All Issue

2025 Vol.34, Issue 1 Preview Page

Original Articles

Machine Learning-Based Weather Factor Prediction for Estimating Reference Crop Evapotranspiration Using the Penman-Monteith Equation

Penman-Monteith 방정식을 사용하여 기준 작물 증발산량을 추정하기 위한 머신러닝 기반 기상인자 예측

Seung Un Ha1
,
Yong Jae Lee1
,
Kwang Ya Lee5
,
Young Kuk Kim34
,
Jong Seok Park23*
하 승운1
,
이 용재1
,
이 광야5
,
김 영국34
,
박 종석23*
1Graduate Student, Department of Bio-AI Convergence, Chungnam National University, Daejeon 34134, Korea
2Professor, Department of Horticultural Science, Chungnam National University Daejeon 34134, Korea
3Professor, Department of Bio-AI Convergence, Chungnam National University, Daejeon 34134, Korea
4Professor, Department of Computer Convergence, Chungnam National University, Daejeon 34134, Korea
5Research Professor, Institute of Agricultural Science, Chungnam National University, Daejeon 34134, Korea
1충남대학교 바이오AI융합학과 대학원생
2충남대학교 농업생명과학대학 원예학과 교수
3충남대학교 바이오AI융합학과 교수
4충남대학교 컴퓨터융합학부 교수
5충남대학교 농업과학연구소 연구교수
*Corresponding Author
31 January 2025. pp. 69-80
PDF XML Citation
Abstract

Crop evapotranspiration can be calculated by multiplying potential evapotranspiration by the crop coefficient, making it widely used method in water resource management. The Penman-Monteith equation (FAO 56-PM), published in Food and Agriculture Organization of the United Nations (FAO) Irrigation and Drainage Paper No. 56, is the standard method for estimating potential evapotranspiration, requiring six meteorological inputs: mean temperature, maximum temperature, minimum temperature, relative humidity, wind speed, and solar radiation. However, weather sensors installed near farmland often come with high installation and maintenance costs, leading to data reliability issues, such as missing values or outliers, which complicate accurate evapotranspiration calculations. This study investigates whether crop evapotranspiration can be estimated without weather sensors by using nearby meteorological data to predict the six required weather variables. We utilized 22 meteorological variables available through the meteorological agency’s API as input data. After training nine regression models, we selected the top three based on performance and applied hyperparameter tuning to identify the optimal model. The Extreme Gradient Boosting Regression (XGBR) model showed the best performance, with R-squared values of 0.98, 0.99, 0.99, 0.91, 0.72, and 0.86 for mean temperature, maximum temperature, minimum temperature, relative humidity, wind speed, and solar radiation, respectively. These results suggest that the XGBR model can accurately predict the necessary inputs for crop evapotranspiration models using meteorological data, eliminating the need for expensive weather sensors. This approach could be particularly beneficial in regions where sensor installation and maintenance are challenging, enabling the use of standard evapotranspiration models without direct sensor data.

Keywords
machine learning
penman-monteith equation (FAO 56-PM)
reference crop evapotranspiration
weather factor

