scholarly journals Crop Yield Prediction using XG Boost Algorithm

2020 ◽  
Vol 8 (5) ◽  
pp. 3516-3520
Keyword(s):  
Crop Yield ◽  
Tamil Nadu ◽  
Crop Yields ◽  
Absolute Error ◽  
Climatic Conditions ◽  
Support Vector ◽  
Yield Prediction ◽  
Indian States ◽  
South Indian ◽  
Proposed Model

The main objective of this research is to predict crop yields based on cultivation area, Rainfall and maximum and minimum temperature data. It will help our Indian farmers to predict crop yielding according to the environment conditions. Nowadays, Machine learning based crop yield prediction is very popular than the traditional models because of its accuracy. In this paper, linear regression, Support Vector Regression, Decision Tree and Random forest is compared with XG Boost algorithm. The above mentioned algorithms are compared based on R2 , Minimum Square Error and Minimum Absolute Error. The dataset is prepared from the data.gov.in site for the year from 2000 to 2014. The data for 4 south Indian states Andhra Pradesh, Karnataka, Tamil Nadu and Kerala data alone is taken since all these states has same climatic conditions. The proposed model in this paper based on XG Boost is showing much better results than other models. In XG Boost R2 is 0.9391 which is the best when compared with other models.

scholarly journals Application of Machine Learning on Crop Yield Prediction in Agriculture Enforcement

2021 ◽  
Vol 11 (2) ◽  
pp. 2142-2155
Author(s):  
D. Jayakumar ◽  
S. Srinivasan ◽  
P. Prithi ◽  
Sreelekha Vemula ◽  
Narashena Sri
Keyword(s):  
Support Vector Machine ◽  
Crop Yield ◽  
Initial Distribution ◽  
Support Vector ◽  
Yield Prediction ◽  
Network Support ◽  
Q Learning ◽  
High Satisfaction ◽  
Proposed Model ◽  
Parametric Functions

Yield forecasting is based totally entirely on soil, water and vegetation to be a possible subject. Deep-based depth-based fashions are widely accustomed extract important plant functions for predictive purposes. Although such strategies are necessary to resolve the matter of predicting yields there are the subsequent abnormalities: they can't create an indirect or indirect map between raw facts and yield values; and also the full functionality of this excess is explained within the high satisfaction of the published works. Deep durability provides guidance and motivation for the above-mentioned errors. Combining master intensity and deep mastering, deep reinforcing mastering creates a comprehensive yield prediction framework which will plan the uncooked facts in crop prediction rates. The proposed project creates a version of the Deep Recurrent Q-Network Support Vector Machine deep mastering set of rules over Q-Learning to strengthen the mastering set of rules for predicting yield. Sequential downloads of the Recurrent Neural community are fed by fact parameters. The Q-mastering community creates a predictive yield environment based totally on input criteria. The precise layer displays the discharge values of the Support Vector Machine on the Q values. The reinforcement master component contains a mix of parametric functions on the sting that helps predict the yield. Finally, the agent obtains a measure of the mixture of steps performed by minimizing the error and increasing the accuracy of the forecast. The proposed model successfully predicts this crop yield that's hip by keeping the initial distribution of facts with 93.7% accuracy.

scholarly journals Crop yield prediction integrating genotype and weather variables using deep learning

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0252402
Author(s):  
Johnathon Shook ◽  
Tryambak Gangopadhyay ◽  
Linjiang Wu ◽  
Baskar Ganapathysubramanian ◽  
Soumik Sarkar ◽  
...  
Keyword(s):  
Crop Yield ◽  
Crop Production ◽  
Short Term Memory ◽  
Time Windows ◽  
Climatic Conditions ◽  
Support Vector ◽  
Yield Prediction ◽  
Lasso Regression ◽  
Important Time ◽  
Interpretable Models

Accurate prediction of crop yield supported by scientific and domain-relevant insights, is useful to improve agricultural breeding, provide monitoring across diverse climatic conditions and thereby protect against climatic challenges to crop production. We used performance records from Uniform Soybean Tests (UST) in North America to build a Long Short Term Memory (LSTM)—Recurrent Neural Network based model that leveraged pedigree relatedness measures along with weekly weather parameters to dissect and predict genotype response in multiple-environments. Our proposed models outperformed other competing machine learning models such as Support Vector Regression with Radial Basis Function kernel (SVR-RBF), least absolute shrinkage and selection operator (LASSO) regression and the data-driven USDA model for yield prediction. Additionally, for providing interpretability of the important time-windows in the growing season, we developed a temporal attention mechanism for LSTM models. The outputs of such interpretable models could provide valuable insights to plant breeders.

