Skip to main content

LSTM integrated with Boruta-random forest optimiser for soil moisture estimation under RCP4.5 and RCP8.5 global warming scenarios

Abstract

Future soil moisture (SM) estimation is a practically useful task for eco-hydrologists, agriculturists, and stakeholders in environment health monitoring to generate comprehensive understanding of hydro-physical and soil dynamic system. This paper demonstrates the capability of a hybridised long short-term memory (LSTM) predictive framework to emulate SM under global warming scenarios. The proposed model is developed by integrating Boruta-random forest (BRF) feature selection and capturing significant antecedent memory of SM behaviour were applied to estimate the future SM using Coupled Model Intercomparison Phase-5 (CMIP5) repository. The BRF is adapted to extract pertinent features in hydro-meteorological variables intrinsically related to SM, and therefore, is used to construct a hybridised deep learning (i.e., BRF-LSTM) model. To establish the viability of deep learning model for SM estimation until 2100, five stations closely matched to the global climate model grid are selected in Australia's Murray Darling Basin. The performance skill of BRF-LSTM model is compared against standalone models (i.e., LSTM, SVR, and MARS). The results showed that the hybrid deep learning model (i.e., BRF-LSTM) with a feature selection capability could significantly outperform the standalone models for both warming simulations. The proposed hybrid model also demonstrated superiority in SM estimation with over 95% of all predictive errors lying below 0.02 mm, and low relative root means square error (≈ 1.06% for RCP4.5 and ≈ 1.888% for RCP8.5) to outperform all the benchmark models. This study demonstrates the capability of LSTM algorithm coupled with BRF feature selection to simulate future soil moisture under climate change, and so, can be successfully implemented in hydrology, agriculture, soil use management and environmental management.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Abbreviations

ADF:

Augmented Dickey–Fuller

ANN:

Artificial neural network

AR5:

Fifth assessment report

BRF:

Boruta-random forest hybridizer algorithm

BRF-LSTM:

Two-stage hybrid model integrating the Boruta feature selection algorithm and significant lagged memory with LSTM

BRF-SVR:

Two-stage hybrid model integrating the Boruta feature selection algorithm and significant lagged memory with SVR

BRF-MARS:

Two-stage hybrid model integrating the Boruta feature selection algorithm and significant lagged memory with MARS

CEDA:

Centre for Environmental Data Analysis

CMIP5:

Coupled Model Inter-comparison Project Phase 5

CNN:

Convolutional neural network

CSIRO:

Commonwealth Scientific and Industrial Research Organization

DL:

Deep learning

ELM:

Extreme learning machine

EMD:

Empirical mode decomposition

FFNN:

Feed forward neural networks

GCM:

Global Climate Models

IPCC:

Intergovernmental Panel on the Climate Change

KGE:

Kling–Gupta efficiency

LM:

Legates–McCabe's index

LSTM:

Long-short term memory

MAE:

Mean absolute error

MAPE:

Mean absolute percentage error

MDB:

Murray–Darling basin

MEMD:

Multivariate empirical mode decomposition

MLP:

Multi-layer perceptron

MSE:

Mean squared error

NSE:

Nash–Sutcliffe efficiency

PACF:

Partial autocorrelation function

QLD:

Queensland

r:

Correlation coefficient

RMSE:

Root-mean-square-error

RNN:

Recurrent neural network

RRMSE:

Relative root-mean-square error

SD:

Standard deviation

SM:

Soil moisture

SVR:

Support vector regression

WI:

Willmott's Index of Agreement

References

  1. Abadi M et al (2016) Tensorflow: a system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16), pp 265–283

  2. Adamowski J, Fung Chan H, Prasher SO, Ozga-Zielinski B, Sliusarieva A (2012) Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada. Water Resour Res. https://doi.org/10.1029/2010wr009945

    Article  Google Scholar 

  3. Adeyemi O, Grove I, Peets S, Domun Y, Norton T (2018) Dynamic neural network modelling of soil moisture content for predictive irrigation scheduling. Sensors (Basel). https://doi.org/10.3390/s18103408

