All Issue

2025 Vol.58, Issue 3 Preview Page

Original research article

Machine learning approach for quantifying methane emissions from a flooded rice paddy in Chungcheong province
Yun-Gu Kang1†
,
Jun-Yeong Lee1†
,
Ji-Hoon Kim2
,
Jiwon Choi2
,
Jun-Ho Kim2
,
Jin-Hyuk Chun3
,
Taek-Keun Oh4*
1Doctoral Student, Department of Bio-Environmental Chemistry, College of Agriculture and Life Sciences, Chungnam National University, Daejeon 34134, Korea
2Master Student, Department of Bio-Environmental Chemistry, College of Agriculture and Life Sciences, Chungnam National University, Daejeon 34134, Korea
3Researcher, The Korea Ginseng Inspection Office, National Agricultural Cooperative Federation, Geumsan 32748, Korea
4Professor, Department of Bio-Environmental Chemistry, College of Agriculture and Life Sciences, Chungnam National University, Daejeon 34134, Korea
*Corresponding Author
†These authors contributed equally to this work.
31 August 2025. pp. 324-334
PDF XML Citation
Abstract

Machine learning (ML)-based estimation of methane (CH4) emissions is essential to effectively assess the impacts of rice production and respond to climate change. This approach not only requires less labor and costs than field-based study, but also entails high reproducibility and applicability. However, optimal ML algorithms and combination of environmental covariates for forecasting CH4 emissions are still lacking. Hence, the goals of this study were (1) to evaluate the regression performance of three ML algorithms (i.e., multiple linear regression, ridge regression, and random-forest) and (2) to assess the relative influence of each environmental factor within the predictive model for CH4 emissions. The environmental covariates, which obtained from rice paddy field at Daejeon, South Korea in 2024, classified as followed: climatic factors (i.e., atmospheric, soil, and water temperatures and precipitation), fertilization method (i.e., quantity of nitrogen fertilization and fertilizer deep-placement application), and soil properties (i.e., oxidation-reduction potential and soil drainage). Our predictive model based on the random-forest algorithm outperformed than the linear-based ML algorithms. The random-forest algorithm achieved the highest reliability of 86.1%, and the mean value of the K-Fold cross-validation was 83.0%. The relative influence of each parameter was exhibited to be high in the order of atmospheric temperature (0.49), soil temperature (0.27), quantity of nitrogen fertilization (0.20), fertilizer deep-placement (0.17), and soil drainage (0.17). These findings revealed the requirement of explanation capacity for non-linear relationship in forecasting the CH4 emissions, and need for collecting various environmental factors related to rice production.

(A) Correlation between environmental factors and methane (CH4) emissions and (B) Comparison of the model performance with variations in the key features.
Keywords
Climate change
Multiple linear regression (MLR)
Random forest
Ridge regression
Sustainable rice production
References
1

Baek N, Lee SI, Pia HI, Park SW, Shin ES, Lee J, Kim HY, Choi WJ. 2025. Biochar effects on methane emission from rice paddy differ with nitrogen fertilization, organic inputs, and water management. Korean J. Soil Sci. Fert. 58:133-143. https://doi.org/10.7745/KJSSF.2025.58.1.133

10.7745/KJSSF.2025.58.1.133
2

Botchkarev A. 2019. A new typology design of performance metrics to measure errors in machine learning regression algorithms. Interdiscip. J. Inf. Knowl. Manag. 14:45-79. https://doi.org/10.28945/4184

10.28945/4184
3

Busman NA, Melling L, Goh KJ, Imran Y, Sangok FE, Watanabe A. 2023. Soil CO2 and CH4 fluxes from different forest types in tropical peat swamp forest. Sci. Total Environ. 858:159973. https://doi.org/10.1016/j.scitotenv.2022.159973

10.1016/j.scitotenv.2022.159973
4

Cui Z, Gong G. 2018. The effect of machine learning regression algorithms and sample size on individualized behavioral prediction with functional connectivity features. NeuroImage 178:622-637. https://doi.org/10.1016/j.neuroimage.2018.06.001

