Original research article
Understanding the environmental factors governing yield variability is essential for stabilizing the productivity of the ‘Baromi2’ rice cultivar under diverse field conditions. This study identified the dominant soil, topographic, and climatic drivers of Baromi2 yield variability across ten major production regions by integrating field-measured soil chemistry and meteorological datasets with Sentinel-2-derived vegetation indices. Pearson-Spearman correlation analysis, ariance inflation factor (VIF), filtered multiple linear regression (MLR), and Random Forest (RF) modeling with 5-fold group cross-validation were employed to evaluate the linear and nonlinear contributions of environmental predictors. The MLR model showed limited explanatory power (R2 = 0.53), indicating that linear approaches cannot fully capture complex soil-climate interactions. In contrast, the RF model achieved improved predictive accuracy (R2 = 0.62; RMSE = 27.8 kg 10a-1), and permutation importance analysis consistently identified soil Mg concentration and altitude as the most influential variables. Recursive feature elimination with cross-validation (RFECV) further demonstrated that these two variables alone produced optimal model performance, highlighting the combined effects of Mg accumulation and poor drainage in low-lying paddies as primary constraints on productivity. Partial dependence plots (PDP) confirmed sharp yield reductions at soil Mg > 1.5 cmolc kg-1 and Altitude < 10 m. In addition, the Sentinel-2-derived OffsetV index showed a positive correlation with yield (R2 = 0.52), effectively capturing canopy vigor and photosynthetic persistence under soil-induced stress. Overall, this study demonstrates that integrating soil Mg management, topographic drainage improvement, and satellite-based canopy monitoring provides a practical framework for mitigating yield instability in Baromi2 rice cultivation, particularly in reclaimed and other environmentally vulnerable landscapes.
Ahn BK, Lim YY, Ko DY, Lee CK, Kim JH, Song YJ, Lee JH. 2016. Investigation of Soil Physico-chemical Properties in Saemangeum Reclaimed Tidal Land in Korea. Korean J. Soil Sci. Fert. 49:347-354. https://doi.org/10.7745/KJSSF.2016.49.4.347
10.7745/KJSSF.2016.49.4.347Becker-Reshef I, Vermote E, Lindeman M, Justice C. 2010. A generalized regression-based model for forecasting winter wheat yields in Kansas and Ukraine using MODIS data. Remote Sens. Environ. 114:1312-1323. https://doi.org/10.1016/j.rse.2010.01.010
10.1016/j.rse.2010.01.010Breiman L. 2001. Random Forests. Mach. Learn. 2001. Machine Learning. 45:5-32. https://doi.org/10.1023/A:1010933404324 A:1010933404324
10.1023/A:1010933404324Cao J, Zhang Z, Luo Y, Zhang L, Zhang J, Li Z, Tao F. 2021. Wheat yield predictions at a county and field scale with deep learning, machine learning, and google earth engine. European J. Agron. 123. https://doi.org/10.1016/j.eja.2020.126204
10.1016/j.eja.2020.126204Chen Y, Cao R, Chen J, Liu L, Matsushita B. 2021. A practical approach to reconstruct high-quality Landsat NDVI time-series data by gap filling and the Savitzky-Golay filter. ISPRS J. Photogram. Remote Sens. 180:174-190. https://doi.org/10.1016/j.isprsjprs.2021.08.015