    Article  Google Scholar 

  4. Ahmed AAM (2017) Prediction of dissolved oxygen in Surma River by biochemical oxygen demand and chemical oxygen demand using the artificial neural networks (ANNs). J King Saud Univ Eng Sci 29(2):151–158. https://doi.org/10.1016/j.jksues.2014.05.001

    Article  Google Scholar 

  5. Ahmed AAM, Shah SMA (2017a) Application of adaptive neuro-fuzzy inference system (ANFIS) to estimate the biochemical oxygen demand (BOD) of Surma River. J King Saud Univ Eng Sci 29(3):237–243. https://doi.org/10.1016/j.jksues.2015.02.001

    Article  Google Scholar 

  6. Ahmed AM, Shah SMA (2017b) Application of artificial neural networks to predict peak flow of Surma River in Sylhet Zone of Bangladesh. Int J Water 11(4):363–375

    Article  Google Scholar 

  7. Akbari Asanjan A et al (2018) Short-term precipitation forecast based on the PERSIANN system and LSTM recurrent neural networks. J Geophys Res Atmos. https://doi.org/10.1029/2018jd028375

    Article  Google Scholar 

  8. Ali M, Deo RC, Downs NJ, Maraseni T (2018) Multi-stage hybridized online sequential extreme learning machine integrated with Markov Chain Monte Carlo copula-Bat algorithm for rainfall forecasting. Atmos Res 213:450–464

    Article  Google Scholar 

  9. Ali M, Deo RC, Maraseni T, Downs NJ (2019) Improving SPI-derived drought forecasts incorporating synoptic-scale climate indices in multi-phase multivariate empirical mode decomposition model hybridized with simulated annealing and kernel ridge regression algorithms. J Hydrol 576:164–184. https://doi.org/10.1016/j.jhydrol.2019.06.032

    Article  Google Scholar 

  10. Ali M, Deo RC, Xiang Y, Li Y, Yaseen ZM (2020a) Forecasting long-term precipitation for water resource management: a new multi-step data-intelligent modelling approach. Hydrol Sci J 1–16

  11. Ali M, Prasad R, Xiang Y, Yaseen ZM (2020b) Complete ensemble empirical mode decomposition hybridized with random forest and kernel ridge regression model for monthly rainfall forecasts. J Hydrol 584:124647

    Article  Google Scholar 

  12. Alizadeh MJ, Kavianpour MR, Kisi O, Nourani V (2017) A new approach for simulating and forecasting the rainfall-runoff process within the next two months. J Hydrol 548:588–597. https://doi.org/10.1016/j.jhydrol.2017.03.032

    Article  Google Scholar 

  13. Al-Musaylh MS, Deo RC, Adamowski JF, Li Y (2019) Short-term electricity demand forecasting using machine learning methods enriched with ground-based climate and ECMWF Reanalysis atmospheric predictors in southeast Queensland. Austr Renew Sustain Energy Rev. https://doi.org/10.1016/j.rser.2019.109293

    Article  Google Scholar 

  14. Alvisi S, Mascellani G, Franchini M, Bardossy A (2006) Water level forecasting through fuzzy logic and artificial neural network approaches. Hydrol Earth Syst Sci Discuss 10(1):1–17

    Article  Google Scholar 

  15. Arto I et al (2019) The socioeconomic future of deltas in a changing environment. Sci Total Environ 648:1284–1296. https://doi.org/10.1016/j.scitotenv.2018.08.139

    CAS  Article  Google Scholar 

  16. Australian Bureau of Statistics (2010) Household use of information technology. Australia

  17. Bouktif S, Fiaz A, Ouni A, Serhani M (2018) Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: comparison with machine learning approaches. Energies. https://doi.org/10.3390/en11071636

    Article  Google Scholar 

  18. Breiman L (2001) Random forests. Mach Learn 45:5–32

    Article  Google Scholar 

  19. Britz D (2015) Recurrent neural network tutorial, part 4 implementing a GRU/LSTM RNN with python and theano. http://www.wildml.com/2015/10/recurrent-neural-network-tutorial-part-4-implementing-a-grulstm-rnn-with-python-and-theano

