Four-parameter beta mixed models with survey and sentinel 2A satellite data for predicting paddy productivity
Ensuring food security, fostering agricultural sustainability, and driving economic development. However, existing prediction models often overlook the unique characteristics of paddy productivity distribution, which varies between areas, skewed, and bounded within a certain minimum and maximum rang...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375524001308 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846124973520846848 |
|---|---|
| author | Dian Kusumaningrum Hari Wijayanto Anang Kurnia Khairil Anwar Notodiputro Muhlis Ardiansyah Islam MD Parvez |
| author_facet | Dian Kusumaningrum Hari Wijayanto Anang Kurnia Khairil Anwar Notodiputro Muhlis Ardiansyah Islam MD Parvez |
| author_sort | Dian Kusumaningrum |
| collection | DOAJ |
| description | Ensuring food security, fostering agricultural sustainability, and driving economic development. However, existing prediction models often overlook the unique characteristics of paddy productivity distribution, which varies between areas, skewed, and bounded within a certain minimum and maximum range, following a four-parameter beta distribution. Consequently, these models yield less accurate and potentially misleading predictions. Additionally, most approaches fail to capture the complex interrelationships among variables that often occur when we incorporate satellite data alongside survey data that has been recognized as a key approach for improving prediction accuracy and optimizing farming practices. To address these shortcomings, this study introduces a four-parameter beta Generalized Linear Mixed Model (GLMM) augmented within a four-parameter beta Generalized Mixed Effect Tree (GMET). The four-parameter beta GMET, an extension of the four-parameter beta GLMM model integrated with a regression tree, offers enhanced flexibility in modeling complex relationships. Application of this methodology to an empirical study in Central Kalimantan and Karawang reveals notable improvements over previous methods, as evidenced by substantially lower AIC and RRMSE values. Notably, the analysis identifies lagged values of band 4, band 8, and NDVI from Sentinel-2A satellite data as significant predictors of paddy productivity, overriding the importance of farmer survey variables. This underscores the potential of satellite data to be utilized in paddy productivity predictions, offering a more efficient and cost-effective alternative to farmer survey-based methods. By enhancing satellite technology, future efforts in paddy productivity prediction can achieve higher efficiency and accuracy, contributing to informed decision-making in agricultural management. |
| format | Article |
| id | doaj-art-af06d9091c404671aa2f1c94e273543b |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-af06d9091c404671aa2f1c94e273543b2024-12-13T11:07:44ZengElsevierSmart Agricultural Technology2772-37552024-12-019100525Four-parameter beta mixed models with survey and sentinel 2A satellite data for predicting paddy productivityDian Kusumaningrum0Hari Wijayanto1Anang Kurnia2Khairil Anwar Notodiputro3Muhlis Ardiansyah4Islam MD Parvez5Business Mathematics Program Study, School of Applied STEM, Universitas Prasetiya Mulya, BSD Campus, BSD City Kav. Edutown I.1, Tangerang 15339, Indonesia; Program on Statistics and Data Science - School of Data Science, Mathematics, and Informatics - IPB University, Jl. Meranti Wing 22 Level 4, Dramaga, Bogor 16680, IndonesiaProgram on Statistics and Data Science - School of Data Science, Mathematics, and Informatics - IPB University, Jl. Meranti Wing 22 Level 4, Dramaga, Bogor 16680, Indonesia; Corresponding author.Program on Statistics and Data Science - School of Data Science, Mathematics, and Informatics - IPB University, Jl. Meranti Wing 22 Level 4, Dramaga, Bogor 16680, IndonesiaProgram on Statistics and Data Science - School of Data Science, Mathematics, and Informatics - IPB University, Jl. Meranti Wing 22 Level 4, Dramaga, Bogor 16680, IndonesiaProgram on Statistics and Data Science - School of Data Science, Mathematics, and Informatics - IPB University, Jl. Meranti Wing 22 Level 4, Dramaga, Bogor 16680, Indonesia; BPS-Statistics of Kotawaringin Timur, Jl Ahmad Yani no 5 Sampit 74322, Central Kalimantan, IndonesiaDepartment