10.1016/j.isprsjprs.2021.08.015De Clercq D and Mahdi A. 2025. Modern computational approaches for rice yield prediction: A systematic review of statistical and machine learning-based methods. Comput. Electro. Agri. 231. https://doi.org/10.1016/j.compag.2024.109852
10.1016/j.compag.2024.109852Deng N, Ling X, Sun Y, Zhang C, Fahad S, Peng S, Cui K, Nie L, Huang J. 2015. Influence of temperature and solar radiation on grain yield and quality in irrigated rice system. Europ. J. Agron. 64:37-46. https://doi.org/10.1016/j.eja.2014.12.008
10.1016/j.eja.2014.12.008Deng L, Mao Z, Li X, Hu Z, Duan F, Yan Y. 2018. UAV-based multispectral remote sensing for precision agriculture: A comparison between different cameras. ISPRS J. Photogram. Remote Sens. 146:124-136. https://doi.org/10.1016/j.isprsjprs.2018.09.008
10.1016/j.isprsjprs.2018.09.008Franch B, San Bautista A, Fita D, Rubio C, Tarrazó-Serrano D, Sánchez A, Skakun S, Vermote E, Becker-Reshef I, Uris A. 2021. Within-field rice yield estimation based on sentinel-2 satellite data. Remote Sens. 13:4095. https://doi.org/10.3390/rs13204095
10.3390/rs13204095Ghaley BB. 2012. Uptake and utilization of 5-split nitrogen topdressing in an improved and a traditional rice cultivar in the bhutan highlands. Exp. Agric. 48:536-550. https://doi.org/10.1017/S0014479712000440
10.1017/S0014479712000440Guyon I, Weston J, Barnhill S, Vapnik V. 2022. Gene Selection for Cancer Classification using Support Vector Machines. Machine Learning. 46:389-422. https://doi.org/10.1023/A:1012487302797
10.1023/A:1012487302797Ha SK, Kim BK, Hwang WH, Mo YJ, Jeong JM, Lee DK, Kim WJ, Kim JJ, Jeung JU. 2022. Early Maturing Rice Variety “Baromi2” with a Floury Endosperm and Suitable for Dry-Milling of Rice Grain. Korean J. Breed. Sci. 54:433-441. https://doi.org/10.9787/KJBS.2022.54.4.433
10.9787/KJBS.2022.54.4.433Hailemariam MB, Woldu Z, Asfaw Z, Lulekal E. 2023. Impact of Elevation Change on the Physicochemical Properties of Forest Soil in South Omo Zone, Southern Ethiopia. Appl. Environ. Soil Sci. 2023, 7305618 https://doi.org/ 10.1155/2023/7305618
10.1155/2023/7305618Hwang YB, Hwang HY, An NH, Lee SM, Lee CR. 2025. Effect of organic materials on phosphorus solubilization in phosphate-accumulated soils: an incubation study. Korean J. Soil Sci. Fert. 58:47-58. https://doi.org/10.7745/KJSSF.2025.58.1.047 KJSSF.2025.58.1.047
10.7745/KJSSF.2025.58.1.047IRRI (International Rice Research Institute). 2013. Standard evaluation system for rice (5th ed.). IRRI, Los Baños, Philippines.
Jeong YJ, Lim SS, Park HJ, Seo BS, Park SI, Ryu JH, Lee KS, Chung DY, Kim HY, Lee SH, et al. 2020. Evaluation of crop suitability for reclaimed tideland soils using soil and water salinity and soil texture. Korean J. Soil Sci. Fert. 53:70-81. https://doi.org/10.7745/KJSSF.2020.53.1.070
10.7745/KJSSF.2020.53.1.070Ji Z, Pan Y, Zhu X, Wang J, Li Q. 2021. Prediction of crop yield using phenological information extracted from remote sensing vegetation index. Sensors. 21:1-17. https://doi.org/10.3390/s21041406