작물 증발산량은 잠재 증발산량에서 작물계수를 곱하여 작물의 요수량을 산출할 수 있어 수자원 관리에 널리 사용되는　방법이다. 특히 유엔식량농업기구(FAO)가 관개 및 배수 논문 NO.56에서 발표한 Penman-Monteith　방정식(FAO 56-PM)은 잠재 증발산량을 추정하는 표준방법으로, 평균온도, 최대온도, 최소온도, 상대습도, 풍속 및 일사량의 6가지 기상 데이터가 필요하다. 그러나　농경지 인근에 설치된 기상센서는 설치 및 유지보수 비용이 높아 결측, 이상치와 같은 데이터 신뢰성 문제를 야기하여 정확한 증발산량 계산을 복잡하게 만든다. 본 연구에서는 인근 기상청의 데이터를 사용하여 필요한 6가지 기상 변수를 예측함으로써 기상 센서 없이 작물 증발산량을 추정할 수 있는지 조사하였다. 우리는 기상청의 API를 통해 수집할 수 있는 22개의 기상 변수를 입력 데이터로 활용했다. 9개의 회귀 모델을 학습한 후 성능에 따라 상위 3개를 선택하고 하이퍼파라미터 튜닝을 적용하여 최적의 모델을 식별했다. 가장 좋은 성능을 보인 모델은 Extreme Gradient Boosting Regression(XGBR)이었으며 평균온도, 최대온도, 최소온도, 상대습도, 풍속 및 일사량에서 결정계수(R2)가 각 0.98, 0.99, 0.99, 0.91, 0.72, 0.86로 높은 결과를 얻을 수 있었다. 이러한 결과는 XGBR 모델이 작물 기상 데이터를 사용하여 작물 증발산 모델에 필요한 입력 값을 정확하게 예측할 수 있어 값비싼 기상 센서가 필요 없음을 시사한다. 이 접근 방식은 센서 설치 및 유지보수가 어려운 지역에서 특히 유용할 수 있으며, 직접적인 센서 데이터 없이도 표준 증발산 모델의 사용을 가능하게 한다.

키워드
기상인자
기준 작물 증발산량
머신러닝
Penman-Monteith 방정식(FAO 56-PM)
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. FAO Rome 300:D05109.

2

Allen R.G., L.S. Pereira, T.A. Howell, and M.E. Jensen 2011, Evapotranspiration information reporting: II. Recommended documentation. Agric Water Manag 98:921-929. doi:10.1016/j.agwat.2010.12.016

10.1016/j.agwat.2010.12.016
3

Allen R.G., W.O. Pruitt, J.L. Wright, T.A. Howell, F. Ventura, R. Snyder, D. Itenfisu, P. Steduto, J. Berengena, J.B. Yrisarry, M. Smith, L.S. Pereira, D. Raes, A. Perrier, I. Alves, I. Walter, R. Elliott 2006, A recommendation on standardized surface resistance for hourly calculation of reference ETo by the FAO56 Penman-Monteith method. Agric Water Manag 18:1-22. doi:10.1016/j.agwat.2005.03.007

10.1016/j.agwat.2005.03.007
4

Breiman L. 2001, Random forests. ML 45:5-32.

10.1023/A:1010933404324
5

Chen T., and C. Guestrin 2016, Xgboost: A scalable tree boosting system. Proc ACM SIGKDD Int Conf Knowl Discov Data Min 785-794. doi:10.1145/2939672.2939785

10.1145/2939672.2939785
6

Chipanshi A., Y. Zhang, L. Kouadio, N. Newlands, A. Davidson, H. Hill, R. Warren, B. Qian, B. Daneshfar, F. Bedard, G. Reichert 2015, Evaluation of the Integrated Canadian Crop Yield Forecaster (ICCYF) model for in-season prediction of crop yield across the Canadian agricultural landscape. Agric For Meteorol 206:137-150. doi: 10.1016/j.agrformet.2015.03.007

10.1016/j.agrformet.2015.03.007
7

Cortes C. 1995, Support-Vector Networks. ML 20:273-297.

10.1007/BF00994018
8

Dai X., H. Shi, Y. Li, Z. Ouyang, and Z. Huo 2009, Artificial neural network models for estimating regional reference evapotranspiration based on climate factors. Hydrol Processes 23:442-450. doi:10.1002/hyp.7153

10.1002/hyp.7153
9

Djaman K., K. Lombard, K. Koudahe, S. Allen, and M. O'Neill 2018, Variability of the ratio of alfalfa to grass reference evapotranspiration under semiarid climate. Irrig Drain Syst Eng 7:2. doi:10.4172/2168-9768.1000204

10.4172/2168-9768.1000204
10

Drexler J.Z., R.L. Snyder, D. Spano, and U, K.T. Paw 2004, A review of models and micrometeorological methods used to estimate wetland evapotranspiration. Hydrol Processes 18:2071-2101. doi:10.1002/hyp.1462

10.1002/hyp.1462
11

Freund Y., and R.E. Schapire 1997, A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55:119-139. doi:10.1006/jcss.1997.1504

10.1006/jcss.1997.1504
12

Friedman J.H. 2001, Greedy function approximation: a gradient boosting machine. Ann Stat. pp 1189-1232.

