Abstract: Agriculture plays a predominant role in the economic growth and development of the country. The major and serious setback in the crop productivity is that the farmers do not choose the right crop for cultivation due to lack of information of soil contents and environmental factors. In order to improve the crop productivity, a crop recommendation system is to be developed that uses the classification techniques of machine learning. Agricultural domain has imbibed the machine-learning algorithm to produce efficient, effective solutions to the difficulties faced by the farmers. Some problems that identified in already implemented systems is that they concentrated on a single parameter (either weather or soil) for predicting the suitability of crop growth. However, in our opinion, both these factors should be taken together into consideration for the best and most accurate prediction for the crops. This is because, a particular soil type may be fit for supporting one type of crop, but if the weather conditions of the regions are not suitable for that crop type, then the yield will suffer. Similarly, there may be a case where the weather conditions are favorable but soil characteristics are not matching and, in some cases, farmers may face surplus problem if all the farmers from the region will grow the same crop.
To eliminate the above-mentioned drawbacks, we have proposed the system which provides a solution for Smart Agriculture by monitoring the agricultural field which can assist the farmers in increasing productivity to a great extent. We have proposed the system in the form of a website. The system integrated into two techniques. For the first technique, we have made use of 'Crop Features Data Set’, This dataset encompasses rainfall, temperature, soil PH and humidity for particular crop and predicting crop using random forest classifier. For suggestions of crops soil type is vital factor, system is capable to predict soil type using teachable machine technique. To recommend the best crop system considered some other parameters like environmental characteristics, rainfall, soil characteristics (N, P, K, type), location, season etc. so by considering these parameters system provides farmers variety of options of crops that can be cultivated. For appropriate choice of crop user can see the previous prices of crop. Thus, our proposed system would help the farmers to make the right choice of crop suitability.
Keywords: Machine Learning, Random Forest, Teachable Machine, Crop Recommendation.
|
DOI:
10.17148/IJARCCE.2021.101222