10.3390/s2104140633671356PMC7922106Kim WJ, Skalsky R, Folberth C, Lee SJ, Schepaschenko D, Kraxner F, Kim J, Kim CG, Jeon SW, Son YW, Lee WK. 2025. A Comparative Assessment of Food Security in South and North Korea Using Food Demand and Supply. Land. 14:1703. https://doi.org/10.3390/land14091703
10.3390/land14091703Kwak D. 2025. Guidebook on Major Rice Varieties. Wanju: Rural Development Administration, National Institute of Crop Science
Lee KB, Kang JG, Lee KD, Lee SH, Hwang SA, Hwang SW, Kim HK. 2013. Soil Characteristics of Newly Reclaimed Tidal Land and Its Changes by Cultivation of Green Manure Crops. Korean J. Soil Sci. Fert. 46:129-135. http://dx.doi.org/10.7745/KJSSF.2013.46.2.129
10.7745/KJSSF.2013.46.2.129Lee YB and Kim KR. 2025. Changes in soil chemical properties and the impact of livestock manure compost use in Korean agricultural soil: sustainable soil management strategies. Korean J. Soil Sci. Fert. 58:262-270. https://doi.org/10.7745/KJSSF.2025.58.2.262
10.7745/KJSSF.2025.58.2.262Li L, Zhang Y, Wang B, Feng P, He Q, Shi Y, Liu K, Harrison MT, Liu DL, Yao N, Li Y, He J, Feng H, Siddique KHM, Yu Q. 2023. Integrating machine learning and environmental variables to constrain uncertainty in crop yield change projections under climate change. Europ. J. Agron. 149:126917. https://doi.org/10.1016/j.eja.2023.126917
10.1016/j.eja.2023.126917Liu P, Zhang T, Wang G, Ju J, Mao W, and Zhao H. 2023. Response of Rice Grain Yield and Soil Fertility to Fertilization Management under Three Rice-Based Cropping Systems in Reclaimed Soil. Agronomy. 13:23. https://doi.org/10.3390/agronomy13071840
10.3390/agronomy13071840Ma JW, Nguyen CH, Lee K, Heo J. 2019. Regional-scale rice-yield estimation using stacked auto-encoder with climatic and MODIS data: a case study of South Korea. Int. J. Remote Sens. 40:51-71. https://doi.org/10.1080/01431161.2018.1488291
10.1080/01431161.2018.1488291Ma L, Xiong Z, Yao L, Liu G, Zhang Q, Liu W. 2020. Soil properties alter plant and microbial communities to modulate denitrification rates in subtropical riparian wetlands. Land Degrad. Dev. 31:1792-1802. https://doi.org/10.1002/ldr.3569
10.1002/ldr.3569Moldenhauer K, Counce P, and Hardke J. 2021. Rice Growth and Development, in Rice Production Handbook, J. Hardke, Ed., ater Management University of Arkansas Division of Agriculture Cooperative Extension Service. 2:9-20. https://www.uaex.uada.edu/publications/pdf/mp192/mp192.pdf
O’brien RM. 2007. A Caution Regarding Rules of Thumb for Variance Inflation Factors. Qual. Quant. 41:673-690. https://doi.org/10.1007/s11135-006-9018-6
10.1007/s11135-006-9018-6Ock HK, Lee KS, Jung KH, Lee SW, Oh YY. 2022. Growth Responses of Kenaf (Hibiscus cannabinus L.) to Irrigation and Fertilization in Saemangeum Reclaimed Land. Korean J. Soil Sci. Fert. 55:273-285. https://doi.org/10.7745/KJSSF.2022.55.4.273
10.7745/KJSSF.2022.55.4.273Onojeghuo AO, Blackburn GA, Wang Q, Atkinson PM, Kindred D, Miao Y. 2017. Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data. Int. J. Remote Sens. 4:1042-1067. https://doi.org/10.1080/01431161.2017.1395969.
