scholarly journals Soil Temperature Estimation with Meteorological Parameters by Using Tree-Based Hybrid Data Mining Models

Mathematics ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1407
Author(s):  
Mohammad Taghi Sattari ◽  
Anca Avram ◽  
Halit Apaydin ◽  
Oliviu Matei
Keyword(s):  
Soil Temperature ◽  
Soil Depth ◽  
Sunshine Duration ◽  
Evaluation Criteria ◽  
Nonlinear Problems ◽  
Soil Temperatures ◽  
Different Depths ◽  
Windowing Technique ◽  
Using Data ◽  
Research Decision

The temperature of the soil at different depths is one of the most important factors used in different disciplines, such as hydrology, soil science, civil engineering, construction, geotechnology, ecology, meteorology, agriculture, and environmental studies. In addition to physical and spatial variables, meteorological elements are also effective in changing soil temperatures at different depths. The use of machine-learning models is increasing day by day in many complex and nonlinear branches of science. These data-driven models seek solutions to complex and nonlinear problems using data observed in the past. In this research, decision tree (DT), gradient boosted trees (GBT), and hybrid DT–GBT models were used to estimate soil temperature. The soil temperatures at 5, 10, and 20 cm depths were estimated using the daily minimum, maximum, and mean temperature; sunshine intensity and duration, and precipitation data measured between 1993 and 2018 at Divrigi station in Sivas province in Turkey. To predict the soil temperature at different depths, the time windowing technique was used on the input data. According to the results, hybrid DT–GBT, GBT, and DT methods estimated the soil temperature at 5 cm depth the most successfully, respectively. However, the best estimate was obtained with the DT model at soil depths of 10 and 20 cm. According to the results of the research, the accuracy rate of the models has also increased with increasing soil depth. In the prediction of soil temperature, sunshine duration and air temperature were determined as the most important factors and precipitation was the most insignificant meteorological variable. According to the evaluation criteria, such as Nash-Sutcliffe coefficient, R, MAE, RMSE, and Taylor diagrams used, it is recommended that all three (DT, GBT, and hybrid DT–GBT) data-based models can be used for predicting soil temperature.

scholarly journals Recognition of Changes in Air and Soil Temperatures at a Station Typical of China’s Subtropical Monsoon Region (1961–2018)

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Ming-jin Zhan ◽  
Lingjun Xia ◽  
Longfei Zhan ◽  
Yuanhao Wang
Keyword(s):  
Climate Change ◽  
Soil Temperature ◽  
Air Temperature ◽  
Soil Depth ◽  
Terrestrial Ecosystems ◽  
Soil Temperatures ◽  
Different Depths ◽  
Change Impact ◽  
The Mean ◽  
Autumn And Winter

Trends in soil temperature are important but rarely reported indicators of climate change. Based on daily air and soil temperatures (depth: 0, 20, 80, and 320 cm) recorded at the Nanchang Weather Station (1961–2018), this study investigated the variation trend, abrupt changes, and years of anomalous annual and seasonal mean air and soil temperatures. The differences and relationships between annual air and soil temperatures were also analyzed. The results showed close correlations between air temperature and soil temperature at different depths. Annual and seasonal mean air and soil temperatures mainly displayed significant trends of increase over the past 58 years, although the rise of the mean air temperature and the mean soil temperature was asymmetric. The rates of increase in air temperature and soil temperature (depth: 0, 20, and 80 cm) were most obvious in spring; the most significant increase in soil temperature at the depth of 320 cm was in summer. Mean soil temperature displayed a decreasing trend with increasing soil depth in both spring and summer. Air temperature was lower than the soil temperature at depths of 0 and 20 cm but higher than the soil temperature at depths of 80 and 320 cm in spring and summer. Mean ground temperature had a rising trend with increasing soil depth in autumn and winter. Air temperature was lower than the soil temperature at all depths in autumn and winter. Years with anomalously low air temperature and soil temperature at depths of 0, 20, 80, and 320 cm were relatively consistent in winter. Years with anomalous air and soil temperatures (depths: 0, 20, and 80 cm) were generally consistent; however, the relationship between air temperature and soil temperature at 320 cm depth was less consistent. The findings provide a basis for understanding and assessing climate change impact on terrestrial ecosystems.