  20. Brownlee J (2016) Deep learning with Python: develop deep learning models on Theano and TensorFlow using Keras. Machine Learning Mastery

  21. Cai Y, Zheng W, Zhang X, Zhangzhong L, Xue X (2019) Research on soil moisture prediction model based on deep learning. PLoS ONE 14(4):e0214508. https://doi.org/10.1371/journal.pone.0214508

    CAS  Article  Google Scholar 

  22. Chai T, Draxler RR (2014) Root mean square error (RMSE) or mean absolute error (MAE)?—Arguments against avoiding RMSE in the literature. Geosci Model Dev 7(3):1247–1250. https://doi.org/10.5194/gmd-7-1247-2014

    Article  Google Scholar 

  23. Chen L, Ye L, Singh V, Zhou J, Guo S (2014) Determination of input for artificial neural networks for flood forecasting using the copula entropy method. J Hydrol Eng. https://doi.org/10.1061/(asce)he.1943-5584.0000932

    Article  Google Scholar 

  24. Chiew FH, Piechota TC, Dracup JA, McMahon TA (1998) El Nino/Southern Oscillation and Australian rainfall, streamflow and drought: Links and potential for forecasting. J Hydrol 204(1–4):138–149

    Article  Google Scholar 

  25. Chollet F (2016) Keras

  26. Christ M, Kempa-Liehr AW, Feindt M (2016) Distributed and parallel time series feature extraction for industrial big data applications. arXiv preprint arXiv:1610.07717

  27. Christensen JH, Boberg F, Christensen OB, Lucas-Picher P (2008) On the need for bias correction of regional climate change projections of temperature and precipitation. Geophys Res Lett 35(20):L20709

    Article  Google Scholar 

  28. Deo RC, Şahin M (2015) Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia. Atmos Res 153:512–525

    Article  Google Scholar 

  29. Deo RC, Sahin M (2016) An extreme learning machine model for the simulation of monthly mean streamflow water level in eastern Queensland. Environ Monit Assess 188(2):90. https://doi.org/10.1007/s10661-016-5094-9

    Article  Google Scholar 

  30. Deo RC, Kisi O, Singh VP (2017) Drought forecasting in eastern Australia using multivariate adaptive regression spline, least square support vector machine and M5Tree model. Atmos Res 184:149–175

    Article  Google Scholar 

  31. Diebold FX, Mariano RS (2002) Comparing predictive accuracy. J Bus Econ Stat 20(1):134–144

    Article  Google Scholar 

  32. Elsafi SH (2014) Artificial Neural Networks (ANNs) for flood forecasting at Dongola Station in the River Nile, Sudan. Alexandria Eng J 53(3):655–662. https://doi.org/10.1016/j.aej.2014.06.010

    Article  Google Scholar 

  33. Gedefaw M, Hao W, Denghua Y, Girma A (2018) Variable selection methods for water demand forecasting in Ethiopia: Case study Gondar town. Cogent Environ Sci 4(1):1537067. https://doi.org/10.1080/23311843.2018.1537067

    Article  Google Scholar 

  34. Ghimire D, Raj M (2019) Deep learning neural networks trained with MODIS satellite-derived predictors for long-term global solar radiation prediction. Energies. https://doi.org/10.3390/en12122407

    Article  Google Scholar 

  35. Ghimire S, Deo RC, Raj N, Mi J (2019) Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms. Appl Energy. https://doi.org/10.1016/j.apenergy.2019.113541

    Article  Google Scholar 

  36. Ghimire S, Deo RC, Downs NJ, Raj N (2019) Global solar radiation prediction by ANN integrated with European Centre for medium range weather forecast fields in solar rich cities of Queensland Australia. J Cleaner Prod 216:288–310. https://doi.org/10.1016/j.jclepro.2019.01.158

    Article  Google Scholar 

  37. Gill MK, Asefa T, Kemblowski MW, McKee M (2006) Soil moisture prediction using support vector machines 1. JAWRA J Am Water Resour Assoc 42(4):1033–1046

    Article  Google Scholar 

  38. Gong G et al (2019) Research on short-term load prediction based on Seq2seq model. Energies. https://doi.org/10.3390/en12163199

