Using Machine Learning Techniques to Select Crop

Abstract

Farming helps meet people\'s essential requirements and development by giving food, clothing, safe houses, medication, and amusement. Consequently, agriculture is the most basic venture on the globe. Agriculture provides food, feed, fiber, fuel, furniture, unrefined substances, and materials for and from production lines; gives free toll and new environs, bountiful nourishment for driving out shortage; favours kinship by taking out contest. One reason for the deficiency of food the nation over can be the decision of improper crop for development. The proposed task will contain data on various products and will recommend the granger crop, which is appropriate for development given the geographic region and climatic statuses like temperature, dampness, and moistness, by utilizing various sensors

Introduction

I. INTRODUCTION

Farming assists with meeting the necessities of individuals and their human advancement by giving supplements, clothing, asylums, medication, and diversion. Consequently, horticulture is the leading venture on the planet. It is a valuable entire where the unconditional gifts of nature, specifically land, light, air, temperature and water, and so forth, are coordinated into a solitary essential unit basic for people. Auxiliary functional units to be specific creatures, including domesticated animals, birds, and bugs, feed on this necessary structure impedes and give concentrated items like meat, milk, fleece, eggs, honey, silk, and ribbon. Accordingly, the term horticulture implies the development of land. i.e., the science and specialty of delivering harvests and domesticated animals for financial purposes. It is additionally alluded to as the study of creating yields and domestic animals from the average assets of the earth. The essential point of horticulture is to make the land produce all the more richly and simultaneously to shield it from disintegration and abuse. It is inseparable from cultivating the creation of food, feed, and other modern materials. India is the biggest maker and buyer of harvests on the planet, establishing 75% of world creation and consuming 90 % of the world creation. The change in development from heartbeats to business crops and the absence of mechanical advancements to increment yields has ruined the ascent in work. UP, Orrisa, Maharashtra, and Karnataka are the producers. Among these, Maharashtra is the biggest maker of products which establishes around 34%, and these four states contribute almost 70% of complete results in the country.

Crop creation relies on ashore factors, such as soil combination piece, precipitation, area, soil type, temperature, etc.  These elements accept a critical occupation in growing harvest yield.  Similarly, financial circumstances impact the crop(s) to build the most impressive benefit.  To expect alone collect to deliver the most critical work with the most outrageous advantage, we should think about every one of the variables.

The AI Java API used in the framework is WEKA. WEKA is available as a tool that comes as a GUI, similarly to CLI. In any case, since we are managing it with our framework, we will utilize the 'weka-api.jar' API. Waikato University was organized in New Zealand to facilitate different AI analyses into one spot. We have used various algorithms in our framework: SVM and Naïve Bayes Classifier, and an output sequencing computation are used for classification.

II. PROPOSED WORK

Considering the crop analysis strategy described in [1], we propose two different harvest choice methods, a widely inclusive work [1].

The proposed plans are:

1. Selection technique
2. Sequencing technique

The factor variable is one of the essential elements which expect a critical occupation in choosing crops. For instance, two harvests produce indistinguishable yields, yet one yield is respected at a lower cost than the other. If the value variable is prohibited from the yield determination strategy, the framework might provoke choosing a misguided harvest to create. Subsequently, the expense is as high as the variables, such as soil type, precipitation, temperature, etc.

The harvest selector first picks the output which suits the given soil type. Once more, crops are filtered through by taking a gander at the current time (for example, Month) with crop establishing time. A collection of products with an exceptional output rate is picked from that.

Finally, we want to choose a specific combination of proposed crops. Every crop has a colossal number of varieties, different from farm days, drowned yield rate, rainfed yield rate. To choose the proper grouping, we check the combinations, which all are sensible for the new to the scene season (for instance, samba, kuruvai, etc.) and the current region. From that arrangement, pick the mixture which gives the prime output rate.

Rest API uses four simple HTTP techniques: GET, POST, PUT, and DELETE. Servlet gets the request and chooses the java controllers for every sale. Each java overseer plays out the business reasoning using data set aside in the data set. MySQL server plays out the data change among server and data set. Finally, the server re-establishes the JSON response, interpreted on the client-side. The designing layout shows up in Figure 2

A. Selection Technique

This paper helps clients with the strategy that would assist them with picking the yield that will augment by taking into retainer every one of the boundaries that influence the harvest's development. Can dissect the different ecological, monetary, and other boundaries connected with the yield in nature to anticipate an exact resultant job. The economic boundaries incorporate interest for the harvest, market rate, and so on, while ecological limits contain the amount of precipitation, temperature, and soil type. So, many elements are considered while anticipating the most proficient harvest to be developed in light of the season [3]. The dataset may resemble this, as shown up in Table - 1.