scholarly journals ON THE ISSUE OF STUDYING THE TEMPERATURE REGIME OF THE BASTAK NATURE RESERVE SOILS WITH THE PROFESSIONAL WEATHER STATION «SOKOL-M»

2021 ◽  
Vol 24 (2-3) ◽  
pp. 85-89
Author(s):  
А.M. Alexandrova
Keyword(s):  
Soil Temperature ◽  
Temperature Regime ◽  
Soil Profile ◽  
Nature Reserve ◽  
Heat Propagation ◽  
Weather Station ◽  
Soil Temperatures ◽  
Different Depths ◽  
Using Data

The paper presents the experience of using data on soil temperature obtained with the help of a professional weather station «Sokol-M» in the Bastak nature reserve. The author has made the analysis of average daily air and soil temperature indicators at different depths. The process of heat propagation deep into the soil is observed, due to the absence of negative soil temperatures at a depth of 25 cm, with negative indicators in the upper 10 cm of the soil profile.

scholarly journals Quality control of 10-min soil temperatures data at RMI

2015 ◽  
Vol 12 (1) ◽  
pp. 23-30 ◽  
Author(s):  
C. Bertrand ◽  
L. González Sotelino ◽  
M. Journée
Keyword(s):  
Quality Control ◽  
Soil Temperature ◽  
Bare Soil ◽  
Climate Conditions ◽  
Air Temperatures ◽  
Temperature Observation ◽  
Soil Temperatures ◽  
Different Depths ◽  
Temperature Records ◽  
Energy Processes

Abstract. Soil temperatures at various depths are unique parameters useful to describe both the surface energy processes and regional environmental and climate conditions. To provide soil temperature observation in different regions across Belgium for agricultural management as well as for climate research, soil temperatures are recorded in 13 of the 20 automated weather stations operated by the Royal Meteorological Institute (RMI) of Belgium. At each station, soil temperature can be measured at up to 5 different depths (from 5 to 100 cm) in addition to the bare soil and grass temperature records. Although many methods have been developed to identify erroneous air temperatures, little attention has been paid to quality control of soil temperature data. This contribution describes the newly developed semi-automatic quality control of 10-min soil temperatures data at RMI.

scholarly journals Development of Shallow-Depth Soil Temperature Estimation Model Based on Thermal Response in Permafrost Area

2018 ◽  
Vol 8 (10) ◽  
pp. 1886 ◽  
Author(s):  
Keunbo Park ◽  
Heekwon Yang ◽  
Bang Lee ◽  
Dongwook Kim
Keyword(s):  
Soil Temperature ◽  
Temperature Measurement ◽  
Thermal Response ◽  
Estimation Model ◽  
Temperature Estimation ◽  
Soil Temperatures ◽  
Different Depths ◽  
The Relationship ◽  
Temperature Depth ◽  
Good Agreement

A soil temperature estimation model for increasing depth in a permafrost area in Alaska near the Bering Sea is proposed based on a thermal response concept. Thermal response is a measure of the internal physical heat transfer of soil due to transferred heat into the soil. Soil temperature data at different depths from late spring to the early autumn period at multiple permafrost sites were collected using automatic sensor measurements. From the analysis results, a model was established based on the relationship between the normalized cumulative soil temperatures (CRCST*i,m and CST*ud,m) of two different depths. CST*ud,m is the parameter of the soil temperature measurement at a depth of 5 cm, and CRCST*i,m is the parameter of the soil temperature measured at deeper depths of i cm (i = 10, 15, 20, and 30). Additionally, the fitting parameters of the mathematical models of the CRCST*i,m–CST*ud,m relationship were determined. The measured soil temperature depth profiles at a different site were compared with their predicted soil temperatures using the developed model for the model validation purpose. Consequently, the predicted soil temperatures at different soil depths using the soil temperature measurement of the uppermost depth (5 cm) were in good agreement with the measured results.

scholarly journals Non-stationary temporal characterization of the temperature profile of a soil exposed to frost in south-eastern Canada

