Modelling daily soil temperature by hydro-meteorological data at different depths using a novel data-intelligence model: deep echo state network model

Soil temperature (Ts) is an essential regulator of a plant’s root growth, evapotranspiration rates, and hence soil water content. Over the last few years, in response to the climatic change, significant amount of research has been conducted worldwide to understand the quantitative link between soil temperature and the climatic factors, and it was highlighted that the hydrothermal conditions in the soil are continuously changing in response to the change of the hydro-meteorological factors. A large amount of the models have been developed and used in the past for the analysis and modelling of soil temperature, however, none of them has investigated the robustness and feasibilities of the deep echo state network (Deep ESN) model. A more accurate model for forecasting Ts presents many worldwide opportunities in improving irrigation efficiency in arid climates and help attain sustainable water resources management. This research compares the application of the novel Deep ESN model versus three conventional machine learning models for soil temperature forecasting at 10 and 20 cm depths. We combined several critical daily hydro-meteorological data into six different input combinations for constructing the Deep ESN model. The accuracy of the developed soil temperature models is evaluated using three deterministic indices. The results of the evaluation indicate that the Deep ESN model outperformed conventional machine learning methods and can reduce the root mean square error (RMSE) accuracy of the traditional models between 30 and 60% in both stations. In the test phase, the most accurate estimation was obtained by Deep ESN at depths of 10 cm by RMSE = 2.41 °C and 20 cm by RMSE = 1.28 °C in Champaign station and RMSE = 2.17 °C (10 cm) and RMSE = 1.52 °C (20 cm) in Springfield station. The superior performance of the Deep ESN model confirmed that this model can be successfully applied for modelling Ts based on meteorological paarameters.

[1]  Mir Jafar Sadegh Safari,et al.  Developing novel hybrid models for estimation of daily soil temperature at various depths , 2020 .

[2]  Ozgur Kisi,et al.  Modeling soil temperatures at different depths by using three different neural computing techniques , 2015, Theoretical and Applied Climatology.

[3]  Mohammad Bagher Menhaj,et al.  Real time identification and control of dynamic systems using recurrent neural networks , 2009, Artificial Intelligence Review.

[4]  Ozgur Kisi,et al.  Modelling reference evapotranspiration by combining neuro-fuzzy and evolutionary strategies , 2020, Acta Geophysica.

[5]  L. Nguyen,et al.  Effects of elevated temperature and elevated CO2 on soil nitrification and ammonia-oxidizing microbial communities in field-grown crop. , 2019, The Science of the total environment.

[6]  Jafar Habibi,et al.  Using self-adaptive evolutionary algorithm to improve the performance of an extreme learning machine for estimating soil temperature , 2016, Comput. Electron. Agric..

[7]  Ozgur Kisi,et al.  A comparative study of several machine learning based non-linear regression methods in estimating solar radiation: Case studies of the USA and Turkey regions , 2020 .

[8]  J. Behmanesh,et al.  Estimation of soil temperature using gene expression programming and artificial neural networks in a semiarid region , 2017, Environmental Earth Sciences.

[9]  Ozgur Kisi,et al.  Soil temperature modeling at different depths using neuro-fuzzy, neural network, and genetic programming techniques , 2017, Theoretical and Applied Climatology.

[10]  Roozbeh Moazenzadeh,et al.  Assessment of bio-inspired metaheuristic optimisation algorithms for estimating soil temperature , 2019, Geoderma.

[11]  Saeid Mehdizadeh,et al.  Evaluating the performance of artificial intelligence methods for estimation of monthly mean soil temperature without using meteorological data , 2017, Environmental Earth Sciences.

[12]  Ian H. Witten,et al.  Induction of model trees for predicting continuous classes , 1996 .

[13]  Jiquan Chen,et al.  Grazing modulates soil temperature and moisture in a Eurasian steppe , 2018, Agricultural and Forest Meteorology.

[14]  Vijay P. Singh,et al.  Modeling daily soil temperature using data-driven models and spatial distribution , 2014, Theoretical and Applied Climatology.

[15]  Jan Adamowski,et al.  Forecasting soil temperature based on surface air temperature using a wavelet artificial neural network , 2017 .