    Article  Google Scholar 

  39. Graves A (2012) Supervised sequence labelling with recurrent neural networks. http://books.google.com/books

  40. Graves A (2013) Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850.

  41. Gupta HV, Kling H, Yilmaz KK, Martinez GF (2009) Decomposition of the mean squared error and NSE performance criteria: implications for improving hydrological modelling. J Hydrol 377(1–2):80–91

    Article  Google Scholar 

  42. Hu C et al (2018) Deep learning with a long short-term memory networks approach for rainfall-runoff simulation. Water. https://doi.org/10.3390/w10111543

    Article  Google Scholar 

  43. Huang C, Li L, Ren S, Zhou Z (2010) Research of soil moisture content forecast model based on genetic algorithm BP neural network. In: International conference on computer and computing technologies in agriculture. Springer, Berlin, pp 309–316

  44. Hur J-H, Ihm S-Y, Park Y-H (2017) A variable impacts measurement in random forest for mobile cloud computing. In: Wireless communications and mobile computing

  45. IPCC-TGICA (2007) General Guidelines on the Use of Scenario Data for Climate Impact and Adaptation Assessment. Version 2. Prepared by T.R. Carter on behalf of the Intergovernmental Panel on Climate Change, Task Group on Data and Scenario Support for Impact and Climate Assessment. 66pp

  46. Kaba K, Sarıgül M, Avcı M, Kandırmaz HM (2018) Estimation of daily global solar radiation using deep learning model. Energy 162:126–135

    Article  Google Scholar 

  47. Karpathy A (2016) The unreasonable effectiveness of recurrent neural networks. http://karpathy.github.io/2015/05/21/rnn-effectiveness

  48. Ketkar N (2017) Introduction to keras, Deep learning with Python. Springer, Berlin, pp 97–111

  49. Kratzert F, Klotz D, Brenner C, Schulz K, Herrnegger M (2018) Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrol Earth Syst Sci 22(11):6005–6022. https://doi.org/10.5194/hess-22-6005-2018

    Article  Google Scholar 

  50. Kursa MB (2016) Embedded all relevant feature selection with random ferns. arXiv preprint arXiv:1604.06133.

  51. Kursa MB, Rudnicki WR (2010) Feature selection with the Boruta package. J Stat Softw 36(11):1–13

    Article  Google Scholar 

  52. Kursa MB, Jankowski A, Rudnicki WR (2010) Boruta—a system for feature selection. Fundamenta Informaticae 101(4):271–285

    Article  Google Scholar 

  53. Le H, Lee J (2019) Application of long short-term memory (LSTM) Neural network for flood forecasting. Water. https://doi.org/10.3390/w11071387

    Article  Google Scholar 

  54. Legates DR, McCabe GJ (1999) Evaluating the use of “goodness-of-fit” Measures in hydrologic and hydroclimatic model validation. Water Resour Res 35(1):233–241. https://doi.org/10.1029/1998wr900018

    Article  Google Scholar 

  55. Legates DR, McCabe GJ (2013) A refined index of model performance: a rejoinder. Int J Climatol 33(4):1053–1056. https://doi.org/10.1002/joc.3487

    Article  Google Scholar 

  56. Leutner BF et al (2012) Modelling forest α-diversity and floristic composition—on the added value of LiDAR plus hyperspectral remote sensing. Remote Sensing 4(9):2818–2845

    Article  Google Scholar 

  57. Li J, Tran M, Siwabessy J (2016) Selecting optimal random forest predictive models: a case study on predicting the spatial distribution of seabed hardness. PLoS ONE 11(2):e0149089

    Article  Google Scholar 

  58. Li J, Johnson F, Evans J, Sharma A (2017) A comparison of methods to estimate future sub-daily design rainfall. Adv Water Resour 110:215–227. https://doi.org/10.1016/j.advwatres.2017.10.020

    Article  Google Scholar 

  59. Liong SY, Sivapragasam C (2002) Flood stage forecasting with support vector machines 1. JAWRA J Am Water Resour Assoc 38(1):173–186

