Korean Journal of Agricultural and Forest Meteorology (한국농림기상학회지)

Korean Society of Agricultural and Forest Meteorology (한국농림기상학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Soil Moisture with Open Source Weather Data and Machine Learning Algorithms

공공 기상데이터와 기계학습 모델을 이용한 토양수분 예측

  • Jang, Young-bin (Program in Regional Information, Department of Agricultural Economics and Rural Development, College of Agriculture and Life Sciences, Seoul National University) ;
  • Jang, Ik-hoon (Program in Regional Information, Department of Agricultural Economics and Rural Development, College of Agriculture and Life Sciences, Seoul National University) ;
  • Choe, Young-chan (Program in Regional Information, Department of Agricultural Economics and Rural Development, College of Agriculture and Life Sciences, Seoul National University)
  • 장영빈 (서울대학교 농생명과학대학 농경제사회학부 지역정보 전공) ;
  • 장익훈 (서울대학교 농생명과학대학 농경제사회학부 지역정보 전공) ;
  • 최영찬 (서울대학교 농생명과학대학 농경제사회학부 지역정보 전공)
  • Received : 2019.12.10
  • Accepted : 2020.03.16
  • Published : 2020.03.30
Download PDF
⟨ Previous Next ⟩

Abstract

As one of the essential resources in the agricultural process, soil moisture has been carefully managed by predicting future changes and deficits. In recent years, statistics and machine learning based approach to predict soil moisture has been preferred in academia for its generalizability and ease of use in the field. However, little is known that machine learning based soil moisture prediction is applicable in the situation of South Korea. In this sense, this paper aims to examine 1) whether publicly available weather data generated in South Korea has sufficient quality to predict soil moisture, 2) which machine learning algorithm would perform best in the situation of South Korea, and 3) whether a single machine learning model could be generally applicable in various regions. We used various machine learning methods such as Support Vector Machines (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting Machines (GBM), and Deep Feedforward Network (DFN) to predict future soil moisture in Andong, Boseong, Cheolwon, Suncheon region with open source weather data. As a result, GBM model showed the lowest prediction error in every data set we used (R squared: 0.96, RMSE: 1.8). Furthermore, GBM showed the lowest variance of prediction error between regions which indicates it has the highest generalizability.

토양수분은 농업에서 필수적인 자원으로 이의 변화와 부족을 예측함으로써 관리되어왔다. 최근 현장에서의 적용 용이성과 다양한 지역에 대한 일반화 가능성이 뛰어난 통계 및 기계학습 알고리즘을 활용한 토양수분 예측 연구가 활발히 진행되고 있다. 하지만 국내에서 생성되는 데이터를 이용한 연구들은 부족한 실정이다. 이에 본 연구는 1) 국내 공공기상 데이터만으로 충분한 성능을 내는 토양수분 예측 모델을 만들 수 있는지, 2) 어떠한 기계학습 모델이 국내에서 생산되는 데이터와 토양환경에서 가장 높은 예측 성능을 보이는지, 3) 단일 기계학습 모델을 이용해 다양한 지역에 적용 가능한지를 확인해보려 한다. 본 연구에서 Support Vector Machines (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting Machines (GBM), and Deep Feedforward Network (DFN) 알고리즘과 종관기상관측 자료, 농업기상관측자료를 활용하여 안동, 보성, 철원, 순천 지역의 토양 수분을 예측하는 모델을 만들었다. 그 결과, GBM을 이용한 모델이 R2 : 0.96, Root Mean Squared Error(RMSE) : 1.8로 가장 낮은 예측 오차를 보였다. 또한 GBM을 사용한 모델이 가장 낮은 지역간 예측 오차 분산을 보여 가장 일반화하기에 적절한 모델로 확인되었다.

