Greenhouse gas (GHG) emissions from paddy fields depend on water management practices and rice varieties. Lysimeter experiments were conducted to determine the effect of rice varieties (lowland; Koshihikari (KH) and upland; Dourado Precoce (DP)) on GHG emissions under two water management practices: alternate wetting and drying (AWD) and continuous flooding (CF). A repeated cycle of drying and wetting in AWD irrigation was performed by drying the soil to −40 kPa soil matric potential and then rewetting. Consequently, the closed chamber method was used to measure direct emissions of methane (CH₄), nitrous oxide (N₂O), and carbon dioxide (CO₂). The result revealed that water management significantly affected CH₄ and N₂O emissions (p < 0.05), while no significant effect was observed between different rice varieties. Although, AWD irrigation reduced CH₄ emissions, it increased N₂O emissions compared to CF irrigation, likely due to increased oxygen supply. AWD irrigation decreased GWP by 55.6% and 59.6% in KH and DP, respectively, compared to CF irrigation. Furthermore, CH₄ and N₂O emissions significantly correlated with soil redox potential and volumetric water content. These results suggest that AWD irrigation might be an effective water management method for mitigating GHG emissions from rice fields in central Japan.

Measurements of greenhouse gas (GHG) emissions from paddy fields can often include flux measurement errors due to either instrument errors or unfavorable weather. Therefore, data post-processing, including the gap-filling process, is required to improve data quality and quantify the GHG flux budget. This study applied machine learning (ML) techniques with polynomial and multivariate polynomial regression models for gap-filling methane (CH4) and carbon dioxide (CO2) fluxes from closed chamber (CC) method measurements and compared results with mean diurnal variation (MDV) and look-up table (LUT) techniques. The most influential factors affecting methane emissions in the paddy field were used for input variables in the models: air temperature, soil temperature, soil redox potential, soil water content, solar radiation, and days after transplanting. The models' performances were compared using mean absolute error (MAE) and root mean square error (RMSE). The results showed that MAE and RMSE for gap-filling CH4 fluxes were 1.299-2.984 and 2.499-4.981 mg CH4 m-2 h-1, respectively. Also, the multivariate polynomial regression models performed better for gap-filling CH4 fluxes (RMSE = 2.499 mg CH4 m-2 h-1) than the polynomial regression models, MDV (RMSE = 3.210 mg CH4 m-2 h-1), and LUT (RMSE = 3.339 mg CH4 m-2 h-1) techniques. The MAE and RMSE for gap-filling CO2 fluxes were 0.282-0.949 and 0.435-1.078 g CO2 m-2 h-1, respectively. The ML techniques with polynomial regression using solar radiation (RMSE = 0.435 g CO2 m-2 h-1) and multivariate models (RMSE = 0.445 g CO2 m-2 h-1) perform better on gap-filling CO2 fluxes than MDV (RMSE = 0.544 g CO2 m-2 h-1), and LUT (RMSE = 0.553 g CO2 m-2 h-1) techniques. The gap-filling using the multivariate polynomial regression models used in this study improved the reliability of the diurnal variation in GHG fluxes. Therefore, ML techniques could be a proper alternative for gap-filling GHG fluxes.