10.1016/j.neuroimage.2018.06.001
5

Hoerl E, Kennard RW, 1970. Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics 12, 55-67. https://doi.org/10.1080/00401706.1970.10488634

10.1080/00401706.1970.10488634
6

Huan S, Liu X. 2025. Machine learning-driven analysis of greenhouse gas emissions from rice production in major Chinese provinces: Identifying key factors and developing reduction strategies. Eur. J. Agron. 164:127536. https://doi.org/10.1016/j.eja.2025.127536

10.1016/j.eja.2025.127536
7

Jahan I, Mehana M, Matheou G, Viswanathan H. 2024. Deep Learning-Based quantification of methane emissions with field applications. Int. J. Appl. Earth Obs. Geoinf. 132:104018. https://doi.org/10.1016/j.jag.2024.104018

10.1016/j.jag.2024.104018
8

Jang H, Kim S. 2022. Income prediction of apple and pear farmers in Chungnam area by automatic machine learning with H2O.Al. Korean J. Agric. Sci. 49:619-627. [in Korean] https://doi.org/10.7744/kjoas.20220056

10.7744/kjoas.20220056
9

Joshi R, Kholiya S, Pandey H, Joshi R, Emmanuel O, Tewari A, Kim T, Cho BK. 2023. A comparison of ATR-FTIR and Raman spectroscopy for the non-destructive examination of terpenoids in medicinal plants essential oils. Korean J. Agric. Sci. 50:675-69. https://doi.org/10.7744/kjoas.500408

10.7744/kjoas.500408
10

Kang YG, Lee JH, Lee JY, Oh TK. 2023a. Statistical estimation of soil carbon stocks in Chungcheong province through digital soil mapping and multiple linear regression. Korean J. Soil Sci. Fert. 56:209-216. [in Korean] https://doi.org/10.7745/KJSSF.2023.56.3.209

10.7745/KJSSF.2023.56.3.209
11

Kang YG, Lee JH, Lee JY, Oh TK. 2023b. The effects of different management strategies on growth and quality of rice (Oryza sativa L.). Korean J. Agric. Sci. 50:75-86. [in Korean] https://doi.org/10.7744/kjoas.20230004

10.7744/kjoas.20230004
12

Kang YG, Lee JY, Kim JH, Oh TK. 2024. Quantifying soil organic matter for sustainable agricultural land management with soil color and machine learning technique. Agron. J. 116:982-989.

10.1002/agj2.21525
13

Kim JH, Kang YG, Lee JY, Kim JH, Choi JW, Oh TK. 2024. Influences of silicate fertilizers containing different rates of iron slag on CH4 emission and rice (Oryza sativa L.) growth. Korean J. Agric. Sci. 51:227-238. [in Korean] https://doi.org/10.7744/kjoas.510213

10.7744/kjoas.510213
14

Kim SU, Lee HH, Kim DH, Lee GH, Hong CO. 2025. Methane emission from paddy soil with different transplanting time of rice (Oryza sativa L.) in Gyeongsang region. Korean J. Soil Sci. Fert. 58:71-80. [in Korean] https://doi.org/10.7745/KJSSF.2025.58.1.071

10.7745/KJSSF.2025.58.1.071
15

Kwon HS, Choi EJ, Lee SI, Lee HS, Lee JM, Kang SS. 2022. Research review of methane emissions from Korean rice paddies. J. Clim. Chang. Res. 13:117-134. [in Korean] https://doi.org/10.15531/KSCCR.2022.13.1.117

10.15531/KSCCR.2022.13.1.117
16

Lee J, Yu M, Oketch EO, Nawarthne SR, Kim YB, Chathuranga NC, Maniraguha V, Cruz BGS, Seo E, Park H, Choi H, Yu DJ, Kim JK, Heo JM. 2024a. Effect of dietary protein levels and age on growth performance, total excreta and nitrogen balance of laying hens during the growing phase. Korean J. Agric. Sci. 51:193-203. [in Korean] https://doi.org/10.7744/kjoas.510210

