which is to predict the best suitable crop type because everyone is familiar with the problems and complications which are currently being faced in the field of agriculture. But the approach which are being applied for selection of best crop for a particular place by the researchers are different. Some are choosing land conditions as the important factor for deciding of the crop like in a research paper which was published in august 2020 titled “crop prediction using machine learning approaches” also states the same problem which is mentioned above that farmers are growing same crop repeatedly without trying out the new varieties of crop which is the same as earlier told but the new problem which they stated is that they are applying fertilizers in random quantity without knowing the deficient content and quantity. So, this is directly affecting the crop yield and is also causing the soil acidification which damages the top layer and makes it less fertile for next use. The basic idea of theirs matches with ours but the solution which they have proposed in the paper is different. They have made a system which works on machine learning and artificial intelligence. Their designed system will recommend the most suitable crop for particular land. Based on weather parameter and soil content such as Rainfall, Temperature, Humidity and pH. The system recommends the crop for the farmer and also recommends the amount of nutrients to be add for the predicted crop. The system has some other specification like displaying approximated yield in q/acre, required seed for cultivation in kg/acre and the market price of the crop. In their system they have develop two algorithms : one is for rainfall prediction and another for crop prediction. Then with result of these two they will combine the land conditions and then will finally give the ouput result. Another research paper of the year 2021 states the problem that to produce mass quantity of crops people are using technology in an exceedingly wrong way. New sorts of hybrid varieties are produced day by day. However, these varieties don’t provide the essential contents as naturally produced crop. These unnatural techniques spoil the soil. It all ends up in further environmental harm. But when the producers of the crops know the accurate information on the crop yield it minimizes the loss. This paper focuses mainly on predicting the yield of the crop by applying various machine learning techniques. Machine learning, a fast-growing approach that’s spreading out and helping every sector in making viable decisions to create the foremost of its applications .The main concept is to increase the throughput of the agriculture sector with the Machine Learning models. But using machine learning and Using past information on weather, temperature and a number of other factors the information is given. In the Application which they developed, runs the algorithm and shows the list of crops suitable for entered data with predicted yield value. Whereas some research work are focused on selection of crop depending upon rainfall prediction for choosing of best suitable crop available.
Every research paper work aims at selection of best suitable crop keeping in mind the problems and difficulties faced by the farmers in today’s era of farming but the idea, approach and system design using machine learning are different. Some of the work of the papers depends on land for selection, some depend on rain, some focus only on particular weather for selection of crop while some focus on particular crop based on weather. But our system keeps in mind the location, type of crop as well as the future weather conditions for the best selection of crop suitable which makes our idea different from others. Presently our farmers are not effectively using technology like machine learning and artificial intelligence and analysis, and also before selecting any plant to grow it is important to have the knowledge and an understanding of the factors that affect the cultivation. So there may be a chance of wrong selection of crop for cultivation that will reduce their income and increase the chance of losses. To reduce those type of loses we will be developing a system which aims at selection of vegetation (crops/flowers/vegetables) on the basis of weather and seasonal conditions of that particular decided area .So, this makes the farmers to take right decision in selecting the crop for cultivation such that agricultural sector will be developed by innovative idea. And the farmers will always be on a safer side whether it is choosing of correct crop or whether it be the harshest of harsh weather.
III. SYSTEM REQUIREMENT SPECIFICATION
A. Hardware Requirements
Processors: Intel Atom® processor or Intel® Core™ i3 processor.
Disk space: 1 GB
B. Software Requirements
Operating systems: Windows* 7 or later, macOS, and Linux.
Python versions: 2.7.X, 3.6.X. , Jupyter Notebook
IV. SYSTEM ANALYSIS AND DESIGN
a. System Design
2. Activity Diagram: Main activities for each of the service provided are described by an activity diagram. This activity diagrams deal with the workflows of the recommender system. The work flows are depicted in sequence and often have conditions specified on the control-flow lines. The diagram is accompanied by the description, the initiator of the activity and the workflow. The initiator is generally a function module that gets called when an activity starts.
