International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 02 | Feb -2017
p-ISSN: 2395-0072
www.irjet.net
Crop Selection Method Based on Various Environmental Factors Using Machine Learning Nishit Jain1, Amit Kumar2, Sahil Garud3, Vishal Pradhan4, Prajakta Kulkarni5 1Student,
Dept. of Information Technology, RMDSSOE, Pune, Maharashtra, India Dept. of Information Technology, RMDSSOE, Pune, Maharashtra, India 3Student, Dept. of Information Technology, RMDSSOE, Pune, Maharashtra, India 4Student, Dept. of Information Technology, RMDSSOE, Pune, Maharashtra, India 5Professor, Dept. of Information Technology, RMDSSOE, Pune, Maharashtra, India 2Student,
-------------------------------------------------------------------***------------------------------------------------------------------------
Abstract - These India is an agriculture based economy
been the widely accepted language for experimenting in machine learning area. Machine learning uses historical data and information to gain experiences and generate a trained classifier by training it with the data. This classifier then makes output predictions. The better the collection of dataset, the better will be the accuracy of the classifier. It has been observed that machine learning methods such as regression and classification perform better than various statistical models.
whose most of the GDP comes from farming. In an economy where most of the produced food is from agriculture, selection of crop(s) plays a very important role. In light of the decreasing crop produce and shortage of food across the country which also has been consequence of bad crop selection and thus, leading to increasing farmer suicides, we suggest a method which would help suggest the most suitable crop(s) which will maximize yield by summing up the analysis of all the affecting parameters. [2] These affecting parameters can be economical, environmental as well as related to yield in nature. Economic factors such as market prices, demand etc. play a very significant role in deciding a crop(s) as does the environmental factors such as rainfall, temperature, soil type and its chemical composition and total produce. Therefore, it’s necessary to design a system taking into consideration all the affecting parameters for the better selection of crop(s) which can be grown over the season.
Crop production is completely dependent upon geographical factors such as soil chemical composition, rainfall, terrain, soil type, temperature etc. These factors play a major role in increasing crop yield. Also, market conditions affect the crop(s) to be grown to gain maximum benefit. We need to consider all the factors altogether to predict a single crop so that it produces maximum yield with maximum benefit. The machine learning Java API used in the system is WEKA. WEKA is also available in the form of a tool which comes as a GUI as well as CLI. But, since we are integrating it with our system, we will be suing ‘weka-api.jar’ API. The full form of WEKA is Waikato Environment for Knowledge Analysis which was designed by Waikato University based in New Zea Land for integrating various machine learning algorithms into one place. Various Algorithms which we have used in our system are Classification using Support vector machines and Naïve Bayes Classifier and a crop sequencing algorithm.
Key Words: Crop Selection Method, Crop Sequencing Method, WEKA, Classification, Select Factor.
1. INTRODUCTION Agriculture plays a very important role where economic growth of a country like India is considered. In a scenario crop yield rate is falling consistently, there is a need of smart system which can solve the problem of decreasing crop yield. For farmers, it’s such a complex when there is more than one crop to grow especially when the market prices are unknown to them [1]. Citing the Wikipedia statistics, the farmer suicide rate in India has ranged between 1.4and 1.8 per 100000 total population, over a 10-year period through 2005. While 2014 saw 5650 farmer suicides, the figure crossed 8000 in 2015. Therefore, to eliminate this problem, we propose a system which will provide crop selection based on economic, environmental and yield rate to reap the maximum yield out of it for the farmers which will sequentially help meet the elevating demands for the food supplies in the country.
2. RELATED WORK Predicting agricultural product plays a very important role in agriculture. It helps in increasing net produce, better planning and gaining more profits. [1] Crop selection thus, is a very difficult task when you have more than a single crop to grow and hence, a crop selection algorithm is devised to decide the crop(s) to be grown over a season on the basis of yield. This method also suggests which sequence of crop(s) should be grown over the growing season to reap the maximum benefits out of it. When all the factors are analyzed together using machine learning, then we can predict more accurate future values rather than relying upon
The system uses machine learning to make predictions of the crop and Java as the programming language since Java has
© 2017, IRJET
|
Impact Factor value: 5.181
|
ISO 9001:2008 Certified Journal
| Page 1530