Keywords

References

  1. Allen, R. G., L. S. Pereira, D. Raes, and M. Smith, 1998: Crop evapotranspiration-guidelines for computing crop water requirements-FAO Irrigation and drainage paper 56. Food and Agriculture Organization of the United Nations, Rome, 1-15.
  2. Breiman, L, 2001: Random forests. Machine learning 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
  3. Cai, Y., W. Zheng, X. Zhang, L. Zhangzhong, and X. Xue, 2019: Research on soil moisture prediction model based on deep learning. PloS One 14(4).
  4. Choi, K. M., S. H. Kim, M. Son, and J. Kim, 2008: Soil moisture modelling at the mopsoil of a hillslope in the Gwangneung National Arboretum using a transfer function. Korean Journal of Agricultural and Forest Meteorology 10(2), 35-46. (in Korean with English abstract) https://doi.org/10.5532/KJAFM.2008.10.2.035
  5. Choi, S. W., S. J. Lee, J. Kim, B. L. Lee, K. R. Kim, and B. C. Choi, 2015: Agrometeorological observation environment and periodic report of korea meteorological administration: current status and suggestions. Korean Journal of Agricultural and Forest Meteorology 17(2), 144-155. (in Korean with English abstract) https://doi.org/10.5532/KJAFM.2015.17.2.144
  6. Cisty, M., F. Cyprich, and V. Soldanova, 2018: Prediction of soil moisture data by various regression techniques. Proceedings of International Multidisciplinary Scientific GeoConference, Surveying Geology and mining Ecology Management, Sofia, 383-389.
  7. Drucker, H., C. J. Burges, L. Kaufman, A. J. Smola, and V. Vapnik, 1997: Support vector regression machines. Advances in Neural Information Processing Systems 9, 155-161.
  8. Friedman, J. H., 2001: Greedy function approximation: a gradient boosting machine. Annals of Statistics 29(5), 1189-1232. https://doi.org/10.1214/aos/1013203451
  9. Geurts, P., D. Ernst, and L. Wehenkel, 2006: Extremely randomized trees. Machine Learning 63(1), 3-42. https://doi.org/10.1007/s10994-006-6226-1
  10. Gill, M. K., T. Asefa, M. W. Kemblowski, and M. McKee, 2006: Soil moisture prediction using support vector machines. Journal of the American Water Resources Association 42(4), 1033-1046. https://doi.org/10.1111/j.1752-1688.2006.tb04512.x
  11. Goodfellow, I., Y. Bengio, and A. Courville, 2016: Deep Learning. MIT press, 1-26.
  12. He, K., X. Zhang, S. Ren, and J. Sun, 2015: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE international conference on computer vision, Institute of Electrical and Electronics Engineers, Santiago, 1026-1034.
  13. https://data.kma.go.kr/data/grnd/selectAsosRltmList.do?pgmNo=72 (2019. 12. 09)
  14. https://data.kma.go.kr/data/grnd/selectAsosRltmList.do?pgmNo=36 (2019. 12. 09)
  15. Kingma, D. P., and J. Ba, 2014: Adam: a Method for Stochastic Optimization. Proceedings of Third International Conference for Learning Representations, San Diego.
  16. Kohavi, R., 1995: A study of cross-validation and bootstrap for accuracy estimation and model selection. Ijcai 14(2), 1137-1145.
  17. Laio, F., A. Porporato, L. Ridolfi, and I. Rodriguez-Iturbe, 2001: Plants in water-controlled ecosystems: active role in hydrologic processes and response to water stress: II. Probabilistic soil moisture dynamics. Advances in Water Resources 24(7), 707-723. https://doi.org/10.1016/S0309-1708(01)00005-7
  18. Natekin, A., and A. Knoll, 2013: Gradient boosting machines, a tutorial. Frontiers in Neurorobotics 7, 21pp. https://doi.org/10.3389/fnbot.2013.00021
  19. National Center for Atmospheric Research, 2004: Community Land Model version 3.0 (CLM3. 0) developer's guide. U. S. Department of Energy.
  20. National Weather Service, 1976: Catchment modeling and initial parameter estimation for the National Weather Service river forecast system. Office of Hydrology.
  21. Nielsen, D., 2016: Tree boosting with XGBoost-why does XGBoost win "every" machine learning competition? NTNU Norwegian University of Science and Technology.
  22. Oleson, K. W., Y. Dai, G. Bonan, M. Bosilovich, R. Dickinson, P. Dirmeyer, F. Hoffman, P. Houser, G. Y. Niu, P. Thornton, M. Vertenstein, Z. L. Yang, and X. Zeng, 2004: Technical description of the Community Land Model (CLM). NCAR Technical Note NCAR/TN-461+STR.
  23. Pavlenko, T, 2003: On feature selection, curse-ofdimensionality and error probability in discriminant analysis. Journal of Statistical Planning and Inference 115(2), 565-584. https://doi.org/10.1016/S0378-3758(02)00166-0
  24. Prakash, S., A. Sharma, and S. S. Sahu, 2018: Soil Moisture Prediction Using Machine Learning. Proceedings of 2018 Second International Conference on Inventive Communication and Computational Technologies, Coimbatore, Institue of Electrical and Electronics Engineers, 1-6.
  25. Shin, Y., B. P. Mohanty, and A. V. Ines, 2018: Development of non-parametric evolutionary algorithm for predicting soil moisture dynamics. Journal of Hydrology 564, 208-221. https://doi.org/10.1016/j.jhydrol.2018.07.003
  26. Song, J., D. Wang, N. Liu, L. Cheng, L. Du, and K. Zhang, 2008: Soil moisture prediction with feature selection using a neural network. Proceedings of 2008 Digital Image Computing: Techniques and Applications, Canberra, Institue of Electrical and Electronics Engineers, 130-136.
  27. Van Dam, J. C., J. Huygen, J. G. Wesseling, R. A. Feddes, P. Kabat, P. E. V. Van Walsum, P. Groenendijk, and C. A. Van Diepen, 1997: Theory of SWAP version 2.0; Simulation of water flow, solute transport and plant growth in the soil-wateratmosphere-plant environment, TD45.HM/10.97, DLO Winand Staring Centre, Wageningen.
  28. Vapnik, V., S. E. Golowich, and A. J. Smola, 1997: Support vector method for function approximation, regression estimation and signal processing. Advances in neural information processing systems 9, 281-287.