3. Sequence Diagram: The sequence diagrams are one of the interaction diagrams that depict the communication between the objects. The collaboration of objects is modelled based on a time sequence. The objects involved in the scenario pass messages between themselves. Here the return messages are not shown but are to be understood as implicit. The diagram below is basically asynchronous way of communication as in the recommender system the similarity scores are to be computed asynchronously without the user having to wait for long.
4. Subsystem Class Design: The class diagrams describe the structure of the system being modelled. They are the building blocks so to speak for object oriented modelling as with them comes all the object oriented concepts that exist among various individual components of the system. The three compartment figure of classes holds the name, the list of attributes and the operations.
5. Entity-Relationship Diagram: ER Diagram stands for Entity Relationship Diagram, also known as ERD is a diagram that displays the relationship of entity sets stored in a database. In other words, ER diagrams help to explain the logical structure of databases. ER diagrams are created based on three basic concepts: entities, attributes and relationships. ER Diagrams contain different symbols that use rectangles to represent entities, ovals to define attributes and diamond shapes to represent relationships.
V. FUTURE WORK
At this point of time, we are only able to predict weather one feature of weather. Future work can involve perfecting present algorithm on different features so that it can give accurate weather result in order to recommend best crops for cultivation.
Our sole motive of this project is to open more opportunities for farmers by connecting them to the modern technologies which will contribute in changing the traditional methods of farming done at present to the newer and more advance level.
 Shivam Tandon, Pawan Kumar Singh, Abhishek Patel, “Weather Prediction Using Machine Learning”, SSRN papers,2021 , Pages 1-5 .  Nischitha K, Dhanush Vishwakarma, Ashwini, Mahendra N, Manjuraju M.R, “Crop Prediction using Machine Learning Approaches”, http://www.ijert.org ,2020, Pages 1-4 .  Anakha Venugopal, Aparna S, Jinsu Mani, Rima Mathew, Vinu Williams , “Crop Yield Prediction using Machine Learning Algorithms”, IJERT ,2021, Pg 1-5 .  Shubhangi Bangar, Priti Sonawane, Apurva Bangane, “Crop Prediction and Weather Detection”, www.ijsdr.org, 2020, Pages 1-2 .  S. Bangaru Kamatchi, R. Parvathi, “Improvement of Crop Production Using Recommender System by Weather Forecasts”, https://www.researchgate.net/, 2019, Pages 1-9 .  Pradeepa Bandara, Thilini Weerasooriya, Ruchirawya T. H., W.J.M. Nanayakkara ,Dimantha M.A.C, Pabasara M.G.P, “Crop Recommendation System”, https://www.researchgate.net/ , 2020, Pages 1-4  Piyush Pathak, Rushikesh Phalke, Parag Patil, Pratik Prakash, Shilpa Bhosale, “Survey on Crop Suggestion Using Weather Analysis” , https://www.irjet.net/, 2020, Pages 1-3 .  Madhusree Kuanr , Bikram Kesari Rath, Sachi Nandan Mohanty, “Crop Recommender System for the Farmers using Mamdani Fuzzy Inference Model ”, International Journal of Engineering & Technology, 2018 .  Juraj Bartok, Ondrej Habala, Peter Bednar, Martin Gazak, Ladislav Hluchý, “Data mining and integration for predicting significant meteorological phenomena”, https://www.sciencedirect.com/ ,2010, Pages 1-10 .  Mihai DOINEA, Catalin Boja, “MACHINE LEARNING TECHNIQUES FOR DATA EXTRACTION AND CLASSIFICATION IN COMPUTER VISION SOFTWARE”, https://www.researchgate.net/, 2014, Pages 1-6.
Copyright © 2022 Ayushi Kumari Singh, Charu Patidar, Anjali Mukati, Siddhi Singh, Aayushi Gurjar, Aditya Medatwal, Priyanshu Singh. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.