Soil Temperature Prediction Using Time-Delay Neural Networks

Mazou, E.; Alvertos, N.; Tsiros, Ioannis X.

doi:10.1007/978-3-642-29172-2_87

Cited by 10 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mazou et al. (2012) used dynamic neural networks, which are recurrent neural networks with feedback loops that include time‐delay elements. The data used for the neural network's training, validation and testing were hourly values for the period 2002–2005 obtained from a weather station in Athens, Greece.…”

Section: Data‐driven Approachmentioning

confidence: 99%

“…Data‐driven techniques such as ANNs have been widely used for soil temperature estimation at multiple depths (George, 2001; Kisi et al., 2015; Mazou et al., 2012; Mihalakakou, 2002; Ozturk et al., 2011; Samadianfard, Asadi, et al., 2018; Sihag et al., 2020; Tabari et al., 2011). Artificial neural networks are mathematical models consisting of a network of computation nodes called neurons with established connections between them (Sattari et al., 2017).…”

Section: Data‐driven Approachmentioning

confidence: 99%

See 1 more Smart Citation

Knowledge‐guided machine learning for improving daily soil temperature prediction across the United States

Abimbola

Meyer

Mittelstet

et al. 2021

Vadose Zone Journal

View full text Add to dashboard Cite

Data-driven models used for predicting soil temperature usually have increasing errors with increasing depth. By exploring the integration of knowledge-based and machine learning approaches, this study used a novel transformation of meteorological variables to increase prediction accuracy of soil temperature with increasing soil depth. Using datasets for two soil textures (silty clay loam and loamy coarse sand) at two locations with different climates, predictive models were developed for five depths (5, 10, 20, 50, and 100 cm) as a function of meteorological features using an adaptive neuro-fuzzy inference system (ANFIS). For each depth, soil temperature was predicted with nontransformation (NT), autocorrelation (AC), moving average (MA), and a combination of transformations (NT-ACMA) of meteorological features. Across all depths, the predictive accuracy of NT-ACMA models was significantly higher than that of NT, AC, and MA models for both soil textures (R 2 = .99, RMSE = 1˚C for silty clay loam; R 2 = .99, RMSE = 1.2˚C for loamy coarse sand), with increasing prediction accuracy as soil depth increases. Results for different soil textures and climates in 11 locations across the contiguous United States show that, except for 100-cm depth, there seems to be significant positive linear relationships between the best moving average and the solar inclination. This makes our NT-ACMA technique transferable to any location in the contiguous United States irrespective of the location, climate, and soil texture. We conclude that integrating lag times and moving averages of meteorological features can lead to better prediction of soil temperature at different soil depths.

show abstract

Section: Data‐driven Approachmentioning

confidence: 99%

Section: Data‐driven Approachmentioning

confidence: 99%

Knowledge‐guided machine learning for improving daily soil temperature prediction across the United States

Abimbola

Meyer

Mittelstet

et al. 2021

Vadose Zone Journal

View full text Add to dashboard Cite

show abstract

“…Therefore, methods that can provide acceptable results may be a suitable solution for estimating ST at the needed locations as well as predicting for subsequent CONTACT Davoud Zarehaghi davoudhaghi@tabrizu.ac.ir months. The use of artificial neural network models has been widely considered in recent years (Chau & Muttil, 2007;Cheng et al, 2005;Fotovatikhah et al, 2018;Kazemi et al, 2018;Kim & Singh, 2014;Kisi et al, 2015;Mazou et al, 2013;Moazenzadeh et al, 2018;Qasem et al, 2019;Samadianfard et al, 2019;Samadianfard, Ghorbani, et al, 2018;Wu et al, 2013;Yaseen et al, 2019). So far, many studies have been carried out on soil temperature estimation.…”

Section: Introductionmentioning

confidence: 99%