Developing novel hybrid models for estimation of daily soil temperature at various depths

Mehdizadeh, Saeid; Fathian, Farshad; Safari, Mir Jafar Sadegh; Khosravi, Ali

doi:10.1016/j.still.2019.104513

Cited by 44 publications

(29 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As a result, the accessibility of accurate and consistent ST data are very limited and hence there a need for robust model that able to capture the mapping between the input(s) and the ST as the model's output Feng et al [19]. Recently, Mehdizadeh et al [20] developed Fractionally Autoregressive Integrated Moving Average (FARIMA) model so as to predict the ST and compare the results with classical Artificial Intelligent (AI) models namely; Gene Expression Programming (GEP) and Feed Forward Back Propagation Neural Network (FFBPNN) methods. Although that the results showed that FARIMA outperformed the FFBPNN and GEP methods, the prediction accuracy for ST using FARIMA were relatively inadequate for the extreme ST values, Mehdizadeh et al [20].…”

Section: Introductionmentioning

confidence: 99%

Advanced machine learning model for better prediction accuracy of soil temperature at different depths

et al. 2020

View full text Add to dashboard Cite

Soil temperature has a vital importance in biological, physical and chemical processes of terrestrial ecosystem and its modeling at different depths is very important for land-atmosphere interactions. The study compares four machine learning techniques, extreme learning machine (ELM), artificial neural networks (ANN), classification and regression trees (CART) and group method of data handling (GMDH) in estimating monthly soil temperatures at four different depths. Various combinations of climatic variables are utilized as input to the developed models. The models' outcomes are also compared with multi-linear regression based on Nash-Sutcliffe efficiency, root mean square error, and coefficient of determination statistics. ELM is found to be generally performs better than the other four alternatives in estimating soil temperatures. A decrease in performance of the models is observed by an increase in soil depth. It is found that soil temperatures at three depths (5, 10 and 50 cm) could be mapped utilizing only air temperature data as input while solar radiation and wind speed information are also required for estimating soil temperature at the depth of 100 cm.

show abstract

Section: Introductionmentioning

confidence: 99%

Advanced machine learning model for better prediction accuracy of soil temperature at different depths

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Therefore, Ts measurements are not easily available for developing countries, such as Iran (Mehdizadeh et al 2020a). In addition, Ts varies on the land surface and at different soil depths (Moazenzadeh and Mohammadi 2019), but stations for recording Ts are often sparse and limited.…”

Section: -Introductionmentioning

confidence: 99%

Hourly soil temperature prediction using integrated machine learning methods, GLUE uncertainty analysis, Taguchi search, and wavelet coherence analysis

Seifi¹,

Ehteram²,

Nayebloei³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this study, hourly Ts variations at 5, 10, and 30 cm soil depth were investigated and predicted for an arid site (Sirjan) and a semi-humid site (Sanandaj) in Iran. Standalone machine learning models (adaptive neuron fuzzy interface system (ANFIS), support vector machine model (SVM), radial basis function neural network (RBFNN), and multilayer perceptron (MLP)) were hybridized with four optimization algorithms (sunflower optimization (SFO), firefly algorithm (FFA), salp swarm algorithm (SSA), particle swarm optimization (PSO)) to improve prediction accuracy and reduce uncertainty. Uncertainty analysis was performed using generalized likelihood uncertainty estimation (GLUE), while wavelet coherence was used to assess interactions between Ts and meteorological parameters. For the arid site, ANFIS-SFO (RMSE = 1.18oC, MAE = 1.05oC, NSE = 0.93, PBIAS = 7%, and R2 = 0.9998) produced the most accurate performance at 5 cm soil depth. At best, hybridization with SFO (ANFIS-SFO, MLP-SFO, RBFNN-SFO, SVM-SFO) decreased RMSE by 5.6, 18, 18.3, and 18.18 % compared with the respective standalone model. At the semi-humid site, all integrated models showed most accurate performance at 10 cm soil depth, with RMSE for the best model (ANFIS-SFO) increasing by 10.5%, and MAE by 10.1%, from 10 to 30 cm depth. GLUE analysis confirmed that integrating optimization algorithms with machine learning models decreased the uncertainty in Ts predictions. Wavelet coherence analysis demonstrated that air temperature, relative humidity, and solar radiation, but not wind speed, had high coherence with Ts at different soil depths at both sites, and meteorological parameters mostly influenced Ts in upper soil layers.

show abstract

“…The ELM was found to provide better performance than the other models. Novel hybrid models were proposed by Mehdizadeh et al (2020a) for modelling the daily ST at different depths. The authors used a time-series-based model called FARIMA, two machine-learning-based models, including feed-forward back propagation neural networks (FFBPNN) and GEP, as well as the hybrid FFBPNN-FARIMA and GEP-FARIMA.…”

Section: Introductionmentioning

confidence: 99%

“…For example, the ST can be estimated by artificial intelligence (AI)‐based models, such as adaptive neuro‐fuzzy inference systems (ANFIS), artificial neural networks (ANN), multivariate adaptive regression splines (MARS), M5 model tree (M5T), gene expression programming (GEP) and support vector machine (SVM) (Nahvi et al ., 2016; Citakoglu, 2017; Sanikhani et al ., 2018). Besides the AI‐based models, time‐series analysis (TSA) approaches could also be appropriate tools for the ST estimation (Mehdizadeh et al ., 2020a). The linear autoregressive (AR), autoregressive moving average (ARMA), autoregressive integrated moving average (ARIMA), fractionally autoregressive integrated moving average (FARIMA), as well as non‐linear bi‐linear (BL), autoregressive conditional heteroscedasticity (ARCH) and self‐exciting threshold autoregressive (SETAR) models belong to the TSA‐based techniques.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modelling daily soil temperature at different depths via the classical and hybrid models

Mehdizadeh

Ahmadi

Sales³

2020

Meteorological Applications

Self Cite

View full text Add to dashboard Cite

Soil temperature (ST) is one of the crucial variables of soil and it plays a fundamental role in different research scopes such as underground soil physical and agricultural applications. The study explores the modelling performance of a time series‐based model (i.e. bi‐linear, BL), and an artificial intelligence‐based approach including adaptive neuro‐fuzzy inference system (ANFIS), for modelling the daily ST of different soil depths (5, 10, 50 and 100 cm). The study also develops and proposes two diverse types of the hybrid models through coupling the ANFIS with the BL and wavelet analysis (W) to improve the accuracy of the ST modelling. Two stations in Iran (i.e. Isfahan and Urmia) were selected as the study locations. The results demonstrated that the ANFIS generally presented better results than the BL. Furthermore, the hybrid models (i.e. W‐ANFIS and ANFIS‐BL) gave superior performances than the classical ANFIS and BL for modelling the daily ST of the studied areas at various soil depths. In addition to the local evaluation of the ANFIS (i.e. modelling the ST at a specific depth by using the original ST data at that depth), an external analysis was also conducted. In doing so, the daily ST data at a 5 cm depth were modelled via the corresponding ST data at a 10 cm depth, and vice versa. The results denoted the applicability of the ST data at another depth for modelling the ST of each specific/target depth.

show abstract

Developing novel hybrid models for estimation of daily soil temperature at various depths

Cited by 44 publications

References 38 publications

Advanced machine learning model for better prediction accuracy of soil temperature at different depths

Advanced machine learning model for better prediction accuracy of soil temperature at different depths

Hourly soil temperature prediction using integrated machine learning methods, GLUE uncertainty analysis, Taguchi search, and wavelet coherence analysis

Modelling daily soil temperature at different depths via the classical and hybrid models

Contact Info

Product

Resources

About