of Biomechanical Systems, Faculty of Agriculture, Ehime University, 3-5-7 Tarumi, Matsuyama 790-8566, JapanEnsuring food security, fostering agricultural sustainability, and driving economic development. However, existing prediction models often overlook the unique characteristics of paddy productivity distribution, which varies between areas, skewed, and bounded within a certain minimum and maximum range, following a four-parameter beta distribution. Consequently, these models yield less accurate and potentially misleading predictions. Additionally, most approaches fail to capture the complex interrelationships among variables that often occur when we incorporate satellite data alongside survey data that has been recognized as a key approach for improving prediction accuracy and optimizing farming practices. To address these shortcomings, this study introduces a four-parameter beta Generalized Linear Mixed Model (GLMM) augmented within a four-parameter beta Generalized Mixed Effect Tree (GMET). The four-parameter beta GMET, an extension of the four-parameter beta GLMM model integrated with a regression tree, offers enhanced flexibility in modeling complex relationships. Application of this methodology to an empirical study in Central Kalimantan and Karawang reveals notable improvements over previous methods, as evidenced by substantially lower AIC and RRMSE values. Notably, the analysis identifies lagged values of band 4, band 8, and NDVI from Sentinel-2A satellite data as significant predictors of paddy productivity, overriding the importance of farmer survey variables. This underscores the potential of satellite data to be utilized in paddy productivity predictions, offering a more efficient and cost-effective alternative to farmer survey-based methods. By enhancing satellite technology, future efforts in paddy productivity prediction can achieve higher efficiency and accuracy, contributing to informed decision-making in agricultural management.http://www.sciencedirect.com/science/article/pii/S2772375524001308Four-parameter beta distributionGeneralized linear mixed model (GLMM)Generalized mixed effect tree (GMET)Paddy productivitySentinel 2A satellite data |
| spellingShingle | Dian Kusumaningrum Hari Wijayanto Anang Kurnia Khairil Anwar Notodiputro Muhlis Ardiansyah Islam MD Parvez Four-parameter beta mixed models with survey and sentinel 2A satellite data for predicting paddy productivity Smart Agricultural Technology Four-parameter beta distribution Generalized linear mixed model (GLMM) Generalized mixed effect tree (GMET) Paddy productivity Sentinel 2A satellite data |
| title | Four-parameter beta mixed models with survey and sentinel 2A satellite data for predicting paddy productivity |
| title_full | Four-parameter beta mixed models with survey and sentinel 2A satellite data for predicting paddy productivity |
| title_fullStr | Four-parameter beta mixed models with survey and sentinel 2A satellite data for predicting paddy productivity |
| title_full_unstemmed | Four-parameter beta mixed models with survey and sentinel 2A satellite data for predicting paddy productivity |
| title_short | Four-parameter beta mixed models with survey and sentinel 2A satellite data for predicting paddy productivity |
| title_sort | four parameter beta mixed models with survey and sentinel 2a satellite data for predicting paddy productivity |
| topic | Four-parameter beta distribution Generalized linear mixed model (GLMM) Generalized mixed effect tree (GMET) Paddy productivity Sentinel 2A satellite data |
| url | http://www.sciencedirect.com/science/article/pii/S2772375524001308 |
| work_keys_str_mv | AT diankusumaningrum fourparameterbetamixedmodelswithsurveyandsentinel2asatellitedataforpredictingpaddyproductivity AT hariwijayanto fourparameterbetamixedmodelswithsurveyandsentinel2asatellitedataforpredictingpaddyproductivity AT anangkurnia fourparameterbetamixedmodelswithsurveyandsentinel2asatellitedataforpredictingpaddyproductivity AT khairilanwarnotodiputro fourparameterbetamixedmodelswithsurveyandsentinel2asatellitedataforpredictingpaddyproductivity AT muhlisardiansyah fourparameterbetamixedmodelswithsurveyandsentinel2asatellitedataforpredictingpaddyproductivity AT islammdparvez fourparameterbetamixedmodelswithsurveyandsentinel2asatellitedataforpredictingpaddyproductivity |