Abstract
Evapotranspiration is one of the most critical features in hydrology. In order to address the prediction of evapotranspiration accurately and scientifically, this study proposes a novel deep learning-based evapotranspiration prediction model, the CNN-BiLSTM-Attention model, using the climatically complex Mount Tai region in China as a case study. The model integrates the feature extraction capabilities of Convolutional Neural Networks (CNN), the temporal dependency capturing of Bidirectional Long Short-Term Memory Networks (BiLSTM), and the feature weighting abilities of the Attention mechanism. In order to enhance prediction accuracy with fewer climate parameters, various input parameter combinations are explored and compared with other classical models in this study. The model's performance is assessed across daily, weekly, and monthly time increments, using evaluation metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2). This study holds significant implications for mountain hydrological cycles, as accurate evapotranspiration prediction aids in more informed decision-making for agricultural production, water resource management, and climate change research.
Similar content being viewed by others
Availability of data and material
All data included in this study are available upon request by contact with the corresponding author.
References
Abed M, Imteaz MA, Ahmed AN, Huang YF (2022) Modelling monthly pan evapotranspiration utilising Random Forest and deep learning algorithms. Sci Rep-Uk 12(1):13132. https://doi.org/10.1038/s41598-022-17263-3
Allawi MF, El-Shafie A (2016) Utilizing RBF-NN and ANFIS methods for multi-lead ahead prediction model of evapotranspiration from reservoir. Water Resour Manag 30:4773–4788. https://doi.org/10.1007/s11269-016-1452-1
Allawi MF, Binti Othman F, Afan HA, Ahmed AN, Hossain MS, Fai CM, El-Shafie A (2019) Reservoir evapotranspiration prediction modeling based on artificial intelligence methods. Water-Sui 11(6):1226. https://doi.org/10.3390/w11061226
Allawi MF, Ahmed ML, Aidan IA, Deo RC, El-Shafie A (2021) Developing reservoir evapotranspiration predictive model for successful dam management. Stoch Env Res Risk A 35:499–514
Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Farhan L (2021) Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J Big Data 8:1–74. https://doi.org/10.1186/s40537-021-00444-8
Arunkumar R, Jothiprakash V (2013) Reservoir evapotranspiration prediction using data-driven techniques. J Hydrol Eng 18(1):40–49
Atiyeh B, Omid BH, Somayeh S, Loáiciga HA (2020) Comparison of methods for estimating loss from water storage by evapotranspiration and impacts on reservoir management. Water Environ J 35(1):218–228. https://doi.org/10.1111/wej.12620
Chen QW, Liu MJ, Li JL, Li G, Otsuki K, Yamanaka N, Sheng D (2022) Characterization of dominant factors on evapotranspiration with seasonal soil water changes in two adjacent forests in the semiarid Loess Plateau. J Hydrol 613:128427. https://doi.org/10.1016/j.jhydrol.2022.128427
Chen JX, Zhang JH, Peng JB, Zou L, Fan YJ, Yang FR, Hu ZW (2023) Alp-valley and elevation effects on the reference evapotranspiration and the dominant climate controls in Red River Basin, China: Insights from geographical differentiation. J Hydrol 39:100966. https://doi.org/10.1016/j.uclim.2021.100966
Danandeh Mehr A, Rikhtehgar Ghiasi A, Yaseen ZM, Sorman AU, Abualigah L (2022) A novel intelligent deep learning predictive model for meteorological drought forecasting. J Amb Intel Hum Comp 14(8):10441–10455. https://doi.org/10.1007/s12652-022-03701-7
Deng H, Chen W, Huang G (2022) Deep insight into daily runoff forecasting based on a CNN-LSTM model. Nat Hazards 113(3):1675–1696. https://doi.org/10.1007/s11069-022-05363-2
Gelete G (2023) Application of hybrid machine learning-based ensemble techniques for rainfall-runoff modeling. Earth Sci Inform. https://doi.org/10.1007/s12145-023-01041-4
Ghanbarian B, Pachepsky Y (2022) Machine learning in vadose zone hydrology: A flashback. Vadose Zone J 21(4):e20212. https://doi.org/10.1002/vzj2.20212
Guo MH, Xu TX, Liu JJ, Liu ZN, Jiang PT, Mu TJ, ... Hu SM (2022) Attention mechanisms in computer vision: A survey. Comp Visual Media 8(3):331–368. https://doi.org/10.1007/s41095-022-0271-y
Haq MA, Khan MAR (2022) Dnnbot: deep neural network-based botnet detection and classification. Comput Mater Continua 71(1):1729–1750. https://doi.org/10.32604/cmc.2022.020938
Haq MA et al (2022a) Cnn based automated weed detection system using uav imagery. Comput Syst Sci Eng 42(2):837–849. https://doi.org/10.32604/csse.2022.023016
Haq MA et al (2022b) Smotednn: a novel model for air pollution forecasting and aqi classification. Comput Mater Continua 71(1):1403–1425. https://doi.org/10.32604/cmc.2022.021968
Haq MA et al (2022c) Cdlstm: a novel model for climate change forecasting. Comput Mater Continua 71(2):2363–2381. https://doi.org/10.32604/cmc.2022.023059
Haq MA, Jilani AK, Prabu P (2022d) Deep learning based modeling of groundwater storage change. Comput Mater Continua 70(3):4599–4617. https://doi.org/10.32604/cmc.2022.020495
Haq MA, Ahmed A, Khan I et al (2022e) Analysis of environmental factors using AI and ML methods. Sci Rep 12:13267. https://doi.org/10.1038/s41598-022-16665-7
Haq MA, Khan MAR, AL-Harbi T (2022f) Development of pccnn-based network intrusion detection system for edge computing. Comput Mater Continua 71(1):1769–1788. https://doi.org/10.32604/cmc.2022.018708
