Spatial and multi-depth temporal soil temperature assessment by assimilating satellite imagery, artificial intelligence and regression based models in arid area

Singh, Vijay Kumar; Singh, Bhaskar Pratap; Kişi, Özgür; Kushwaha, Daniel Prakash

doi:10.1016/j.compag.2018.04.019

Cited by 33 publications

(9 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Soil temperature and moisture are essential for investigating the dynamics of solar energy exchange between the land surface and the sub‐surface soil layers. Both Singh et al (2018) and Sanikhani et al (2018) analysed the model sensitivity via NN‐based models as ANFIS and ELM that generally perform higher predictive accuracy by means of statistical scores and diagnostic plots. With respect to soil moisture, Maroufpoor et al (2019) and Navarro‐Hellín et al (2016) tested two ANFIS‐based algorithms considered to be the best models for separately enhancing the simulation accuracy and reducing the weekly irrigating needs estimation.…”

Section: Ai Applications In Soil Management and Agricultural Productionmentioning

confidence: 99%

AI‐enhanced soil management and smart farming

Chen

Chong³

et al. 2021

Soil Use and Management

View full text Add to dashboard Cite

Soil and crop management are facing challenges, in particular an increasing pressure to feed a growing population and improve food safety. Smart farming assists in dealing with these issues by incorporating information and communication technologies into farming practice. The Multiponics Vertical Farming (MVF) system is a very promising concept in smart farming that saves space, transportation cost and delivery time. Complicated systems and messy data can be processed by advanced technologies to achieve greater accuracy and efficiency in modelling and computing. For dynamic and complex problems, Artificial Intelligence (AI) provides rapid evaluation and aids in designing effective solutions. This study discusses how AI is adopted in soil management and MVF for tasks including classification, detection and forecasting. Three categories of AI and machine learning techniques, Support Vector Machine (SVM), Decision Tree (DT) and Neural Network (NN)‐based models, that are widely used will be presented. Future perspectives on urban farming are also discussed.

show abstract

Section: Ai Applications In Soil Management and Agricultural Productionmentioning

confidence: 99%

AI‐enhanced soil management and smart farming

Chen

Chong³

et al. 2021

Soil Use and Management

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%

“…Some machine learning approaches have been widely used in geosciences engineering and Ts prediction. These include artificial neural network (ANN) (Tabari et al 2015;Sanikhani et al 2018;Mehdizadeh et al 2017;Kisi et al 2017;Samadianfard et al 2018a;Kazemi et al 2018), multilayer perceptron (MLP) (Kim and Singh 2014;Kisi et al 2015;Heddam, 2019;Sihag et al 2020), radial basis function (RBF) (Kisi et al 2015); general regression neural network (GRNN) (Feng et al 2019); extreme learning machine (ELM) (Nahvi et al 2016;Sanikhani et al 2018;Feng et al 2019), support vector machine (SVM) Delbari et al 2019), wavelet neural network (WNN) (Araghi et al 2017;Samadianfard et al 2018a), adaptive neuron fuzzy inference system (ANFIS) (Talaee 2014;Abyaneh et al 2016;Citakoglu 2017;Singh et al 2018), M5 model tree (Sanikhani et al 2018;Feng et al 2019), and gene expression programming (GEP) (Mehdizadeh et al 2017;Kisi et al 2017;Samadianfard et al 2018a). These models have proven useful in dealing with difficult non-linear and hidden relationships among input data, but often suffer from some weaknesses, such as easily falling into local optimums, membership function learning problems, over-fitting, and low convergence speed (Zhao et al 2019;Mehdizadeh et al 2020;Qasem et al 2019).…”

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

“…Over the last years, the AI-based techniques have been proposed in various areas of research, such as meteorological, hydrological and soil sciences (Tabari et al, 2011;Talaee, 2014;Aitkenhead and Coull, 2016;Liu et al, 2016;Citakoglu, 2017;Mehdizadeh et al, 2017aMehdizadeh et al, , 2018aGavili et al, 2018;Massawe et al, 2018;Singh et al, 2018;Maroufpoor et al, 2019;Azad et al, 2020;Mehdizadeh, 2020). For example, the AI approaches were applied successfully by Mehdizadeh (2018a), Mehdizadeh et al (2017b) and Azad et al (2020) to estimate the dew point and air temperatures.…”

Section: Introductionmentioning

confidence: 99%

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

Mehdizadeh

Ahmadi

Sales³

2020

Meteorological Applications

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

Spatial and multi-depth temporal soil temperature assessment by assimilating satellite imagery, artificial intelligence and regression based models in arid area

Cited by 33 publications

References 49 publications

AI‐enhanced soil management and smart farming

AI‐enhanced soil management and smart farming

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