A Study on the Prediction of Rice Yields of Agricultural Use in Saemangeum Reclaimed Land Using Satellite Imagery and Deep Learning

Sooyoung Lim; Eunhye Ha; Gunhak Lee

doi:10.22776/kgs.2023.58.6.585

All Issue

2023 Vol.58, Issue 6 Preview Page Next Page

Research Article

A Study on the Prediction of Rice Yields of Agricultural Use in Saemangeum Reclaimed Land Using Satellite Imagery and Deep Learning 위성영상과 딥러닝을 이용한 새만금 간척지의 벼 수확량 예측 연구

31 December 2023. pp. 585-598

PDF XML

Abstract

As 30 years have passed since the start of the Saemanguem Comprehensive Development Plan, it is time for a diagnosis of the Saemangeum project. In particular, the agricultural land in Saemangeum is a major goal of the first phase of the development plan, which was most recently completed (2020), and agricultural activities have recently begun in the temporary agricultural lease area. In this context, this study aims to present a deep neural network model that can provide an assessment of the potential for agricultural land creation and food production in regions designated for temporary farming from agricultural land in Saemangeum. For this purpose, the Enhanced Vegetation Index (EVI), Vegetation Soil Salinity Index (VSSI), Land Surface Water Index (LSWI) constructed from satellite images, and meteorological variables were used to construct a dataset that reflects spatiotemporal variation in paddy land cover across the country. As a result of the validation of the model, the RMSE (Root Mean Square Error) was 7.5901 (t) and R2 was 0.9980 which demonstrated excellent performance compared to previous studies of several machine learning models such as Random Forest, GBDT, Adaboost, and Linear Regression. When applied to the region designated as temporary farming areas, it demonstrated an average expected yield of 415kg per 10a, which was lower than the national average rice yield standard of 518kg per 10a in 2022. This study is expected to be used for the future sustainable land use plan for Saemangeum and policymaking, by specifically showing the potential utilization of agricultural lands in Saemangeum through satellite images and a deep learning approach.

Keywords

satellite imagery

deep learning

deep neural network

rice yield

Saemangeum reclaimed lands

새만금 종합개발계획 착공 30년이 지난 현재, 새만금 사업에 대한 진단이 필요한 시점이다. 특히 새만금의 농생명용지는 가장 최근 완료 시점(2020년)이 도래한 1단계 개발계획의 주요 목표이며, 최근 해당 용지 내 임시영농 임대 구역에서 농업 활동이 시작되었다. 이에 본 연구에서는 새만금 간척지 임시영농 구역의 농업용지 조성 및 식량 생산 가능성에 대한 평가를 위한 심층신경망 모델을 제시하고자 한다. 이를 위해 전국의 논 토지피복에 대해 시공간적 변이를 반영하는 데이터셋을 구성하였고, 위성영상 기반 강화식생지수(EVI), 식생토양염분지수(VSSI), 지표수분지수(LSWI) 및 기상 변수를 사용하여 훈련을 진행하였다. 기존 연구에서 제시한 머신러닝 모델(Random Forest, GBDT, Adaboost, Linear regression)들과 성능을 비교한 결과, 본 연구에서 제안하는 DNN 모델이 RMSE 7.5901(t), R² 0.9980로 우수한 성능을 보였다. 이를 새만금 임시영농 구역에 적용한 결과, 2022년 기준 전국 평균 벼 수확량인 518kg/10a에 못 미치는 415kg/10a의 2023년 예측 수확량을 나타내었다. 본 연구는 위성영상 데이터와 딥러닝을 통해 새만금 간척지 농업용지의 잠재적 활용성을 보다 구체적으로 진단함으로써 향후 지속가능한 새만금 토지이용 계획과 정책 수립에 기여할 것으로 기대된다.

키워드

위성영상

딥러닝

심층신경망

벼 수확량

새만금 간척지

References

김경섭･정윤재･전병운, 2022, "Sentinel-2 위성영상과 강우 및 토양자료를 활용한 벼 수량 예측," 한국지리정보학회지, 25(1), 133-149.

농촌진흥청 국립식량과학원, 2022, 새만금 농생명용지 5공구 토양 화학성 조사.

박종화･나상일･이규호･백신철･김형섭, 2010, 농작물 생산통계의 원격탐사기술 활용방안 연구, 통계청.

새만금개발청, 2014, 새만금 기본계획.

새만금개발청, 단계별 개발계획, https://www.saemangeum. go.kr/sda/content.do?key=2108029121381, 2023년 6월 23일 접속.

오창환･김재병･한승우･오동필･김강주, 2020, 새만금 수질 평가 및 개선방향 제시를 위한 연구용역 보고서, 전북대 지구환경과학과 지구환경시스템 연구소.

조경숙･윤진일, 1999, "일기상자료에 의한 읍면별 벼 작황진단 및 쌀 생산량 예측," 한국농림기상학회지, 1(1), 1-10.

조수빈･윤유정･김서연･정예민･김근아･강종구･이양원, 2021, "우리나라 시군단위 벼 수확량 예측을 위한 다종 기상자료의 비교평가," 대한원격탐사학회지, 37(2), 337-357.