Regional factors of grain crop yield growth in the dynamics of recent years

2021 ◽  
pp. 29-36
Author(s):  
Yuriy P. Bondarenko ◽  
Keyword(s):  
Crop Yield ◽  
Crop Yields ◽  
Methodological Approach ◽  
Climatic Conditions ◽  
Grain Production ◽  
Fixed Assets ◽  
Production Complex ◽  
Grain Crop ◽  
Regional Factors

In view of the significant increase in grain production in Russia, a methodological approach is proposed to analyze the significance of regional factors of grain crop yield growth in the country in recent years, especially against the background of the lack of expansion of acreage under grain crops. Based on the results of the calculations, the effectiveness of the influence of climatic, financial, infrastructural and production factors on the growth of grain yield was described. It is concluded that various factors had different effects on the growth of grain crop yields in regions with high-, medium - and low-intensity grain production complex. The role of reducing the influence of financial factors on the growth of grain yields and a sharp increase in the role of agro-climatic conditions is noted. The revealed trend of increasing depreciation of fixed assets of agriculture as a whole is particularly emphasized, with a slight increase in the volume of their renewal and modernization in the leading regions in terms of grain crop yield growth. Without taking appropriate measures to reduce the depreciation of fixed assets in the near future, this will result in a sharp decline in the achieved volumes of grain production in the country.

scholarly journals A Methodology for Predicting Aggregate Flight Departure Delays in Airports Based on Supervised Learning

2020 ◽  
Vol 12 (7) ◽  
pp. 2749 ◽  
Author(s):  
Bojia Ye ◽  
Bo Liu ◽  
Yong Tian ◽  
Lili Wan
Keyword(s):  
Supervised Learning ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Support Vector ◽  
Accuracy Rate ◽  
Forecast Horizon ◽  
Learning Methods ◽  
Extremely Randomized Trees ◽  
Proposed Model ◽  
Operational Data

This paper proposes a new methodology for predicting aggregate flight departure delays in airports by exploring supervised learning methods. Individual flight data and meteorological information were processed to obtain four types of airport-related aggregate characteristics for prediction modeling. The expected departure delays in airports is selected as the prediction target while four popular supervised learning methods: multiple linear regression, a support vector machine, extremely randomized trees and LightGBM are investigated to improve the predictability and accuracy of the model. The proposed model is trained and validated using operational data from March 2017 to February 2018 for the Nanjing Lukou International Airport in China. The results show that for a 1-h forecast horizon, the LightGBM model provides the best result, giving a 0.8655 accuracy rate with a 6.65 min mean absolute error, which is 1.83 min less than results from previous research. The importance of aggregate characteristics and example validation are also studied.

A COMPARITIVE ANALYSIS AND TIME SERIES FORECASTING OF MONTHLY STREAM FLOW DATA USING HYBRID MODEL

2015 ◽  
Vol 76 (13) ◽  
Author(s):  
Siraj Muhammed Pandhiani ◽  
Ani Shabri
Keyword(s):  
Hybrid Model ◽  
Stream Flow ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Least Square ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Flow Data ◽  
Indus River ◽  
Proposed Model

In this study, new hybrid model is developed by integrating two models, the discrete wavelet transform and least square support vector machine (WLSSVM) model. The hybrid model is then used to measure for monthly stream flow forecasting for two major rivers in Pakistan. The monthly stream flow forecasting results are obtained by applying this model individually to forecast the rivers flow data of the Indus River and Neelum Rivers. The root mean square error (RMSE), mean absolute error (MAE) and the correlation (R) statistics are used for evaluating the accuracy of the WLSSVM, the proposed model. The results are compared with the results obtained through LSSVM. The outcome of such comparison shows that WLSSVM model is more accurate and efficient than LSSVM.

scholarly journals Screening of South Indian Culinary Melon (Cucumis melo subsp. agrestis var. acidulus) Accessions for Downy Mildew Disease under Natural Epiphytotic Condition

2021 ◽  
Vol 8 (4) ◽  
pp. 211-216
Author(s):  
Ratnakar M. Shet ◽  
◽  
A. Prashantha ◽  
P. S. Mahanthesh ◽  
K. S. Sankarappa ◽  
...  
Keyword(s):  
Downy Mildew ◽  
Cucumis Melo ◽  
Tamil Nadu ◽  
Indian Subcontinent ◽  
Indian States ◽  
South Indian ◽  
The Family ◽  
Percent Disease Index ◽  
Moderately Resistant ◽  
Downy Mildew Disease

Culinary melon also known as non dessert cucumber (Cucumis melo subsp. agrestis var. acidulus) belongs to the family Cucurbitaceae. It is widely cultivated in Southern parts of Indian subcontinent. It is mainly utilized for preparation of lentil soup, sambar, dosa, palya and chutney. 70 accessions were collected from six South Indian states namely Karnataka, Kerala, Andhra Pradesh, Tamil Nadu, Telangana and Goa. The accessions were evaluated for incidence of downy mildew resistance during Kharif 2018 under natural condition. The percent disease index (PDI) for downy mildew ranged from 3.70 to 48.64%. 10 accessions showed resistance to downy mildew. Among them, accession MS21 showed resistance with average least PDI of 3.70 followed by MS 6 (6.54). 50 accessions were found to be moderately resistant with average PDI ranging from 20 to 39.80. 12 accessions were found susceptible with PDI ranging from 41 to 49. None of the accession was found highly susceptible to the disease. The resistant accessions can be utilized as donor parents for resistant breeding in the improvement of culinary melon as well as melon group of vegetables.

