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

Alizamir, Meysam; Kim, Sung-Won; Zounemat‐Kermani, Mohammad; Heddam, Salim; Shahrabadi, Amin Hasanalipour; Gharabaghi, Bahram

doi:10.1007/s10462-020-09915-5

Cited by 23 publications

(13 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…), and vegetation (coverage, species, etc. ), with complex variation characteristics [34][35][36]. In arid and semi-arid regions, land use is a critical factor that influences soil temperature changes [7,37].…”

Section: Characteristics Of Variation In Soil Moisture and Temperaturementioning

confidence: 99%

Sloping land use affects the complexity of soil moisture and temperature changes in the loess hilly region of China

et al. 2022

View full text Add to dashboard Cite

Various land use types have been implemented by the government in the loess hilly region of China to facilitate sustainable land use. Understanding the variability in soil moisture and temperature under various sloping land use types can aid the ecological restoration and sustainable utilization of sloping land resources. The objective of this study was to use approximate entropy (ApEn) to reveal the variations in soil moisture and temperature under different land use types, because ApEn only requires a short data series to obtain robust estimates, with a strong anti-interference ability. An experiment was conducted with four typical land use scenarios (i.e., soybean sloping field, maize terraced field, jujube orchard, and grassland) over two consecutive plant growing seasons (2014 and 2015), and the time series of soil moisture and temperature within different soil depth layers of each land use type were measured in both seasons. The results showed that the changing amplitude, degree of variation, and active layer of soil moisture in the 0–160 cm soil depth layer, as well as the changing amplitude and degree of variation of soil temperature in the 0–100 cm soil layer increased in the jujube orchard over the two growing seasons. The changing amplitude, degree of variation, and active layer of soil moisture all decreased in the maize terraced field, as did the changing amplitude and degree of variation of soil temperature. The ApEn of the soil moisture series was the lowest in the 0–160 cm soil layer in the maize terraced field, and the ApEn of the soil temperature series was the highest in the 0–100 cm layer in the jujube orchard in the two growing seasons. Finally, the jujube orchard soil moisture and temperature change process were more variable, whereas the changes in the maize terraced field were more stable, with a stable soil moisture and temperature. This work highlights the usefulness of ApEn for revealing soil moisture and temperature changes and to guide the management and development of sloping fields.

show abstract

Section: Characteristics Of Variation In Soil Moisture and Temperaturementioning

confidence: 99%

Sloping land use affects the complexity of soil moisture and temperature changes in the loess hilly region of China

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Classification is the task of categorizing an input sample data into one of the predefined classes. In the literature, there are several soil temperature prediction studies that apply different machine learning techniques, such as regression (Alizamir et al 2020a;Alizamir et al 2020b;Sattari et al 2020;Abyaneh et al 2016;Li et al 2020) and time series (Zeynoddin et al 2020;Mehdizadeh et al 2020). For example, (Alizamir et al 2020b) proposed a deep echo state network (Deep ESN) regression model for soil temperature prediction at 10 and 20 cm depths.…”

Section: Introductionmentioning

confidence: 99%

“…In the literature, there are several soil temperature prediction studies that apply different machine learning techniques, such as regression (Alizamir et al 2020a;Alizamir et al 2020b;Sattari et al 2020;Abyaneh et al 2016;Li et al 2020) and time series (Zeynoddin et al 2020;Mehdizadeh et al 2020). For example, (Alizamir et al 2020b) proposed a deep echo state network (Deep ESN) regression model for soil temperature prediction at 10 and 20 cm depths. In another study, a new time-series model, called fractionally autoregressive integrated moving average (FARIMA), was implemented for daily soil temperature prediction at four depths (5, 10, 50, and 100 cm) (Mehdizadeh et al 2020).…”

Section: Introductionmentioning

confidence: 99%

“…More specifically, this study brings together notions from the fields of agriculture and machine learning for information fusion. In the regression studies, DT (Sattari et al 2020;Sanikhani et al 2018), Support Vector Regression (SVR) (Li et al 2020a;Li et al 2020b;Shamshirband et al 2020;Delbari et al 2019;Mehdizadeh et al 2018;Xing et al 2018), RF (Alizamir et al 2020b;Tsai et al 2020;Feng et al 2019), NN (Abimbola et al 2021;Bayatvarkeshi et al 2021;Wang et al 2021;Hao et al 2020;Penghui et al 2020;Citakoglu 2017;Abyaneh et al 2016;Kisi et al 2015), ELM (Alizamir et al 2020a) algorithms have been preferred for predicting soil temperatures. In addition, some of the time-series studies have also applied NN (Li et al 2020c;Bonakdari et al 2019), ELM (Zeynoddin et al 2020;Mehdizadeh et al 2020), SVR (Nanda et al 2020) algorithms for the prediction performance comparison.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)

KÜÇÜK

Birant

Taşer

2022

J Agr Sci-Tarim Bili

View full text Add to dashboard Cite

show abstract

“…Soil temperature (Ts( is an influential and vital parameter in sustainable agriculture and geosciences practices, since it greatly influences physical, geological, chemical, and microbiological processes in the soil (Feng et al 2019;Alizamir et al 2020;Singh et al 2018).…”

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

Self Cite

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

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

Cited by 23 publications

References 64 publications

Sloping land use affects the complexity of soil moisture and temperature changes in the loess hilly region of China

Sloping land use affects the complexity of soil moisture and temperature changes in the loess hilly region of China

A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC)

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

Contact Info

Product

Resources

About