Explainable artificial intelligence to estimate the Sri Lankan (Ceylon) Tea crop yield

Accurate cash crop yield prediction is important in the context of changing climate to ensure sustainable development. Artificial intelligence (AI) has played a significant role in prediction in nonlinear systems including cash crop prediction. However, despite its global recognition, Sri Lanka'...

Full description

Saved in:
Bibliographic Details
Main Authors: Lakindu Mampitiya, Harindu S. Sumanasekara, Namal Rathnayake, Yukinobu Hoshino, Upaka Rathnayake
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525002321
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850134369983791104
author Lakindu Mampitiya
Harindu S. Sumanasekara
Namal Rathnayake
Yukinobu Hoshino
Upaka Rathnayake
author_facet Lakindu Mampitiya
Harindu S. Sumanasekara
Namal Rathnayake
Yukinobu Hoshino
Upaka Rathnayake
author_sort Lakindu Mampitiya
collection DOAJ
description Accurate cash crop yield prediction is important in the context of changing climate to ensure sustainable development. Artificial intelligence (AI) has played a significant role in prediction in nonlinear systems including cash crop prediction. However, despite its global recognition, Sri Lanka's renowned Ceylon Tea has never been modeled for yield prediction based on meteorological, soil, and fertilizer parameters. Sri Lanka is one of the most impacted countries due to climate change while its agricultural production is significant in economic contribution. Therefore, this study presents the first-ever research to predict the tea crop yield with respect to meteorological, soil, and fertilizer features. State-of-the-art machine learning models were tested with the aid of Dampahala Tea Company production. Results showcased that the CatBoost algorithm produces the best prediction model with a coefficient of determination, RCatBoost2= of 0.90374 (other models tested, RXGBoost2=0.87385;RLightGBM2=0.79772;RANN2=0.57346;RRidge2=0.42033;RLASSO2=0.42512;RElasticNet2=0.42168). In addition, explainability aspects using SHAP showcased that the morning relative humidity, evaporation, and T0 200 fertilizer have a significant impact on the prediction model. The developed AI model can be disseminated across the country to enhance understanding of predictions under future climatic scenarios.
format Article
id doaj-art-89264d7ee9524fdc9510c7d4efd92d7b
institution OA Journals
issn 2772-3755
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-89264d7ee9524fdc9510c7d4efd92d7b2025-08-20T02:31:44ZengElsevierSmart Agricultural Technology2772-37552025-08-011110099910.1016/j.atech.2025.100999Explainable artificial intelligence to estimate the Sri Lankan (Ceylon) Tea crop yieldLakindu Mampitiya0Harindu S. Sumanasekara1Namal Rathnayake2Yukinobu Hoshino3Upaka Rathnayake4Water Resources Management and Soft Computing Research Laboratory, Millennium City, Athurugiriya 10150, Sri LankaRegional Integrated Multi-Hazard Early Warning System (RIMES) - Sri Lanka National Centre for Climate Applications (SNCCA), Irrigation Department, Colombo, Sri LankaDepartment of Civil Engineering, Faculty of Engineering, The University of Tokyo, Bunkyo City, Tokyo 113-8656, JapanSchool of Systems Engineering, Kochi University of Technology, Tosayamada, Kami, Kochi 782-8502, JapanDepartment of Civil Engineering and Construction, Faculty of Engineering and Design, Atlantic Technological University, F91 YW50 Sligo, Ireland; Corresponding author.Accurate cash crop yield prediction is important in the context of changing climate to ensure sustainable development. Artificial intelligence (AI) has played a significant role in prediction in nonlinear systems including cash crop prediction. However, despite its global recognition, Sri Lanka's renowned Ceylon Tea has never been modeled for yield prediction based on meteorological, soil, and fertilizer parameters. Sri Lanka is one of the most impacted countries due to climate change while its agricultural production is significant in economic contribution. Therefore, this study presents the first-ever research to predict the tea crop yield with respect to meteorological, soil, and fertilizer features. State-of-the-art machine learning models were tested with the aid of Dampahala Tea Company production. Results showcased that the CatBoost algorithm produces the best prediction model with a coefficient of determination, RCatBoost2= of 0.90374 (other models tested, RXGBoost2=0.87385;RLightGBM2=0.79772;RANN2=0.57346;RRidge2=0.42033;RLASSO2=0.42512;RElasticNet2=0.42168). In addition, explainability aspects using SHAP showcased that the morning relative humidity, evaporation, and T0 200 fertilizer have a significant impact on the prediction model. The developed AI model can be disseminated across the country to enhance understanding of predictions under future climatic scenarios.http://www.sciencedirect.com/science/article/pii/S2772375525002321Explainable artificial intelligenceMachine learning techniquesMeteorological parametersSri lankan (Ceylon) TeaYIELD prediction
spellingShingle Lakindu Mampitiya
Harindu S. Sumanasekara
Namal Rathnayake
Yukinobu Hoshino
Upaka Rathnayake
Explainable artificial intelligence to estimate the Sri Lankan (Ceylon) Tea crop yield
Smart Agricultural Technology
Explainable artificial intelligence
Machine learning techniques
Meteorological parameters
Sri lankan (Ceylon) Tea
YIELD prediction
title Explainable artificial intelligence to estimate the Sri Lankan (Ceylon) Tea crop yield
title_full Explainable artificial intelligence to estimate the Sri Lankan (Ceylon) Tea crop yield
title_fullStr Explainable artificial intelligence to estimate the Sri Lankan (Ceylon) Tea crop yield
title_full_unstemmed Explainable artificial intelligence to estimate the Sri Lankan (Ceylon) Tea crop yield
title_short Explainable artificial intelligence to estimate the Sri Lankan (Ceylon) Tea crop yield
title_sort explainable artificial intelligence to estimate the sri lankan ceylon tea crop yield
topic Explainable artificial intelligence
Machine learning techniques
Meteorological parameters
Sri lankan (Ceylon) Tea
YIELD prediction
url http://www.sciencedirect.com/science/article/pii/S2772375525002321
work_keys_str_mv AT lakindumampitiya explainableartificialintelligencetoestimatethesrilankanceylonteacropyield
AT harindussumanasekara explainableartificialintelligencetoestimatethesrilankanceylonteacropyield
AT namalrathnayake explainableartificialintelligencetoestimatethesrilankanceylonteacropyield
AT yukinobuhoshino explainableartificialintelligencetoestimatethesrilankanceylonteacropyield
AT upakarathnayake explainableartificialintelligencetoestimatethesrilankanceylonteacropyield