홍석영･허지나･안중배･이지민･민병걸･이충근･김이현･이경도･김선화･김건엽･심교문, 2012, "MODIS NDVI와 기상자료를 이용한 우리나라 벼 수량 예측," 대한원격탐사학회지, 28(5), 509-520. 10.7780/kjrs.2012.28.5.4

Bhojani, S. H. and Bhatt, N., 2020, Wheat crop yield prediction using new activation functions in neural network, Neural Computing and Applications, 32, 13941-13951. 10.1007/s00521-020-04797-8

Bouman, B. A., Humphreys, E., Tuong, T. P. and Barker, R., 2007, Rice and water, Advances in Agronomy, 92, 187-237. 10.1016/S0065-2113(04)92004-4

Cao, J., Zhang, Z., Luo, Y., Zhang, L., Zhang, J., Li, Z. and Tao, F., 2021, Wheat yield predictions at a county and field scale with deep learning, machine learning, and google earth engine, European Journal of Agronomy, 123, 126204. 10.1016/j.eja.2020.126204

Chandrasekar, K., Sesha Sai, M. V. R., Roy, P. S., and Dwevedi, R. S., 2010, Land Surface Water Index (LSWI) response to rainfall and NDVI using the MODIS vegetation index product, International Journal of Remote Sensing, 31(15), 3987-4005. 10.1080/01431160802575653

Dehni, A. and Lounis, M., 2012, Remote sensing techniques for salt affected soil mapping: application to the Oran region of Algeria, Procedia Engineering, 33, 188-198. 10.1016/j.proeng.2012.01.1193

Filippi, P., Jones, E. J., Wimalathunge, N. S., Somarathna, P. D., Pozza, L. E., Ugbaje, S. U., Jephcott, T. G., Paterson, S. E., Whelan, B. M. and Bishop, T. F., 2019, An approach to forecast grain crop yield using multi- layered, multi-farm data sets and machine learning, Precision Agriculture, 20, 1015-1029. 10.1007/s11119-018-09628-4

Jeong, S., Ko, J. and Yeom, J. M., 2022, Predicting rice yield at pixel scale through synthetic use of crop and deep learning models with satellite data in South and North Korea, Science of The Total Environment, 802, 149726. 10.1016/j.scitotenv.2021.14972634464811

Ji, B., Sun, Y., Yang, S., and Wan, J., 2007, Artificial neural networks for rice yield prediction in mountainous regions, The Journal of Agricultural Science, 145(3), 249-261. 10.1017/S0021859606006691

Khaki, S. and Wang, L., 2019, Crop yield prediction using deep neural networks, Frontiers in Plant Science, 10, 621. 10.3389/fpls.2019.0062131191564PMC6540942

Maimaitijiang, M., Sagan, V., Sidike, P., Hartling, S., Esposito, F. and Fritschi, F. B., 2020, Soybean yield prediction from UAV using multimodal data fusion and deep learning, Remote Sensing of Environment, 237, 111599. 10.1016/j.rse.2019.111599

Muruganantham, P., Wibowo, S., Grandhi, S., Samrat, N. H. and Islam, N., 2022, A systematic literature review on crop yield prediction with deep learning and remote sensing, Remote Sensing, 14(9), 1990. 10.3390/rs14091990

Nguyen, K. A., Liou, Y. A., Tran, H. P., Hoang, P. P. and Nguyen, T. H., 2020, Soil salinity assessment by using near-infrared channel and vegetation soil salinity index derived from Landsat 8 OLI data: a case study in the Tra Vinh Province, Mekong Delta, Vietnam, Progress in Earth and Planetary Science, 7, 1-16. 10.1186/s40645-019-0311-0

Paudel, D., Boogaard, H., de Wit, A., Janssen, S., Osinga, S., Pylianidis, C. and Athanasiadis, I. N., 2021, Machine learning for large-scale crop yield forecasting, Agricultural Systems, 187, 103016. 10.1016/j.agsy.2020.103016

Saravi, B., Nejadhashemi, A. P. and Tang, B., 2020, Quantitative model of irrigation effect on maize yield by deep neural network, Neural Computing and Applications, 32, 10679-10692. 10.1007/s00521-019-04601-2

Son, N. T., Chen, C. F., Chen, C. R., Minh, V. Q. and Trung, N. H., 2014, A comparative analysis of multitemporal MODIS EVI and NDVI data for large-scale rice yield estimation, Agricultural and Forest Meteorology, 197, 52-64. 10.1016/j.agrformet.2014.06.007

Sridevi, V. and Chellamuthu, V., 2015, Impact of weather on rice - a review, International Journal of Applied Research, 1(9), 825-831.

Van Klompenburg, T., Kassahun, A. and Catal, C., 2020, Crop yield prediction using machine learning: a systematic literature review, Computers and Electronics in Agriculture, 177, 105709. 10.1016/j.compag.2020.105709

Information

Publisher :The Korean Geographical Society
Publisher(Ko) :대한지리학회
Journal Title :Journal of the Korean Geographical Society
Journal Title(Ko) :대한지리학회지
Volume : 58
No :6
Pages :585-598
Received Date : 2023-09-25
Revised Date : 2023-11-09
Accepted Date : 2023-11-27
DOI :https://doi.org/10.22776/kgs.2023.58.6.585

Journal of the Korean Geographical Society 대한지리학회지 ISSN:1225-6633(Print)

All Issue