Use of regression techniques for rice yield estimation in the North-Western province of Sri Lanka

One of the aspects in the agriculture sector beneficial to farmers and all other stakeholders is the prior knowledge on the yield of crops expected from an agricultural season. In this paper, several regression techniques have been used to model the relationship between climatic factors and paddy pr...

Full description

Bibliographic Details
Main Authors: E. M. P. Ekanayake, L. C. D. Wickramasinghe, R. T. Weliwatta
Format: Article
Language:English
Published: Faculty of Science, University of Peradeniya, Sri Lanka 2021-12-01
Series:Ceylon Journal of Science
Subjects:
Online Access:https://cjs.sljol.info/articles/7942
_version_ 1811323883658149888
author E. M. P. Ekanayake
L. C. D. Wickramasinghe
R. T. Weliwatta
author_facet E. M. P. Ekanayake
L. C. D. Wickramasinghe
R. T. Weliwatta
author_sort E. M. P. Ekanayake
collection DOAJ
description One of the aspects in the agriculture sector beneficial to farmers and all other stakeholders is the prior knowledge on the yield of crops expected from an agricultural season. In this paper, several regression techniques have been used to model the relationship between climatic factors and paddy production in the North-Western province of Sri Lanka that makes a significant contribution to the total harvest of the country. Nearly two decades of rice yield data from 2000 to 2018 and several climatic factors in the two agricultural seasons of Yala (May-August) and Maha (September-March) were considered in the analysis. Monthly mean climatic data of temperature, evaporation, sunshine, and wind speed were applied along with the overall rainfall in four regression techniques <em>viz.</em> Support Vector Machine Regression, Multiple Linear regression, Power Regression, and the Robust Regression on MATLAB and R software. The performance of the models developed on those techniques was evaluated in terms of the Mean Absolute Error and the Coefficient of Determination. It was found that the Support Vector Machine Regression produces the best correlation between actual and predicted yields in both administrative districts of the Province, which can be used for yield estimation under normal climatic conditions.
first_indexed 2024-04-13T14:03:56Z
format Article
id doaj.art-9251f930eaf840fda8b68dd0464313bf
institution Directory Open Access Journal
issn 2513-2814
2513-230X
language English
last_indexed 2024-04-13T14:03:56Z
publishDate 2021-12-01
publisher Faculty of Science, University of Peradeniya, Sri Lanka
record_format Article
series Ceylon Journal of Science
spelling doaj.art-9251f930eaf840fda8b68dd0464313bf2022-12-22T02:43:58ZengFaculty of Science, University of Peradeniya, Sri LankaCeylon Journal of Science2513-28142513-230X2021-12-0150443944710.4038/cjs.v50i4.79425898Use of regression techniques for rice yield estimation in the North-Western province of Sri LankaE. M. P. Ekanayake0L. C. D. Wickramasinghe1R. T. Weliwatta2Wayamba University of Sri Lanka, KuliyapitiyaWayamba University of Sri Lanka, KuliyapitiyaWayamba University of Sri Lanka, KuliyapitiyaOne of the aspects in the agriculture sector beneficial to farmers and all other stakeholders is the prior knowledge on the yield of crops expected from an agricultural season. In this paper, several regression techniques have been used to model the relationship between climatic factors and paddy production in the North-Western province of Sri Lanka that makes a significant contribution to the total harvest of the country. Nearly two decades of rice yield data from 2000 to 2018 and several climatic factors in the two agricultural seasons of Yala (May-August) and Maha (September-March) were considered in the analysis. Monthly mean climatic data of temperature, evaporation, sunshine, and wind speed were applied along with the overall rainfall in four regression techniques <em>viz.</em> Support Vector Machine Regression, Multiple Linear regression, Power Regression, and the Robust Regression on MATLAB and R software. The performance of the models developed on those techniques was evaluated in terms of the Mean Absolute Error and the Coefficient of Determination. It was found that the Support Vector Machine Regression produces the best correlation between actual and predicted yields in both administrative districts of the Province, which can be used for yield estimation under normal climatic conditions.https://cjs.sljol.info/articles/7942regression, coefficient of determination, mean absolute error, yield estimation, north-western province
spellingShingle E. M. P. Ekanayake
L. C. D. Wickramasinghe
R. T. Weliwatta
Use of regression techniques for rice yield estimation in the North-Western province of Sri Lanka
Ceylon Journal of Science
regression, coefficient of determination, mean absolute error, yield estimation, north-western province
title Use of regression techniques for rice yield estimation in the North-Western province of Sri Lanka
title_full Use of regression techniques for rice yield estimation in the North-Western province of Sri Lanka
title_fullStr Use of regression techniques for rice yield estimation in the North-Western province of Sri Lanka
title_full_unstemmed Use of regression techniques for rice yield estimation in the North-Western province of Sri Lanka
title_short Use of regression techniques for rice yield estimation in the North-Western province of Sri Lanka
title_sort use of regression techniques for rice yield estimation in the north western province of sri lanka
topic regression, coefficient of determination, mean absolute error, yield estimation, north-western province
url https://cjs.sljol.info/articles/7942
work_keys_str_mv AT empekanayake useofregressiontechniquesforriceyieldestimationinthenorthwesternprovinceofsrilanka
AT lcdwickramasinghe useofregressiontechniquesforriceyieldestimationinthenorthwesternprovinceofsrilanka
AT rtweliwatta useofregressiontechniquesforriceyieldestimationinthenorthwesternprovinceofsrilanka