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

Abstract

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.

Applicability of a CEEMD–ARIMA Combined Model for Drought Forecasting: A Case Study in the Ningxia Hui Autonomous Region

“…A model with the lowest RMSE and MAE and the highest KGE, WI, and NSE was selected and proposed as an appropriate model. The formulae are as follows [35][36][37][38]:…”

The role of soil temperature in mediterranean vineyards in a climate change context

“…( Bullied et al., 2003 ; Howell et al., 2020 ). At deeper soil layers ST influences root metabolism and growth, soil respiration, water and nutrient uptake, microbial diversity and activity, organic matter (OM) dynamics, soil bio-chemistry) ( Akter et al., 2015 ; Onwuka and Mang, 2018 ; Mehdizadeh et al., 2020a ; Mehdizadeh et al., 2020b ; Shah et al., 2022 ).…”

Machine Learning Approaches for One-Day Ahead Soil Temperature Forecasting

“…However, these approaches often require much data that may not be available for long-term forecasts. In the second category, artificial intelligence (AI) and machine learning models such as an artificial neural network (ANN) (Citakoglu 2017;Singhal et al 2021;Zhou et al 2020), support vector machine (Xing et al 2018), gene expression programming (GEP) (Mehdizadeh et al 2017), genetic programming (Gill & Singh 2015;Stajkowski et al 2020), adaptive neuro-fuzzy inference system (ANFIS) (Mehdizadeh et al 2020a) and hybrid models (Sattari et al 2020;Shamshirband et al 2020) are used. Various studies have modeled ST as a non-linear physical aspect (Li et al 2020;Xu et al 2020;Zeynoddin et al 2020;Hao et al 2021).…”