scholarly journals Agriculture Data Analytics in Crop Yield Estimation: A Critical Review

2018 ◽  
Vol 12 (3) ◽  
pp. 1087 ◽  
Author(s):  
B.M. Sagar ◽  
Cauvery N K
Keyword(s):  
Big Data ◽  
Crop Yield ◽  
Data Analytics ◽  
Crop Production ◽  
Big Data Analytics ◽  
Agricultural Practices ◽  
Climatic Conditions ◽  
Yield Prediction ◽  
Main Challenge ◽  
Crop Health

<p>Agriculture is important for human survival because it serves the basic need. A well-known fact that the majority of population (≥55%) in India is into agriculture. Due to variations in climatic conditions, there exist bottlenecks for increasing the crop production in India. It has become challenging task to achieve desired targets in Agri based crop yield. Factors like climate, geographical conditions, economic and political conditions are to be considered which have direct impact on the production, productivity of the crops. Crop yield prediction is one of the important factors in agriculture practices. Farmers need information regarding crop yield before sowing seeds in their fields to achieve enhanced crop yield. The use of technology in agriculture has increased in recent year and data analytics is one such trend that has penetrated into the agriculture field being used for management of crop yield and monitoring crop health. The recent trends in the domain of agriculture have made the people to understand the significance of          Big data. The main challenge using big data in agriculture is identification of impact and effectiveness of big data analytics.  Efforts are going on to understand how big data analytics can be used to improve the productivity in agricultural practices. The analysis of data related to agriculture helps in crop yield prediction, crop health monitoring and other such related activities. In literature, there exist several studies related to the use of data analytics in the agriculture domain. The present study gives insights on various data analytics methods applied to crop yield prediction. The work also signifies the important lacunae points’ in the proposed area of research.</p>

scholarly journals Comparative Study for Classification Algorithms Performance in Crop Yields Prediction Systems

2021 ◽  
Vol 1 (2) ◽  
pp. 19-24
Author(s):  
Halbast Rashid Ismael ◽  
Adnan Mohsin Abdulazeez ◽  
Dathar A. Hasan
Keyword(s):  
Data Mining ◽  
Crop Yield ◽  
Crop Yields ◽  
Effective Field ◽  
Research Field ◽  
Support Vector ◽  
Classification Algorithms ◽  
Yield Quality ◽  
Prediction Systems ◽  
The Impact

The agriculture importance is not restricted to our daily life; it is also an effective field that enhances the economic growth in any country. Therefore, developing the quality of the crop yields using recent technologies is a crucial procedure to obtain competitive crops. Nowadays, data mining is an emerging research field in agriculture especially in the predicting and analysis of crop yield. This paper focuses on utilizing various data mining classification algorithms to predict the impact of various parameters such as area, season and production on the crop yield quality. The performance of the decision tree, naive Bayes, random forest, support vector machine and K-nearest neighbour is measured and compared to each other. The comparison involves measuring the error values and accuracy. The SVM algorithm achieved the highest accuracy value with 76.82%. while the lowest is achieved by the KNN algorithm with 35.76%. The highest error value was 111.8855 for KNN. Also, the prediction help farmer to increased and improved the income level.  

scholarly journals A Comparison Between Major Artificial Intelligence Models for Crop Yield Prediction: Case Study of the Midwestern United States, 2006–2015

2019 ◽  
Vol 8 (5) ◽  
pp. 240 ◽  
Author(s):  
Nari Kim ◽  
Kyung-Ja Ha ◽  
No-Wook Park ◽  
Jaeil Cho ◽  
Sungwook Hong ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
United States ◽  
Crop Yield ◽  
Layer Structure ◽  
Absolute Error ◽  
Activation Function ◽  
Drop Out ◽  
Yield Prediction ◽  
Midwestern United States ◽  
Artificial Intelligence Models

This paper compares different artificial intelligence (AI) models in order to develop the best crop yield prediction model for the Midwestern United States (US). Through experiments to examine the effects of phenology using three different periods, we selected the July–August (JA) database as the best months to predict corn and soybean yields. Six different AI models for crop yield prediction are tested in this research. Then, a comprehensive and objective comparison is conducted between the AI models. Particularly for the deep neural network (DNN) model, we performed an optimization process to ensure the best configurations for the layer structure, cost function, optimizer, activation function, and drop-out ratio. In terms of mean absolute error (MAE), our DNN model with the JA database was approximately 21–33% and 17–22% more accurate for corn and soybean yields, respectively, than the other five AI models. This indicates that corn and soybean yields for a given year can be forecasted in advance, at the beginning of September, approximately a month or more ahead of harvesting time. A combination of the optimized DNN model and spatial statistical methods should be investigated in future work, to mitigate partly clustered errors in some regions.

Sign in / Sign up

Export Citation Format

Share Document