FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215035018> ?p ?o ?g. }

• W3215035018 abstract "One key issue in the agricultural sector of any developing country is that of low yield. The yield per farm from a developing country is around 30% less than that of developed countries. The key reasons for such low yield are decrease in soil fertility due to inappropriate utilization, continuous use of pesticides, loss due to poor weather conditions, inappropriate crop for the farm land, lack of awareness about best farming technologies etc [1]. As per a world bank report, the three important agricultural challenges for India are raising agricultural productivity per unit of land, reducing rural poverty through a socially inclusive strategy that comprises both agriculture as well as non-farm employment and ensuring that agricultural growth responds to food security needs [2]. Recent developments are contributing to precision farming in India where technology is available for weather stations [3], soil proximity prediction [4], smart irrigation systems [5], etc. Optimal yield will have an impact on the profit and thus on a farmer's ability to continue with his farming. The Centre for Study of Developing Societies (CSDS) based in Delhi found that given an option majority of farmers in the country would prefer to take up some other work. Poor income, bleak future and stress are the main reasons why they want to give up farming [6]. Precision farming or smart farming has the capability to support better yield generation [7]. Machine learning [10] methods such as convolutional neural networks [11], regression analysis [12], deep neural networks [13] etc. have been used for yield predictions. Big data and data mining methods also have been adopted for yield prediction [14]. However, smart farming methods available in the market has not reached majority of the farmers due the cost involved in employing such technologies [8]. At the same time, many farmers in rural India possess abundant historical knowledge about farm practices such as crop rotation which leads to balanced chemical composition of the soil and thus better yield [9]. Many of these technological solutions depend of scientific data pertaining to soil properties, weather forecasting, nutrient information etc [15,16,17,18]. There is no or very less work done, according to best of our knowledge, on making suggestions crop rotation for optimum yield.In our proposed solution, soil chemical property data, weather data, yield and crop rotation data are collected from different sources as given in Table 1.Table 1.DataSourceSoilhttp://dataverse.icrisat.org/dataset.xhtml?persistentId=doi:10.21421/D2/QYCEGRWeatherhttp://dataverse.icrisat.org/dataset.xhtml?persistentId=doi:10.21421/D2/B3NNUBCrophttps://www.kaggle.com/abhiseklewan/crop-production-statistics-from-1997-in-india/dataCrop RotationExtracted from https://www.kaggle.com/abhiseklewan/crop-production-statistics-from-1997-in-india/data The data obtained from different sources were in different format and was for varied timelines. At first, the weather data was shrotened for years from 1998 to 2014 so as to match with crop statistics data. The weather and crop statistics data were pruned to match the locatiion of soil data. The entire data was normalized as part of data pre-processing step as given in Fig 1. Three different classification algorithms such as K-Means Clustering, Multiple Linear Regression Model and Decision Tree Classification Model are applied on the normalized data, as depicted in Fig 2. The results from these three models are ensembled using simple voting to increase the accuracy of crop suggestion and yield prediction.The novelty of the proposed solution is as follows.Crop suggestions based on weather forecast, soil properties, nutrient supply and historical crop rotation dataMachine learning based yield prediction about the suggested crop" @default.
• W3215035018 created "2021-12-06" @default.
• W3215035018 creator A5003495566 @default.
• W3215035018 creator A5048017229 @default.
• W3215035018 creator A5066549983 @default.
• W3215035018 date "2021-10-09" @default.
• W3215035018 modified "2023-09-24" @default.
• W3215035018 title "Crop Rotation Suggestions using Machine Learning for Better Yield" @default.
• W3215035018 cites W2200121095 @default.
• W3215035018 cites W2221746568 @default.
• W3215035018 cites W2532686361 @default.
• W3215035018 cites W2550552207 @default.
• W3215035018 cites W2732692660 @default.
• W3215035018 cites W2809602495 @default.
• W3215035018 cites W2891765392 @default.
• W3215035018 cites W2977331688 @default.
• W3215035018 cites W3098019734 @default.
• W3215035018 hasPublicationYear "2021" @default.
• W3215035018 type Work @default.
• W3215035018 sameAs 3215035018 @default.
• W3215035018 citedByCount "0" @default.
• W3215035018 crossrefType "journal-article" @default.
• W3215035018 hasAuthorship W3215035018A5003495566 @default.
• W3215035018 hasAuthorship W3215035018A5048017229 @default.
• W3215035018 hasAuthorship W3215035018A5066549983 @default.
• W3215035018 hasConcept C118518473 @default.
• W3215035018 hasConcept C120217122 @default.
• W3215035018 hasConcept C128383755 @default.
• W3215035018 hasConcept C134121241 @default.
• W3215035018 hasConcept C144133560 @default.
• W3215035018 hasConcept C162324750 @default.
• W3215035018 hasConcept C166957645 @default.
• W3215035018 hasConcept C175444787 @default.
• W3215035018 hasConcept C181622380 @default.
• W3215035018 hasConcept C189326681 @default.
• W3215035018 hasConcept C191897082 @default.
• W3215035018 hasConcept C192562407 @default.
• W3215035018 hasConcept C204983608 @default.
• W3215035018 hasConcept C205649164 @default.
• W3215035018 hasConcept C48824518 @default.
• W3215035018 hasConcept C50522688 @default.
• W3215035018 hasConcept C549605437 @default.
• W3215035018 hasConceptScore W3215035018C118518473 @default.
• W3215035018 hasConceptScore W3215035018C120217122 @default.
• W3215035018 hasConceptScore W3215035018C128383755 @default.
• W3215035018 hasConceptScore W3215035018C134121241 @default.
• W3215035018 hasConceptScore W3215035018C144133560 @default.
• W3215035018 hasConceptScore W3215035018C162324750 @default.
• W3215035018 hasConceptScore W3215035018C166957645 @default.
• W3215035018 hasConceptScore W3215035018C175444787 @default.
• W3215035018 hasConceptScore W3215035018C181622380 @default.
• W3215035018 hasConceptScore W3215035018C189326681 @default.
• W3215035018 hasConceptScore W3215035018C191897082 @default.
• W3215035018 hasConceptScore W3215035018C192562407 @default.
• W3215035018 hasConceptScore W3215035018C204983608 @default.
• W3215035018 hasConceptScore W3215035018C205649164 @default.
• W3215035018 hasConceptScore W3215035018C48824518 @default.
• W3215035018 hasConceptScore W3215035018C50522688 @default.
• W3215035018 hasConceptScore W3215035018C549605437 @default.
• W3215035018 hasIssue "01" @default.
• W3215035018 hasLocation W32150350181 @default.
• W3215035018 hasOpenAccess W3215035018 @default.
• W3215035018 hasPrimaryLocation W32150350181 @default.
• W3215035018 hasVolume "1" @default.
• W3215035018 isParatext "false" @default.
• W3215035018 isRetracted "false" @default.
• W3215035018 magId "3215035018" @default.
• W3215035018 workType "article" @default.