Abstract
This article uses machine learning technology to analyze the correlation of climate factors that affect crop yields, and conduct prediction and comprehensive evaluation to guide agricultural production. This paper selects early rice crops in Guangxi as the research object. Based on the climatic data of early rice planting areas in Guangxi from 1990 to 2017, a cart decision tree is constructed to generate a random forest model to analyze the correlation between early rice yield and climatic factors in each growth period, and obtain the various growth periods The ranking of the importance of climatic factors on the yield, thus forming the basis for calculating the weights of the climatic factors in each growth period of early rice; based on the climatic data in Guilin, Guangxi from 2008 to April to July 2017, predicted by the long and short-term memory network Guilin's various climate data from April to July 2018.
Highlights
Machine learning algorithms have demonstrated their capabilities in many fields
Applying machine learning algorithms to agriculture as well,reading large amounts of data and discovering internal laws and connections will be helpful to agricultural production.Random forest model[1] through continuous training on the data set, analysis can draw the importance of variables to the dependent variable.Long short-term memory network algorithm (LSTM) is an improvement of recurrent neural network [2]
(2)Traverse all the early rice meteorological yield fluctuation data A, calculate the Gini index of the value a of the climate factor data of all possible growth periods, and select the minimum Gini index e of D to make the data divided into two subsets to have a better effect
Summary
Machine learning algorithms have demonstrated their capabilities in many fields. Applying machine learning algorithms to agriculture as well,reading large amounts of data and discovering internal laws and connections will be helpful to agricultural production.Random forest model[1] through continuous training on the data set, analysis can draw the importance of variables to the dependent variable.Long short-term memory network algorithm (LSTM) is an improvement of recurrent neural network [2]. Its algorithm improvement effectively solves the former problem of gradient explosion. It is used in processing time series data and predicting unknown time series data.Has a very good effect [3].The purpose of training the data through the LSTM model is to discover the inherent laws in the time series data,so as to accurately achieve the prediction results,and make the weather forecasting of agricultural production more accurate
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