Table 1: Crop Selection method Dataset

Notwithstanding certain exceptional cases, for instance, there are different harvest conditions and gives up or changes in properties seen using various soil types. For example, when jute is grown in sandy soil, the fiber gets rough; however, it gets tenacious when set in clayey soil. We have ensured before going on with the harvest determination technique.

We have used WEKA Classifiers and backslide techniques to unequivocally expect the best crop(s) to be created in that season. There are many more features, such as wetness, soil food regard, pH, etc., which are associated with the planning dataset. However, for convenience, simply the major impacting features are displayed in the portrayal. Crop Sequencing Method:

It uses a crop sequencing calculation to propose the crop(s) progression in light of crop rate and market costs. Expenses of the harvests are genuinely poor upon the yield speeds of the harvests. Like this, the item's cost is quite possibly the essential component in proposing the harvest gathering, depending on accessible expenses. Table-2 is a portrayal of the dataset used for the yield sequencing technique.

Here, the result and expenses could change uninhibitedly per the climatic and monetary circumstances. These are just the normal, expected characteristics we have used for assessment. In the Crop Sequencing Method, we have been utilized sets (some place almost two than two) of the crop(s) as a promise to our calculation (the social occasion could consolidate something like one than one harvest), which gives alone set as yield. The Crop Sequencing assessment proposes the most reasonable blueprint of the crop(s) all through the entire season, considering the reap's yield rate and expenses (s). Condition 1 explains the calculation.

This explained above works in light of the fact that the normal result rate resembles the market costs. The 'select Factor' implied in the examination results from the normal result rate and current market cost of that specific harvest. This makes us set up our suppositions concerning the yield rate and the market costs. This is one of the star assessments used in our calculation structure. The select component for each collect could vary.

Conclusion

Since the yield of residence significantly depends upon the harvest chosen for advancement and environmental boundaries along these lines, authentic choice of produce before the story is fundamental in developing. Since the number of farmer suicides has been extending bit by bit, this framework can help expect crop groupings similarly to enhancing yield rates and related cash benefits to the farmers. In like manner, planning AI with agribusiness in predicting crop sicknesses, specific water framework plans, thinking about crop re-enactments, etc., can incite further movements in horticulture by helping yield and propelling the use of resources included.

References

[1] Jain, N., Kumar, A., Garud, S., Pradhan, V., & Kulkarni, P. (2017). Crop selection method based on various environmental factors using machine learning. International Research Journal of Engineering and Technology, 4(02). [2] Yesugade, K. D., Kharde, A., Mirashi, K., IMuley, K., & Chudasama, H. (2018). Machine learning approach for crop selection based on agro-climatic conditions. Machine Learning, 7(10). [3] Rakesh Kumar, M.P. Singh, Prabhat Kumar and J.P. Singh,”Crop Selection Method to Maximize Crop Yield Rate using Machine Learning Technique” 2015 International Conference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials (ICSTM), 6 - 8 May 2015. pp.138-145. [4] M. Young, The Technical Writer’s Handbook. Mill Valley, CA: University Science, 1989. [5] Karandeep Kaur,” Machine Learning: Applications in Indian Agriculture”. International Journal of Advanced Research in Computer and Communication Engineering Vol. 5, Issue 4, April 2016. [6] Miss.Snehal, S.Dahikar, Dr.Sandeep V.Rode, ”Agricultural Crop Yield Prediction Using Artificial Neural Network Approach”. International Journal ofInnovative Reasearch in Electrical, Electronic, Instrumentation and Control Engineering, Vol. 2, Issue 1, January 2014. [7] Chlingaryan, A., Sukkarieh, S., & Whelan, B. (2018). Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review. Computers and electronics in agriculture, 151, 61-69. [8] Park, S., Im, J., Jang, E., & Rhee, J. (2016). Drought assessment and monitoring through blending of multi-sensor indices using machine learning approaches for different climate regions. Agricultural and forest meteorology, 216, 157-169. [9] Thoranin Sujjaviriyasup, “Agricultural Product Forecasting Using Machine Learning Approach”. Int. Journal of Math. Analysis, Vol. 7, 2013, no. 38, 1869 – 1875. [10] Anastasiya Kolesnikova, Chi-Hwa Song, Won Don Lee,” Applying UChooBoost algorithm in Precision Agriculture”. ACM International Conference on Advances in Computing, Communication and Control, Mumbai, India, January 2009. [11] Krishna Kumar, K. Rupa Kumar, R. G. Ashrit, N. R. Deshpande and J. W. Hansen,” Climate Impacts on Indian Agriculture”. International Journal of climatology, 24: 13751393, 2004. [12] Raorane A.A., Kulkarni R.V.,” Data Mining: An effective tool for yield estimation in the agricultural sector”. International Journal of Emerging Trends & Technology in Computer Science (IJETTCS) Volume 1, Issue 2, July August 2012.

Copyright

Copyright © 2022 Aarav Mangla. 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.