10.1080/01431161.2017.1395969Park HJ, Seo BS, Jeong YJ, Yang HI, Park SI, Baek N, Kwak JH, Choi WJ. 2021. Soil salinity, fertility and carbon content, and rice yield of salt-affected paddy with different cultivation period in southwestern coastal area of South Korea. Soil Sci. Plant Nutri. 68:53-63. https://doi.org/10.1080/00380768.2021.1967082
10.1080/00380768.2021.1967082Park SW, Baek N, Lee SI, Shin ES, Lee JY, Lee KS, Kang BH, Lee KS, Kim HY, Choi WJ. 2025. Water quality of inland lakes affects salinity and sodicity of coastal paddy soils in southwestern Korea. Korean J. Soil Sci. Fert. 58:59-70. https://doi.org/10.7745/KJSSF.2025.58.1.059
10.7745/KJSSF.2025.58.1.059Paudel D, de Wit A, Boogaard H, Marcos D, Osinga S, Athanasiadis IN. 2023. Interpretability of deep learning models for crop yield forecasting. Computers and Electro. Agri. 206. https://doi.org/10.1016/j.compag.2023.107663. 107663
10.1016/j.compag.2023.107663Quille-Mamani JA, Ruiz LA, Ramos-Fernández L. 2023. Rice Crop Yield Prediction from Sentinel-2 Imagery Using Phenological Metric. Environ. Sci. Proceed. 16:16. https://doi.org/10.3390/environsciproc2023028016
10.3390/environsciproc2023028016Rouse JWJ, Haas RH, Schell JA, Deering DW. 1974. Monitoring vegetation systems in the great plains with ERTS. NASA. Goddard Space Flight Center 3d ERTS-1 Symp. 1:309-317. https://ntrs.nasa.gov/api/citations/19740022614/downloads/19740022614.pdf
Savitzky A and Golay MJE. 1964. Smoothing and Differentiation of Data by Simplified Least Squares Procedures. Anal. Chem. 36:1627-1639. https://doi.org/10.1021/ac60214a047
10.1021/ac60214a047Seo BS, Jeong YJ, Lee KS, Choi WJ. 2021. Effects of equilibrium time on electrical conductivity measurements using soil-water extracts and soil saturated paste. Korean J. Soil Sci. Fert. 54:257-263. https://doi.org/10.7745/KJSSF.2021.54.2.257
10.7745/KJSSF.2021.54.2.257Shook J, Gangopadhyay T, Wu L, Ganapathysubramanian B, Sarkar S, Singh AK. 2021. Crop yield prediction integrating genotype and weather variables using deep learning. PLoS One. 16:e0252402. https://doi.org/10.1371/journal.pone.0252402
10.1371/journal.pone.025240234138872PMC8211294Soriano-González J, Angelats E, Martínez-Eixarch M, and Alcaraz C. 2022. Monitoring rice crop and yield estimation with Sentinel-2 data. Field Crops Res. 281. https://doi.org/10.1016/j.fcr.2022.108507
10.1016/j.fcr.2022.108507Statistics Korea. 2024. Agricultural Area Survey: Cultivated land area by type (rice field and dry field) by province. https://kosis.kr/statHtml/statHtml.do?orgId=101&tblId=DT_1ET0021&conn_path=I2
Tucker CJ. 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens. Environ. 8:127-150. https://doi.org/10.1016/0034-4257(79)90013-0
10.1016/0034-4257(79)90013-0Wang L, Zhang FC, Jing YS, Jiang XD, Yang SB, Han XM. 2014. Multi-temporal detection of rice phenology stages using canopy stagespectrum. Rice Sci. 21:108-115. https://doi.org/10.1016/S1672-6308(13)60170-5
10.1016/S1672-6308(13)60170-5White PJ. 2011. Growth and Mineral Nutrition of Field Crops. 3rd edition. By Fageria NK, Baligar VC and Jones CA. Boca Raton, FL, USA: CRC Press. Experimental Agriculture. 47:574. ISBN 978-1-4398-1695-0. https:// doi.org/10.1017/S0014479711000263
10.1017/S0014479711000263- 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 : 59
- No :1
- Pages :61-76
- Received Date : 2025-11-03
- Revised Date : 2025-11-24
- Accepted Date : 2025-11-26
- DOI :https://doi.org/10.7745/KJSSF.2026.59.1.061
Korean Journal of Soil Science and Fertilizer
