Skip to main content
Erschienen in: Environmental Earth Sciences 9/2024

01.05.2024 | Original Article

A SOM-LSTM combined model for groundwater level prediction in karst critical zone aquifers considering connectivity characteristics

verfasst von: Fei Guo, Shilong Li, Gang Zhao, Huiting Hu, Zhuo Zhang, Songshan Yue, Hong Zhang, Yi Xu

Erschienen in: Environmental Earth Sciences | Ausgabe 9/2024

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Accurate groundwater level (GWL) prediction is crucial for the management and sustainable utilization of groundwater resources. This study proposes a method, considering spatial–temporal correlation among geographic multi-feature in data, and Self-Organizing Map (SOM)-based clustering technique to identify and partition spatially connectivity among observation wells. Finally, based on the connectivity results, the observation well dataset is determined as inputs to LSTM for GWL prediction. This approach provides a new idea to enhance the accuracy of existing data-driven methods in karst critical zones characterized by significant spatial heterogeneity in GWL. Comparing with prediction models that solely consider internal data correlations, experiments are conducted in the typical highly spatially heterogeneous karst critical zone of Jinan City, Shandong Province, China. The results show a significant improvement in prediction accuracy when considering spatial connectivity between observation wells based on geographical multi-feature spatial–temporal correlation. Confirming that considering the spatial connectivity of observation wells in GWL prediction methods are more accurate, particularly in areas with significant spatial heterogeneity in karst aquifers.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Literatur
Zurück zum Zitat Banwart SA, Chorover J, Gaillardet J, Sparks D, White T, Anderson S, Ragnarsdottir KV (2013) Sustaining Earth’s critical zone basic science and interdisciplinary solutions for global challenges. The University of Sheffield, United Kingdom Banwart SA, Chorover J, Gaillardet J, Sparks D, White T, Anderson S, Ragnarsdottir KV (2013) Sustaining Earth’s critical zone basic science and interdisciplinary solutions for global challenges. The University of Sheffield, United Kingdom
Zurück zum Zitat da Silva IN, Cagnon JÂ, Saggioro NJ (2013) Recurrent neural network based approach for solving groundwater hydrology problems. Artificial neural networks-architectures and applications. InTech, p 225 da Silva IN, Cagnon JÂ, Saggioro NJ (2013) Recurrent neural network based approach for solving groundwater hydrology problems. Artificial neural networks-architectures and applications. InTech, p 225
Zurück zum Zitat Ford D, Williams PD (2007) Karst hydrogeology and geomorphology. WileyCrossRef Ford D, Williams PD (2007) Karst hydrogeology and geomorphology. WileyCrossRef
Zurück zum Zitat Hameed MM, AlOmar MK (2019) Prediction of compressive strength of high-performance concrete: hybrid artificial intelligence technique. In International Conference on Applied Computing to Support Industry: Innovation and Technology. Cham: Springer International Publishing. pp 323–335. https://doi.org/10.1007/978-3-030-38752-5_26. Hameed MM, AlOmar MK (2019) Prediction of compressive strength of high-performance concrete: hybrid artificial intelligence technique. In International Conference on Applied Computing to Support Industry: Innovation and Technology. Cham: Springer International Publishing. pp 323–335. https://​doi.​org/​10.​1007/​978-3-030-38752-5_​26.
Zurück zum Zitat Li CM (1985) Karst groundwater resources and springs protection in Jinan City. Carsol Sin 1(2):31–39 Li CM (1985) Karst groundwater resources and springs protection in Jinan City. Carsol Sin 1(2):31–39
Zurück zum Zitat Nourani V, Baghanam AH, Vousoughi VD, Alami MT (2012) Classification of groundwater level data using SOM to develop ANN-based forecasting model. Int J Soft Comput Eng 2(1):2231–2307 Nourani V, Baghanam AH, Vousoughi VD, Alami MT (2012) Classification of groundwater level data using SOM to develop ANN-based forecasting model. Int J Soft Comput Eng 2(1):2231–2307
Zurück zum Zitat Sahoo BB, Sankalp S, Kisi O (2023a) A novel smoothing-based deep learning time-series approach for daily suspended sediment load prediction. Water Resour Manage 37(11):4271–4292CrossRef Sahoo BB, Sankalp S, Kisi O (2023a) A novel smoothing-based deep learning time-series approach for daily suspended sediment load prediction. Water Resour Manage 37(11):4271–4292CrossRef
Zurück zum Zitat Sahoo BB, Panigrahi B, Nanda T, Tiwari MK, Sankalp S (2023b) Multi-step ahead urban water demand forecasting using deep learning models. SN Comput Sci 4(6):752CrossRef Sahoo BB, Panigrahi B, Nanda T, Tiwari MK, Sankalp S (2023b) Multi-step ahead urban water demand forecasting using deep learning models. SN Comput Sci 4(6):752CrossRef
Zurück zum Zitat Sundermeyer M, Schlüter R, Ney H (2012) LSTM neural networks for language modeling. In: Thirteenth annual conference of the international speech communication association Sundermeyer M, Schlüter R, Ney H (2012) LSTM neural networks for language modeling. In: Thirteenth annual conference of the international speech communication association
Zurück zum Zitat Swagatika S, Paul JC, Sahoo BB, Gupta SK, Singh PK (2024) Improving the forecasting accuracy of monthly runoff time series of the Brahmani River in India using a hybrid deep learning model. J Water Clim Chang 15(1):139–156CrossRef Swagatika S, Paul JC, Sahoo BB, Gupta SK, Singh PK (2024) Improving the forecasting accuracy of monthly runoff time series of the Brahmani River in India using a hybrid deep learning model. J Water Clim Chang 15(1):139–156CrossRef
Zurück zum Zitat Wunsch A, Liesch T, Broda S (2021) Groundwater level forecasting with artificial neural networks: a comparison of long short-term memory (LSTM), convolutional neural networks (CNNs), and non-linear autoregressive networks with exogenous input (NARX). Hydrol Earth Syst Sci 25(3):1671–1687. https://doi.org/10.5194/hess-25-1671-2021CrossRef Wunsch A, Liesch T, Broda S (2021) Groundwater level forecasting with artificial neural networks: a comparison of long short-term memory (LSTM), convolutional neural networks (CNNs), and non-linear autoregressive networks with exogenous input (NARX). Hydrol Earth Syst Sci 25(3):1671–1687. https://​doi.​org/​10.​5194/​hess-25-1671-2021CrossRef
Metadaten
Titel
A SOM-LSTM combined model for groundwater level prediction in karst critical zone aquifers considering connectivity characteristics
verfasst von
Fei Guo
Shilong Li
Gang Zhao
Huiting Hu
Zhuo Zhang
Songshan Yue
Hong Zhang
Yi Xu
Publikationsdatum
01.05.2024
Verlag
Springer Berlin Heidelberg
Erschienen in
Environmental Earth Sciences / Ausgabe 9/2024
Print ISSN: 1866-6280
Elektronische ISSN: 1866-6299
DOI
https://doi.org/10.1007/s12665-024-11567-5

Weitere Artikel der Ausgabe 9/2024

Environmental Earth Sciences 9/2024 Zur Ausgabe