노지 채소 경작에서 최적의 재배전략과 생구무게의 예측
(Optimal Cultivation Strategies and Prediction of Fresh Weight in Vegetable Farming)
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
작금의 농업현장에서 노지에서 재배되고 있는 작물들은 기후와 온도변화, 강수량 등의 문제가 발생하며, 여러 가지 환경요인과 재배 방법에 따라서 수확량이 크게 달라지고 있다. 따라서 양파와 마늘 등 작물의 수확량을 극대화할 수 있는 재배전략과 이를 확인할 수 있는 생구무게의 예측방법을 제안하였다. 무안의 파속채소연구소에 시범단지를 조성하여 양파와 마늘 각각에 대해서 일정한 간격으로 수작업을 통한 생육특성, 다분광 영상을 통한 식생지수 그리고 이들에 대응되는 생구무게를 측정하였다. 이를 NFCRM(Nonparametric Functional Concurrent Regression Model), RFRM(Random Forest Regressor Model), 1D-CABL(1D-CNN+Attention BiLSTM) 세 가지 예측모형을 사용하여 생구무게를 예측할 때 어떤 모형이 예측력이 가장 우수한지 비교 분석하였다. 성능을 비교한 결과 양파와 마늘 모두 NFCRM이 RFRM와 1DCABL의 경우보다 예측력이 우수한 것으로 나타났다.
Abstract
Crops grown in open fields are greatly affected by various environmental factors such as climate, temperature changes and precipitation which can significantly influence crop yields depending on cultivation methods and environmental conditions. Therefore, this study proposes cultivation strategies to maximize the yield of onions and garlic along with methods for predicting bulb weight. An experimental site was established at the Allium Crop Research Institute in Muan, where growth characteristics were manually measured, and vegetation indices were acquired using multispectral imaging, along with corresponding bulb weights for both onions and garlic at regular intervals. To predict bulb weight, three predictive models were applied: NFCRM, RFRM, and 1D-CNN+Attention BiLSTM. Comparative analysis of predictive performance showed that NFCRM outperformed the other models, RFRM and 1DCABL, in predicting of the bulb weight of both onions and garlic.
참고문헌 (32)
- Ali, M. H. E., "Deep Learning Peephole LSTM Neural Network-Based Channel Stat Estimators for OFDM 5G and Beyond Networks", Mathematics, 11(15), pp.3386~ (2023)
- Bhattachariee, S., "Concurrent object regression", Electronic Journal of Statistics, 16(2), pp.4031~4089 (2022)
- Borup, D., "Targeting predictors in random forest regression", International Journal of Forecasting, 39(2), pp.841~868 (2023)
- Breiman, L., "Ramdom Forests", Machine Learning, 45, pp.5~32 (2001)
- Liaw, A., "Classification and Regression by randomFores", R News, 2(3), pp.18~22 (2002)
- Carr, T. W., "Climate change impacts and adaptation strategies for crops in West Africa : a systematic review", Environmental Research Letters, 17, pp.1~15 (2022)
- Fan, M., "Improving crop productivity and resource use efficiency to ensure food security and environmental quality in China", Journal Of Exerimental Botany, 63(1), pp.13~24 (2012)
- Ghasemi, J. B., "Application of random forest regression to spectral multivariate calibration", Analytical Methods, 7(5), pp.1863~1871 (2013)
- Ghosal, R., "Variable selection in nonparametric functional concurrent regression", The Canadian Journal of Statistics, 50(1), pp.142~161 (2022)
- Guo, J., "Attention-based BILSTM for the degradation trend prediction of lithium battery", Energy Reports, 9, pp.655~664 (2023)
- Kang, Q., "Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling", Underground Space, 13, pp.335~350 (2023)
- Kim, A R., "The Design of the 1D CNN-GRU Network Based on the RCS for Classification of Multiclass Missiles", Remote Sensing, 15(3), pp.31~19 (2023)
- Kim, J., "Tutorial on time series prediction using 1D-CNN and BiLSTM : A case example of perk electricy demand and system marginal price prediction", Engineering Applications of Artificial Intelligence, 126, pp.1~14 (2023)
- Kim, J. S., "Additive nonlinear functional concurrent model", Statistics and Its Interface, 11(4), pp.669~685 (2018)
- Leung, H., "Stressed genomics-Bringing relief to rice fields", Current Opinion in Plant Biology, 11(2), pp.201~208 (2008)
- Liu, Fan., "Attention Mechanism-Combined LSTM for Grain Yield Prediction in China Using Multi-Source Satellite Imagery", Sustainability, 15(12), pp.1~20 (2023)
- Maity, A., "Nonparametric functional concurrent regression models", Advanced Review, 9(9), pp.1~11 (2017)
- Metclfe D. S., "Crop Production : Principles and Practices" (1980), Macmillan Publishing Co
- Inc. Michelon, N., "Strategies for Improved Yield and Water UseEfficiency of Lettuce(Lactuca sativa L. )throughSimplified Soilless Cultivation underSemi-Arid Climate", Agronomy, 10(9), pp.1379~ (2020)
- Muhammad, L. N., "Guidelines for repeated measures statistical analysis approaches with basic science research considerations", The Journal of Clinical Investigation, 133(11) (2023)
- Noya, I., "Environmental impacts of the cultivation-phase associated with agricultural crops for feed production", Journal of Cleaner Production, 172, pp.3741~3733 (2019)
- Oldfield, E. E., "Global meta-analysis of the relationship between soil organic matter and crop yields", The Soil, 5(1), pp.15~32 (2019)
- Pan, R., "Detection of Interaction Effects in a Nonparametric Concurrent Regression Model", Entropy, 25(9), pp.1~15 (2023)
- Park, D. G., "Analysis of variance and repeated measures data" (2007), Minyeongsa
- Park, E., "Correct Use of Repeated Measures Analysis of Variance", Korean J Lab Med, 29(1), pp.1~9 (2009)
- Sathi, K. A., "Attention-assisted hybrid 1D CNN-BiLSTM model for predicting electric field induced by transcranial magnetic stimulation coil", Scientific Reports, 13(1), pp.1~12 (2023)
- Shanmuga, P. S, "Attention based Peephole LSTM model for Soybean crop yield prediction", Journal of Physics : Conference Series, 2571(1), pp.1~9 (2023)
- Singh, PK, "Efficient crop management strategies to improve cropresilience and crop-water productivity enhancementunder direct seeded rice cultivation system in adverseclimatic conditions : A review", The Pharma Innovation, 12(4), pp.1988~1997 (2023)
- Relationship between changers in agricultural productivity and the incidence of poverty in developing countries, "Thirtle, C.", DFID, 1~33, pp.DFID Report, No. 7946 (2001)
- Turner, N. C., "Strategies to increase the yield and yield stability of crops under drought-are we making progress?", Functional Plant Biology, 41(11), pp.1199~1206 (2014)
- Wu, P., "A Combined Deep Learning Method with Attention-Based LSTM Model for Short-Term Traffic Speed Forecasting", Journal of Advanced Transportation, 2020(1), pp.1~15 (2020)
- Xu, H., "Optimized management strategy increased grain yield, promoted nitrogen balance, and improved water productivity in winter wheat", Frontiers in Plant Science, 2023(14), pp.1~14 (2023)