[16]  Bahram Gharabaghi,et al.  A reliable linear stochastic daily soil temperature forecast model , 2019, Soil and Tillage Research.

[17]  Ozgur Kisi,et al.  Advanced machine learning model for better prediction accuracy of soil temperature at different depths , 2020, PloS one.

[18]  Hatice Citakoglu,et al.  Comparison of artificial intelligence techniques for prediction of soil temperatures in Turkey , 2017, Theoretical and Applied Climatology.

[19]  Bahram Gharabaghi,et al.  New insights into soil temperature time series modeling: linear or nonlinear? , 2019, Theoretical and Applied Climatology.

[20]  M. Bahador,et al.  Modelling seed germination and seedling emergence of flax and sesame as affected by temperature, soil bulk density, and sowing depth , 2019 .

[21]  Parveen Sihag,et al.  Model-based soil temperature estimation using climatic parameters: the case of Azerbaijan Province, Iran , 2020, Geology, Ecology, and Landscapes.

[22]  V. Singh,et al.  Assessing the biochemical oxygen demand using neural networks and ensemble tree approaches in South Korea. , 2020, Journal of environmental management.

[23]  Nguyen Thi Thuy Linh,et al.  Implementing novel hybrid models to improve indirect measurement of the daily soil temperature: Elman neural network coupled with gravitational search algorithm and ant colony optimization , 2020 .

[24]  S. Heddam.  Development of air–soil temperature model using computational intelligence paradigms: artificial neural network versus multiple linear regression , 2018, Modeling Earth Systems and Environment.

[25]  P. Hosseinzadeh Talaee.  Daily soil temperature modeling using neuro-fuzzy approach , 2014, Theoretical and Applied Climatology.

[26]  Mohammad Ali Ghorbani,et al.  Forecasting soil temperature at multiple-depth with a hybrid artificial neural network model coupled-hybrid firefly optimizer algorithm , 2018, Information Processing in Agriculture.

[27]  Ozgur Kisi,et al.  Wavelet neural networks and gene expression programming models to predict short-term soil temperature at different depths , 2018 .

[28]  Özgür Kisi,et al.  Spatial and multi-depth temporal soil temperature assessment by assimilating satellite imagery, artificial intelligence and regression based models in arid area , 2018, Comput. Electron. Agric..

[29]  Özgür Kisi,et al.  Daily pan evaporation modeling using chi-squared automatic interaction detector, neural networks, classification and regression tree , 2016, Comput. Electron. Agric..

[30]  Lin Zhao,et al.  Variations in soil temperature from 1980 to 2015 in permafrost regions on the Qinghai-Tibetan Plateau based on observed and reanalysis products , 2019, Geoderma.

[31]  Weimin Ju,et al.  Remotely sensed soil temperatures beneath snow-free skin-surface using thermal observations from tandem polar-orbiting satellites: An analytical three-time-scale model , 2014 .

[32]  Xuesong Zhang,et al.  Modeling soil temperature in a temperate region: A comparison between empirical and physically based methods in SWAT , 2019, Ecological Engineering.

[33]  Bahram Gharabaghi,et al.  Spatial variability analysis and mapping of soil physical and chemical attributes in a salt-affected soil , 2019, Arabian Journal of Geosciences.

[34]  Gaihe Yang,et al.  Impact of straw management on seasonal soil carbon dioxide emissions, soil water content, and temperature in a semi-arid region of China. , 2019, The Science of the total environment.

[35]  Ningbo Cui,et al.  Estimation of soil temperature from meteorological data using different machine learning models , 2019, Geoderma.

[36]  Yu Zhang,et al.  Soil temperature in Canada during the twentieth century: Complex responses to atmospheric climate change , 2005 .

[37]  S. Mehdizadeh,et al.  Modelling daily soil temperature at different depths via the classical and hybrid models , 2020, Meteorological Applications.

[38]  Ozgur Kisi,et al.  Dissolved oxygen prediction using a new ensemble method , 2020, Environmental Science and Pollution Research.

[39]  Jan Adamowski,et al.  Estimating the aeration coefficient and air demand in bottom outlet conduits of dams using GEP and decision tree methods , 2017 .

[40]  Cihan Kaleli,et al.  A review on deep learning for recommender systems: challenges and remedies , 2018, Artificial Intelligence Review.