    Article  Google Scholar 

  60. Liong SY, Lim WH, Kojiri T, Hori T (2000) Advance flood forecasting for flood stricken Bangladesh with a fuzzy reasoning method. Hydrol Process 14(3):431–448

    Article  Google Scholar 

  61. Liu Y et al (2011) An improved particle swarm optimization for feature selection. J Bionic Eng 8(2):191–200

    Article  Google Scholar 

  62. Lyu B, Zhang Y, Hu Y (2017) Improving PM2. 5 air quality model forecasts in China using a bias-correction framework. Atmosphere 8(8):147

    Article  Google Scholar 

  63. Marsland S et al (2013) Evaluation of ACCESS climate model ocean diagnostics in CMIP5 simulations. Aust Meteorol Oceanogr J 63:101–119

    Article  Google Scholar 

  64. Martin G et al (2011) The HadGEM2 family of Met Office Unified Model climate configurations. Geosci Model Dev 4:723–757. https://doi.org/10.5194/gmd-4-723-2011

    Article  Google Scholar 

  65. Matthews KB et al (2011) Raising the bar? – The challenges of evaluating the outcomes of environmental modelling and software. Environ Modell Softw 26(3):247–257. https://doi.org/10.1016/j.envsoft.2010.03.031

    Article  Google Scholar 

  66. Meher JK, Das L, Akhter J, Benestad RE, Mezghani A (2017) Performance of CMIP3 and CMIP5 GCMs to Simulate Observed Rainfall Characteristics over the Western Himalayan Region. J Clim 30(19):7777–7799. https://doi.org/10.1175/jcli-d-16-0774.1

    Article  Google Scholar 

  67. Mouatadid S, Adamowski J (2017) Using extreme learning machines for short-term urban water demand forecasting. Urban Water J 14(6):630–638. https://doi.org/10.1080/1573062X.2016.1236133

    CAS  Article  Google Scholar 

  68. Murray-Darling Basin Authority (2010) Guide to the proposed Basin Plan. Murray-Darling Basin Authority, Canberra

    Google Scholar 

  69. Olah C (2015) Understanding lstm networks. http://colah.github.io/posts/2015-08-Understanding-LSTMs

  70. Park et al (2019) Temperature prediction using the missing data refinement model based on a long short-term memory neural network. Atmosphere 10:718. https://doi.org/10.3390/atmos10110718

    Article  Google Scholar 

  71. Pedregosa F et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12(Oct):2825–2830

    Google Scholar 

  72. Phien HN, Kha NDA (2003) Flood forecasting for the upper reach of the Red River Basin. North Vietnam Water Sa 29(3):267–272

    Google Scholar 

  73. Prasad R, Deo RC, Li Y, Maraseni T (2017) Input selection and performance optimization of ANN-based streamflow forecasts in the drought-prone Murray Darling Basin region using IIS and MODWT algorithm. Atmos Res 197:42–63. https://doi.org/10.1016/j.atmosres.2017.06.014

    Article  Google Scholar 

  74. Prasad R, Deo RC, Li Y, Maraseni T (2018) Soil moisture forecasting by a hybrid machine learning technique: ELM integrated with ensemble empirical mode decomposition. Geoderma 330:136–161. https://doi.org/10.1016/j.geoderma.2018.05.035

    Article  Google Scholar 

  75. Prasad R, Deo RC, Li Y, Maraseni T (2019) Weekly soil moisture forecasting with multivariate sequential, ensemble empirical mode decomposition and Boruta-random forest hybridizer algorithm approach. CATENA 177:149–166. https://doi.org/10.1016/j.catena.2019.02.012

    Article  Google Scholar 

  76. Raman H, Sunilkumar N (1995) Multivariate modelling of water resources time series using artificial neural networks. Hydrol Sci J Sci Hydrol 40(2)

  77. Ramesh KV, Goswami P (2014) Assessing reliability of regional climate projections: the case of Indian monsoon. Sci Rep 4:4071. https://doi.org/10.1038/srep04071

    CAS  Article  Google Scholar 

  78. Ren Y, Suganthan P, Srikanth N (2014) A comparative study of empirical mode decomposition-based short-term wind speed forecasting methods. IEEE Trans Sustain Energy 6(1):236–244

    Article  Google Scholar 

  79. Sak H, Senior A, Beaufays F (2014) Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. arXiv preprint arXiv:1402.1128.

