Attention 기반 Encoder-Decoder 모델을 활용한 작물의 생산량 예측
Forecasting Crop Yield Using Encoder-Decoder Model with Attention
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Purpose: The purpose of this study is the time series analysis for predicting the yield of crops applicable to each farm using environmental variables measured by smart farms cultivating tomato. In addition, it is intended to confirm the influence of environmental variables using a deep learning model that can be explained to some extent. Methods: A time series analysis was performed to predict production using environmental variables measured at 75 smart farms cultivating tomato in two periods. An LSTM-based encoder-decoder model was used for cases of several farms with similar length. In particular, Dual Attention Mechanism was applied to use environmental variables as exogenous variables and to confirm their influence. Results: As a result of the analysis, Dual Attention LSTM with a window size of 12 weeks showed the best predictive power. It was verified that the environmental variables has a similar effect on prediction through wieghtss extracted from the prediction model, and it was also verified that the previous time point has a greater effect than the time point close to the prediction point. Conclusion: It is expected that it will be possible to attempt various crops as a model that can be explained by supplementing the shortcomings of general deep learning model.
Abstract
Purpose: The purpose of this study is the time series analysis for predicting the yield of crops applicable to each farm using environmental variables measured by smart farms cultivating tomato. In addition, it is intended to confirm the influence of environmental variables using a deep learning model that can be explained to some extent. Methods: A time series analysis was performed to predict production using environmental variables measured at 75 smart farms cultivating tomato in two periods. An LSTM-based encoder-decoder model was used for cases of several farms with similar length. In particular, Dual Attention Mechanism was applied to use environmental variables as exogenous variables and to confirm their influence. Results: As a result of the analysis, Dual Attention LSTM with a window size of 12 weeks showed the best predictive power. It was verified that the environmental variables has a similar effect on prediction through wieghtss extracted from the prediction model, and it was also verified that the previous time point has a greater effect than the time point close to the prediction point. Conclusion: It is expected that it will be possible to attempt various crops as a model that can be explained by supplementing the shortcomings of general deep learning model.
참고문헌 (18)
- Alhnaity, B., "Using Deep Learning to Predict Plant Growth and Yield in Greenhouse Environments", Acta Hortic, 1296, pp.425~432 (2020)
- Chen, T., "TADA : Trend Alignment with Dual-Attention Multi-Task Recurrent Neural Networks for Sales Prediction", 2018 IEEE International Conference on Data Mining, pp.49~58 (2018)
- Chen, Y., "A dual-Attention-Based Stock Price Trend Prediction Model With Dual Features", IEEE Access, 7, pp.148047~148058 (2019)
- Choudhury, A., "Crop Yield Prediction Using Time Series Models", Journal of Economic and Economic Education Research, 15(3), pp.53~68 (2014)
- 정대희, "기후변화를 고려한 쌀 토지생산성 모형의 예측력 평가", 환경정책, 26(4), pp.197~222 (2018), 한국환경정책학회[DOI]
- Dharmaraja, S., "Empirical Analysis for Crop Yield Forecasting in India", Agric Res, 9(1), pp.132~138 (2020)
- Farook, A., J., "Climate Change Impact on Rice Yield in India-Vector Autoregression Approach", Sri Lankan Journal of Applied Statistics, 16(3), pp.161~178 (2014)
- Feng, L., "Dual attention-based encoder-decoder: A customized sequence-to-sequence learning for soft sensor development", IEEE Transactions on Neural Networks and Learning Systems, pp.1~12 (2020)[DOI]
- 한민수, "Long Short-Term Memory를 활용한 건화물운임지수 예측", 품질경영학회지, 47(3), pp.497~508 (2019), 한국품질경영학회[DOI]
- Hossain, M., M., "On the Production Behaviors and Forecasting the Tomatoes Production in Bangladesh", Journal of Agricultural Economics and Development, 4(5), pp.66~74 (2015)
- Jiang, Z., "Predicting county-scale maize yields with publicly available data", Scientific Reports, 10, pp.14957~ (2020)
- 김나리, "기후재분석자료 시계열모델링을 통한 곡물수확량 예측실험: 1960-2009년 미국 아이오와주 사례", 한국지도학회지, 16(2), pp.115~126 (2016), 한국지도학회
- 이승훈, "광업 데이터의 시계열 분석을 통해 실리카 농도를 예측하기 위한 머신러닝 모델", 품질경영학회지, 48(3), pp.511~520 (2020), 한국품질경영학회[DOI]
- Li, L., "Time+User Dual Attention Based Sentiment Prediction for Multiple Social Network Texts With Time Series", IEEE Access, 7, pp.17644~17653 (2018)
- 나명환, "딥러닝 알고리즘을 이용한 토마토에서 발생하는 여러가지 병해충의 탐지와 식별에 대한 웹응용 플렛폼의 구축", 품질경영학회지, 48(4), pp.581~596 (2020), 한국품질경영학회[DOI]
- 오승원, "공간 및 기상정보 시계열 모형을 이용한 양파 생산량 예측", Journal of The Korean Data Analysis Society, 19(5), pp.2447~2456 (2017), 한국자료분석학회[DOI]
- Qin, Y., "A dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction", arXiv preprint:1704.02971, ~ (2017)
- Shook, J., "Crop Yield Prediction Integrating Genotype and Weather Variables Using Deep Learning", arXiv preprint:2006.13847, ~ (2020)