Heydari M, Ghadim HB, Rashidi M, Noori M (2020) Application of holt-winters time series models for predicting climatic parameters (case study: Robat Garah-Bil Station, Iran). Pol J Environ Stud 29(1):617–627
Khorrami B, Gorjifard S, Ali S et al (2023) Local-scale monitoring of evapotranspiration based on downscaled GRACE observations and remotely sensed data: An application of terrestrial water balance approach. Earth Sci Inform 16:1947. https://doi.org/10.1007/s12145-023-00989-7
Lee WK, Tuan Resdi TA (2016) Simultaneous hydrological prediction at multiple gauging stations using the NARX network for Kemaman catchment, Terengganu, Malaysia. Hydrolog Sci J 61(16):2930–2945. https://doi.org/10.1080/02626667.2016.1174333
Li Y, Wang W, Wang G, Tan Q (2022) Actual evapotranspiration estimation over the Tuojiang River Basin based on a hybrid CNN-RF model. J Hydrol 610:127788. https://doi.org/10.1016/j.jhydrol.2022.127788
Li B, Li R, Sun T, Gong A, Tian F, Khan MYA, Ni G (2023) Improving LSTM hydrological modeling with spatiotemporal deep learning and multi-task learning: A case study of three mountainous areas on the Tibetan Plateau. J Hydrol 620:129401. https://doi.org/10.1016/j.jhydrol.2023.129401
Marçais J, Dreuzy JR (2017) Prospective interest of deep learning for hydrological inference. Groundwater 55(5):688–692. https://doi.org/10.1111/gwat.12557
McColl KA (2020) Practical and theoretical benefits of an alternative to the Penman-Monteith evapotranspiration equation. Water Resour Res 56(6):e2020WR027106. https://doi.org/10.1029/2020WR027106
Mohammadi B (2022) Application of machine learning and remote sensing in hydrology. Sustainability-Basel 14(13):7586. https://doi.org/10.3390/su141375861
Popović P, Gocić M, Petković K et al (2023) Neural network based system in evapotranspiration time series prediction. Earth Sci Inform 16:919–928. https://doi.org/10.1007/s12145-023-00935-7
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Ieee T Pattern Anal 39(6):1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Shimi M, Najjarchi M, Khalili K, Hezavei E, Mirhoseyni SM (2020) Investigation of the accuracy of linear and nonlinear time series models in modeling and forecasting of pan evapotranspiration in IRAN. Arba J Geosci 13:1–16. https://doi.org/10.1007/s12517-019-5031-7
Tan YX, Ng JL, Huang YF (2023) Spatiotemporal variability assessment and accuracy evaluation of Standardized Precipitation Index and Standardized Precipitation Evapotranspiration Index in Malaysia. Earth Sci Inform. https://doi.org/10.1007/s12145-022-00921-5
Vicente-Serrano SM, Beguería S, Lopez-Moreno JI (2010) A multiscalar drought index sensitive to global warming: the standardized precipitation evapotranspiration index. J Climate 23(7):1696–1718. https://doi.org/10.1175/2009JCLI2909.1
Wang WC, Chau KW, Xu DM, Chen XY (2015) Improving forecasting accuracy of annual runoff time series using ARIMA based on EEMD decomposition. Water Resources Manag 29:2655–2675
Wu Z, Cui N, Gong D, Zhu FY, Xing LW, Zhu B, Chen X, Wen SL, Liu QS (2023) Simulation of daily maize evapotranspiration at different growth stages using four machine learning models in semi-humid regions of northwest China. J Hydrol 617:128947. https://doi.org/10.1016/j.jhydrol.2022.128947
Yao J, Wang P, Wang G, Shrestha S, Xue B, Sun W (2020) Establishing a time series trend structure model to mine potential hydrological information from hydrometeorological time series data. Sci Total Environ 698:134227. https://doi.org/10.1016/j.scitotenv.2019.134227
Yu Y, Si X, Hu C, Zhang J (2019) A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput 31(7):1235–1270. https://doi.org/10.1162/neco_a_01199
Zhu G, Qin D, Tong H, Liu Y, Li J, Chen D, Wang K, Hu P (2016) Variation of thornthwaite moisture index in Hengduan Mountains, China. Chinese Geogr Sci 26:687–702. https://doi.org/10.1007/s11769-016-0820-3
Funding
This study was funded by National Natural Science Foundation of China (42002282).
Author information
Authors and Affiliations
Contributions
Shichao Wang designed and conducted the experiments, analyzed the results, and wrote the initial draft of the paper. Xiaoge Yu assisted with the revision of the initial draft and participated in data analysis. Yan Li provided the data and also participated in data analysis. Shujun Wang conducted the final review and revision of the paper. Can Meng contributed to editing and visualization.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Conflicts of interest
The authors have no conflicts of interest to declare.
Ethical declarations
In the course of this study, we have adhered to the highest ethical standards. We affirm that the research does not involve any breach of data privacy. The climate data used in this study was either provided by the corresponding author's affiliated institution or sourced from publicly available datasets, and it does not contain any personal or confidential information. Furthermore, we have taken appropriate measures to ensure that the training data used in our analysis is unbiased and representative of the Mount Tai region's climate patterns.
Additional information
Communicated by: Hassan Babaie
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, S., Yu, X., Li, Y. et al. Application of a hybrid deep learning approach with attention mechanism for evapotranspiration prediction: a case study from the Mount Tai region, China. Earth Sci Inform 16, 3469–3487 (2023). https://doi.org/10.1007/s12145-023-01103-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-023-01103-7