  80. Seo Y, Kim S (2016) Hydrological forecasting using hybrid data-driven approach. Am J Appl Sci 13(8):891–899. https://doi.org/10.3844/ajassp.2016.891.899

    Article  Google Scholar 

  81. Sharma E, Deoa RC, Prasadb R, Parisia AV (2019) A hybrid air quality early-warning framework: hourly forecasting model with online sequential extreme learning machine and empirical mode decomposition algorithm

  82. Sillmann J, Kharin VV, Zhang X, Zwiers FW, Bronaugh D (2013) Climate extremes indices in the CMIP5 multimodel ensemble: Part 1. Model evaluation in the present climate. J Geophys Res Atmos 118(4):1716–1733. https://doi.org/10.1002/jgrd.50203

    Article  Google Scholar 

  83. Stoppiglia H, Dreyfus G, Dubois R, Oussar Y (2003) Ranking a random feature for variable and feature selection. J Mach Learn Res 3(1):1399–1414

    Google Scholar 

  84. Strobl C, Boulesteix A-L, Kneib T, Augustin T, Zeileis A (2008) Conditional variable importance for random forests. BMC Bioinform 9(1):307

    Article  Google Scholar 

  85. Sun Q, Miao C, Duan Q (2015) Comparative analysis of CMIP3 and CMIP5 global climate models for simulating the daily mean, maximum, and minimum temperatures and daily precipitation over China. J Geophys Res Atmos 120(10):4806–4824. https://doi.org/10.1002/2014jd022994

    Article  Google Scholar 

  86. Taylor KE (2001) Summarizing multiple aspects of model performance in a single diagram. J Geophys Res Atmos 106(D7):7183–7192

    Article  Google Scholar 

  87. Taylor KE, Stouffer RJ, Meehl GA (2012) An overview of CMIP5 and the experiment design. Bull Am Meteor Soc 93(4):485–498. https://doi.org/10.1175/bams-d-11-00094.1

    Article  Google Scholar 

  88. Tiwari M, Adamowski J, Adamowski K (2016) Water demand forecasting using extreme learning machines. J Water Land Dev 28(1):37–52. https://doi.org/10.1515/jwld-2016-0004

    Article  Google Scholar 

  89. Tripathi S, Srinivas VV, Nanjundiah RS (2006) Downscaling of precipitation for climate change scenarios: a support vector machine approach. J Hydrol 330(3–4):621–640. https://doi.org/10.1016/j.jhydrol.2006.04.030

    Article  Google Scholar 

  90. Ul Hasson S, Pascale S, Lucarini V, Boehner J (2016) Seasonal cycle of precipitation over major river basins in South and Southeast Asia: a review of the CMIP5 climate models data for present climate and future climate projections. Atmos Res 180:42–63

    Article  Google Scholar 

  91. van Dijk AIJM et al (2013) The Millennium Drought in southeast Australia (2001–2009): Natural and human causes and implications for water resources, ecosystems, economy, and society. Water Resour Res 49(2):1040–1057. https://doi.org/10.1002/wrcr.20123

    Article  Google Scholar 

  92. Wang Y, Wu L (2016) On practical challenges of decomposition-based hybrid forecasting algorithms for wind speed and solar irradiation. Energy 112:208–220. https://doi.org/10.1016/j.energy.2016.06.075

    Article  Google Scholar 

  93. Wang B et al (2018) Using multi-model ensembles of CMIP5 global climate models to reproduce observed monthly rainfall and temperature with machine learning methods in Australia. Int J Climatol 38(13):4891–4902. https://doi.org/10.1002/joc.5705

    Article  Google Scholar 

  94. Willmott CJ, Matsuura K (2005) Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Res 30(1):79–82

    Article  Google Scholar 

  95. Willmott CJ et al (1985) Statistics for the evaluation and comparison of models. J Geophys Res Oceans 90(C5):8995–9005