10.1214/aos/1013203451
13

Ge J., L. Zhao, Z. Yu, H. Liu, L. Zhang, X. Gong, and H. Sun 2022, Prediction of greenhouse tomato crop evapotranspiration using XGBoost machine learning model. Plant 11:1923. doi:10.3390/plants11151923

10.3390/plants1115192335893626PMC9330426
14

George B.A., B.R.S. Reddy, N.S. Raghuwanshi, and W.W. Wallender 2002, Decision support system for estimating reference evapotranspiration. J Irrig Drain Eng 128:1-10. doi:10.1061/(ASCE)0733-9437(2002)128:1(1)

10.1061/(ASCE)0733-9437(2002)128:1(1)
15

Hara P., M. Piekutowska, and G. Niedbała 2021, Selection of independent variables for crop yield prediction using artificial neural network models with remote sensing data. Land 10:609. doi:10.3390/land10060609

10.3390/land10060609
16

Hastie T., and R. Tibshirani 1995, Discriminant adaptive nearest neighbor classification and regression. Advances in neural information processing systems 8.

17

Itenfisu D., R.L. Elliott, R.G. Allen, and I.A. Walter 2003, Comparison of reference evapotranspiration calculations as part of the ASCE standardization effort. J Irrig Drain Eng, 129:440-448. doi:10.1061/(ASCE)0733-9437(2003)129:6(440)

10.1061/(ASCE)0733-9437(2003)129:6(440)
18

Kim M., Y. Choi, S. O'Shaughnessy, P. Colaizzi, Y. Kim, J. Jeon, and S. Lee 2019, Estimation of Reference Crop Evapotranspiration Using Backpropagation Neural Network Model. J Korean Soc Agric Eng 61:111-121. doi:10.5389/KSAE.2019.61.6.111

19

Loh, W.Y. 2011, Classification and regression trees. Wiley Interdiscip Rev Data Min Knowl. Discov 1:14-23. doi:10.1002/widm.8

10.1002/widm.8
20

Lu Y., D. Ma, X. Chen, and J. Zhang 2018, A simple method for estimating field crop evapotranspiration from pot experiments. Water 10:1823. doi:10.3390/w10121823

10.3390/w10121823
21

Montgomery, D. C., E. A. Peck, and G. G. Vining 2021, Introduction to linear regression analysis. John Wiley and Sons.

22

Parisi S., L. Mariani, G. Cola, and T. Maggiore 2009, Mini-lysimeters evapotranspiration measurements on suburban environment. Ital J Agrometeorol 3:13-16.

23

Rumelhart D.E., G.E. Hinton, and R.J Williams. 1986, Learning representations by back-propagating errors. Nature 323: 533-536.

10.1038/323533a0
24

Smith M., A. Segeren, L. Santos Pereira, A. Perrier, and R. Allen 1990, Report on the expert consultation on procedures for revision of FAO guidelines for prediction of crop water requirements.

25

Suntaranont B., S. Aramkul, M. Kaewmoracharoen, and P. Champrasert 2020, Water irrigation decision support system for practical weir adjustment using artificial intelligence and machine learning techniques. Sustainability 12:1763. doi:10.3390/su12051763

10.3390/su12051763
26

Vyas K.N., and R. Subbaiah 2016, Application of artificial neural network approach for estimating reference evapotranspiration. Curr World Environ 11:637-647. doi:10.12944/CWE

10.12944/CWE
Information
  • Publisher :The Korean Society for Bio-Environment Control
  • Publisher(Ko) :(사)한국생물환경조절학회
  • Journal Title :Journal of Bio-Environment Control
  • Journal Title(Ko) :생물환경조절학회지
  • Volume : 34
  • No :1
  • Pages :69-80
  • Received Date : 2024-11-04
  • Revised Date : 2025-01-10
  • Accepted Date : 2025-01-22
  • DOI :https://doi.org/10.12791/KSBEC.2025.34.1.069
Journal Informaiton Journal of Bio-Environment Control Journal of Bio-Environment Control
Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close