[41]  Ehsan Mohammadi,et al.  Modeling daily soil temperature over diverse climate conditions in Iran—a comparison of multiple linear regression and support vector regression techniques , 2019, Theoretical and Applied Climatology.

[42]  J. Adamowski,et al.  Investigating the management performance of disinfection analysis of water distribution networks using data mining approaches , 2018, Environmental Monitoring and Assessment.

[43]  Bahram Gharabaghi,et al.  Genetic-Algorithm-Optimized Sequential Model for Water Temperature Prediction , 2020, Sustainability.

[44]  Ozgur Kisi,et al.  Prediction of diffuse photosynthetically active radiation using different soft computing techniques , 2017 .

[45]  A. A. Mahboubi,et al.  Temperature effect on the transport of bromide and E. coli NAR in saturated soils , 2015 .

[46]  Bahram Gharabaghi,et al.  A modified FAO evapotranspiration model for refined water budget analysis for Green Roof systems , 2018, Ecological Engineering.

[47]  Ozgur Kisi,et al.  Modelling reference evapotranspiration using a new wavelet conjunction heuristic method: Wavelet extreme learning machine vs wavelet neural networks , 2018, Agricultural and Forest Meteorology.

[48]  Saeid Mehdizadeh,et al.  Comprehensive modeling of monthly mean soil temperature using multivariate adaptive regression splines and support vector machine , 2018, Theoretical and Applied Climatology.

[49]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[50]  Ozgur Kisi,et al.  Non-tuned data intelligent model for soil temperature estimation: A new approach , 2018, Geoderma.

[51]  Joaquín Salas,et al.  Dynamics of soil surface temperature with unmanned aerial systems , 2020, Pattern Recognit. Lett..

[52]  John Abraham,et al.  Prediction of Groundwater Level in Ardebil Plain Using Support Vector Regression and M5 Tree Model , 2018, Ground water.

[53]  R. Conrad,et al.  Effect of temperature on the microbial community responsible for methane production in alkaline NamCo wetland soil , 2019, Soil Biology and Biochemistry.

[54]  Mawloud Guermoui,et al.  Modeling soil temperature based on Gaussian process regression in a semi-arid-climate, case study Ghardaia, Algeria , 2016 .

[55]  Ladislav Hluchý,et al.  Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey , 2019, Artificial Intelligence Review.

[56]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[57]  A. A. Mahboubi,et al.  Comparison of three models describing bromide transport affected by different soil structure types , 2016 .

[58]  Kerry T.B. MacQuarrie,et al.  Climate change impacts on groundwater and soil temperatures in cold and temperate regions: Implications, mathematical theory, and emerging simulation tools , 2014 .

[59]  Sungwon Kim,et al.  Deep echo state network: a novel machine learning approach to model dew point temperature using meteorological variables , 2020 .

[60]  Ren Li,et al.  Evaluation of reanalysis soil temperature and soil moisture products in permafrost regions on the Qinghai-Tibetan Plateau , 2020 .

[61]  Ozgur Kisi,et al.  Modeling groundwater fluctuations by three different evolutionary neural network techniques using hydroclimatic data , 2017, Natural Hazards.

[62]  Pedro Henriques Abreu,et al.  Using deep learning techniques in medical imaging: a systematic review of applications on CT and PET , 2019, Artificial Intelligence Review.

[63]  Peter Xiaoping Liu,et al.  Deep learning for face image synthesis and semantic manipulations: a review and future perspectives , 2020, Artificial Intelligence Review.

[64]  Bahram Gharabaghi,et al.  An experimental and modeling study of evapotranspiration from integrated green roof photovoltaic systems , 2020 .

[65]  Alain Royer,et al.  AMSR-E data inversion for soil temperature estimation under snow cover , 2010 .

[66]  P. Hosseinzadeh Talaee,et al.  Daily soil temperature modeling using neuro-fuzzy approach , 2014 .

[67]  Claudio Gallicchio,et al.  Comparison between DeepESNs and gated RNNs on multivariate time-series prediction , 2018, ESANN.

[68]  Mohammad Zounemat-Kermani,et al.  Hydrometeorological Parameters in Prediction of Soil Temperature by Means of Artificial Neural Network: Case Study in Wyoming , 2013 .