    Article  Google Scholar 

  96. Willmott CJ, Robeson SM, Matsuura K (2012) A refined index of model performance. Int J Climatol 32(13):2088–2094. https://doi.org/10.1002/joc.2419

    Article  Google Scholar 

  97. Xu Y, Xu C, Gao X, Luo Y (2009) Projected changes in temperature and precipitation extremes over the Yangtze River Basin of China in the 21st century. Quatern Int 208(1–2):44–52

    Article  Google Scholar 

  98. Yan J, Chen X, Yu Y, Zhang X (2019) Application of a parallel particle swarm optimization-long short term memory model to improve water quality data. Water. https://doi.org/10.3390/w11071317

    Article  Google Scholar 

  99. Yang L et al (2018) Application of multivariate recursive nesting bias correction, multiscale wavelet entropy and AI-based models to improve future precipitation projection in upstream of the Heihe River. Northwest China Theor Appl Climatol 137(1–2):323–339. https://doi.org/10.1007/s00704-018-2598-y

    Article  Google Scholar 

  100. Yoo C, Cho E (2018) Comparison of GCM precipitation predictions with their RMSEs and pattern correlation coefficients. Water. https://doi.org/10.3390/w10010028

    Article  Google Scholar 

  101. Yoon H, Jun S-C, Hyun Y, Bae G-O, Lee K-K (2011) A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. J Hydrol 396(1–2):128–138. https://doi.org/10.1016/j.jhydrol.2010.11.002

    Article  Google Scholar 

  102. Yu P-S, Chen S-T, Chang IF (2006) Support vector regression for real-time flood stage forecasting. J Hydrol 328(3–4):704–716. https://doi.org/10.1016/j.jhydrol.2006.01.021

    Article  Google Scholar 

  103. Zaman B, McKee M (2014) Spatio-temporal prediction of root zone soil moisture using multivariate relevance vector machines. Open J Mod Hydrol 04(03):80–90. https://doi.org/10.4236/ojmh.2014.43007

    Article  Google Scholar 

  104. Zhang W et al (2017) A combined model based on CEEMDAN and modified flower pollination algorithm for wind speed forecasting. Energy Convers Manag 136:439–451. https://doi.org/10.1016/j.enconman.2017.01.022

    Article  Google Scholar 

  105. Zhang J, Zhu Y, Zhang X, Ye M, Yang J (2018) Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas. J Hydrol 561:918–929

    Article  Google Scholar 

  106. Zheng H, Yuan J, Chen L (2017) Short-term load forecasting using EMD-LSTM neural networks with a Xgboost algorithm for feature importance evaluation. Energies. https://doi.org/10.3390/en10081168

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to recognise the funding contribution of the Chinese Academy of Science (CAS) and the University of Southern Queensland (USQ) to provide a USQ-CAS postgraduate research scholarship (2019–2021) awarded to the first author, managed by the USQ Graduate Research School. The authors are greatful to the Editor and Reviewers whose comments have imporved the clarity of the final paper.

Author information

Affiliations

Authors

Contributions

A.A.M.A.: Writing—original draft, Conceptualisation, Methodology, Software, Model development and application. R.C.D.: Conceptualisation, Writing—review and editing, Investigation, Supervision. A.G.: Conceptualisation, Writing—review and editing. N.R.: Writing—review and editing, Q.F.: Writing—review and editing. Z.Y.: Writing—review and editing, L.Y.: Writing—review and editing.

Corresponding authors

Correspondence to A. A. Masrur Ahmed or Ravinesh C. Deo.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ahmed, A.A.M., Deo, R.C., Ghahramani, A. et al. LSTM integrated with Boruta-random forest optimiser for soil moisture estimation under RCP4.5 and RCP8.5 global warming scenarios. Stoch Environ Res Risk Assess 35, 1851–1881 (2021). https://doi.org/10.1007/s00477-021-01969-3

Download citation

Keywords

  • Soil moisture
  • Hybrid model
  • Boruta-random forest optimiser algorithm (BRF)
  • Global climate model (GCM)
  • Murray darling basin
  • Long short-term memory (LSTM)