10.7744/kjoas.510210
17

Lee JH, Lee JY, Kang YG, Kim JH, Oh TK. 2023. Evaluating methane emissions from rice paddies: A study on the cultivar and transplanting date. Sci. Total Environ. 902:166174. https://doi.org/10.1016/j.scitotenv.2023.166174

10.1016/j.scitotenv.2023.166174
18

Lee JY, Kang YG, Kim JH, Kim JH, Choi J, Oh TK. 2024b. Quantification of methane emissions in rice paddies: A machine learning approach with rice cultivar and transplanting date. Korean J. Soil Sci. Fert. 57:331-343. [in Korean] https://doi.org/10.7745/KJSSF.2024.57.4.331

10.7745/KJSSF.2024.57.4.331
19

Nikolaisen M, Hillier J, Smith P, Nayak D. 2023. Modelling CH4 emission from rice ecosystem: A comparison between existing empirical models. Front. Agron. 4:1058649. https://doi.org/10.3389/fagro.2022.1058649

10.3389/fagro.2022.1058649
20

Park HJ, Choi WJ. 2022. Prediction of soil organic carbon contents of rice paddies in South-Western Coastal Area of Korea using random forest models. Korean J. Soil Sci. Fert. 55:58-70. [in Korean] https://doi.org/10.7745/KJSSF.2022.55.1.058

10.7745/KJSSF.2022.55.1.058
21

Pence I, Kumas K, Cesmeli MS, Akyuz A. 2024. Future prediction of biogas potential and CH4 emission with boosting algorithms: the case of cattle, small ruminant, and poultry manure form Turkey. Environ. Sci. Pollut. Res. 31:24461-24479. https://doi.org/10.1007/s11356-024-32666-7

10.1007/s11356-024-32666-738441735PMC10998781
22

Shin JH, Kang YG, Lee JY, Kim JH, Oh TK. 2024. Effect of poultry manure biochar on soil nutrition and carbon improvement in Saemangeum reclaimed soils. Korean J. Agric. Sci. 51:643-654. [in Korean] https://doi.org/10.7744/kjoas.510418

10.7744/kjoas.510418
23

Sonn YK, Yoo JH, Luyima D, Lee JY, Chun JH, Kang YG, Oh TK, Cho J. 2022. Development of models to estimate total soil carbon across different croplands at a regional scale using RGB photography. Int. J. Environ. Res. Public Health 19:9344. https://doi.org/10.3390/ijerph19159344

10.3390/ijerph1915934435954699PMC9368161
24

Su Y, Liu W, Rahaman MH, Chen Z, Zhai J. 2024. Methane emission from water level fluctuation zone of the Three Gorges Reservoir: Seasonal variation and microbial mechanism. Sci. Total Environ. 912:168935. https://doi.org/10.1016/j.scitotenv.2023.168935

10.1016/j.scitotenv.2023.168935
25

Wang Y, Hu Z, He S, Jing Q, Shen L, Wu Z, Huang W, Lu G, Cao R, Zheng K, Dong N, Jiang L, Ye J, Rong A, Xia X, Sun Y. 2023. Linear relationship between CH4 fluxes and atmospheric CO2 concentration levels controlled by rice biomass and soil methanogenic communities. Nutr. Cycl. Agroecosyst. 127:247-263. https://doi.org/10.1007/s10705-023-10299-5

10.1007/s10705-023-10299-5
Information
  • Publisher :Korean Society of Soil Science and Fertilizer
  • Publisher(Ko) :한국토양비료학회
  • Journal Title :Korean Journal of Soil Science and Fertilizer
  • Journal Title(Ko) :한국토양비료학회 학회지
  • Volume : 58
  • No :3
  • Pages :324-334
  • Received Date : 2025-07-22
  • Revised Date : 2025-08-10
  • Accepted Date : 2025-08-18
  • DOI :https://doi.org/10.7745/KJSSF.2025.58.3.324
Journal Informaiton Korean Journal of Soil Science and Fertilizer Korean Journal of Soil Science and Fertilizer
KJSSF Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close