EUVIMEDEUVIMED entdecken
Crossref

ການຄາດຄະເນຜົນຜະລິດເຂົ້າໃນ ສປປ ລາວ ໂດຍຜ່ານເຕັກນິກການຮຽນຮູ້ຂອງຄອມພິວເຕີ

Sackthavy Lasichan, Somsack Inthasone, Amone Chanthaphavong

Lao Journal of Science and Technology · 20.01.2026 · 3 (2) · 73-81

DOI: 10.71026/ljst.2025.02007 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Lao Journal of Science and Technology, online erschienen am 20.01.2026. Verfasst von Sackthavy Lasichan und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agriculture remains a key sector in Lao PDR, contributing significantly to job creation, rural development, and food security, despite a decline in its share of GDP in recent years (TheGlobalEconomy, 2025). Rice accounts for almost half of agricultural output, making it both a staple food and a major export commodity (World Bank, 2025). However, rice production is highly vulnerable to multiple uncertainties, including climate change, land-use change, and population pressures, which limit the effectiveness of traditional statistical forecasting methods. This study explores the use of machine learning techniques to improve production forecasts in Lao PDR. Using food production data from the Food and Agriculture Organization of the United Nations (FAO), combined with 13 socio-economic indicators and environmental factors from 1991 to 2024, three machine learning models were fitted: Decision Tree Regression, Random Forest Regression, and Support Vector Regression. In addition, enhancement techniques such as Time series train-test split, decomposition model (trend + residual), lag variables, differencing, rolling averages, trend feature, bias correction and recursive forecasting were applied to capture temporal dynamics and nonlinear data patterns. The results show that Random Forest models achieved highest prediction accuracy, with R² values of 0.94, and Mean Absolute Percentage Error values only 0.73%. The analysis also found thatO emission from fertilizer using has the highest positive correlation with rice production, while inflation and insecticide use show the opposite effect. This finding suggests that machine learning methods, particularly Random Forest regression models, can be applied in practice and policymaking to enhance planning, strengthen food security strategies, and support sustainable agricultural development in Lao PDR.

Zitieren

APA

Lasichan, S., Inthasone, S., & Chanthaphavong, A. (2026). ການຄາດຄະເນຜົນຜະລິດເຂົ້າໃນ ສປປ ລາວ ໂດຍຜ່ານເຕັກນິກການຮຽນຮູ້ຂອງຄອມພິວເຕີ. Lao Journal of Science and Technology, 3(2), 73-81. https://doi.org/10.71026/ljst.2025.02007

Vancouver

Lasichan S, Inthasone S, Chanthaphavong A. ການຄາດຄະເນຜົນຜະລິດເຂົ້າໃນ ສປປ ລາວ ໂດຍຜ່ານເຕັກນິກການຮຽນຮູ້ຂອງຄອມພິວເຕີ. Lao Journal of Science and Technology. 2026;3(2):73-81. doi:10.71026/ljst.2025.02007

BibTeX
@article{Lasichan2026,
  author = {Lasichan, Sackthavy and Inthasone, Somsack and Chanthaphavong, Amone},
  title = {ການຄາດຄະເນຜົນຜະລິດເຂົ້າໃນ ສປປ ລາວ ໂດຍຜ່ານເຕັກນິກການຮຽນຮູ້ຂອງຄອມພິວເຕີ},
  journal = {Lao Journal of Science and Technology},
  year = {2026},
  volume = {3},
  number = {2},
  pages = {73--81},
  doi = {10.71026/ljst.2025.02007}
}
Kostenlos starten →