2008 ◽  
Vol 15 (3) ◽  
pp. 409-416 ◽  
Author(s):  
F. Anctil ◽  
A. Pratte ◽  
L. E. Parent ◽  
M. A. Bolinder
Keyword(s):  
Time Series ◽  
Soil Temperature ◽  
Temperature Profile ◽  
Air Temperature ◽  
Soil Depth ◽  
Time Lag ◽  
Power Spectra ◽  
Temperature Time Series ◽  
Soil Temperatures ◽  
Temperature Time

Abstract. The objective of this work was to compare time and frequency fluctuations of air and soil temperatures (2-, 5-, 10-, 20- and 50-cm below the soil surface) using the continuous wavelet transform, with a particular emphasis on the daily cycle. The analysis of wavelet power spectra and cross power spectra provided detailed non-stationary accounts with respect to frequencies (or periods) and to time of the structure of the data and also of the relationships that exist between time series. For this particular application to the temperature profile of a soil exposed to frost, both the air temperature and the 2-cm depth soil temperature time series exhibited a dominant power peak at 1-d periodicity, prominent from spring to autumn. This feature was gradually damped as it propagated deeper into the soil and was weak for the 20-cm depth. Influence of the incoming solar radiation was also revealed in the wavelet power spectra analysis by a weaker intensity of the 1-d peak. The principal divergence between air and soil temperatures, besides damping, occurred in winter from the latent heat release associated to the freezing of the soil water and the insulation effect of snowpack that cease the dependence of the soil temperature to the air temperature. Attenuation and phase-shifting of the 1-d periodicity could be quantified through scale-averaged power spectra and time-lag estimations. Air temperature variance was only partly transferred to the 2-cm soil temperature time series and much less so to the 20-cm soil depth.

scholarly journals THE ANALYSIS OF SOIL TEMPERATURES IN DIFFERENT DEPTHS USING SPEARMAN’S RHO AND MANN-KENDALL CORRELATION TESTS: THE CASE STUDY OF NIGDE CENTER IN TURKEY

2020 ◽  
Vol 7 (5) ◽  
pp. 38-55
Author(s):  
M. Cüneyt Bagdatlı ◽  
Yiğitcan Ballı
Keyword(s):  
Soil Temperature ◽  
Soil Depth ◽  
Research Result ◽  
Significant Trend ◽  
Maximum Temperature ◽  
Average Maximum ◽  
Soil Temperatures ◽  
Average Maximum Temperature ◽  
Maximum Temperatures ◽  
Kendall Correlation

This research was conducted to determine soil temperatures in different soil depths in located Turkey’s Anatolia Region in Center of Nigde Province. In the study, the maximum, minimum and average soil temperature values of 10 cm, 50 cm and 100 cm depths observed between 1970-2019 were examined. All soil temperature data were evaluated monthly within the scope of the study. In the study, Mann-Kendall, Sperman's Rho correlation test and Sen's slope method were used.  According to the research result; The average of maximum soil temperatures in 10 cm depth was calculated as 6,8 0C in winter months and 20,7 0C in spring months. The average minimum soil temperature was calculated as 0,3 0C in winter and 5,0 0C in spring Months in long periods Generally, it was observed that there was an increasingly significant trend at maximum temperatures of 10 cm depth. According to the Mann-Kendal facility, a significant increase trend was observed in minimum soil temperatures in spring, winter and Summer months except for the months of autumn. Considering the average maximum temperature values in 50 cm; It was calculated as 6,6 °C in winter and 13,6 °C in spring months. The minimum soil temperature average was calculated as 3,5 0C in winter and 8,3 0C in spring months in long period (50 year, 600 months). In general, it was observed that there was an increasingly significant trend at maximum temperatures of 50 cm soil depth. According to Mann-Kendall and Sperman Rho test, a significant increase trend was observed in minimum soil temperatures in all seasons except for autumn months. According to the average maximum temperature values in 100 cm depth; It was calculated as 9,2 0C in winter and 11,5 0C in spring. The minimum soil temperature average was calculated as 7,1 0C in winter and 8.7 0C in spring months. It has been observed that there is a significant increase trend in the increasing of maximum and minimum soil temperatures of 100 cm soil depth.

scholarly journals HOW SOIL TEMPERATURE REGIMES CHANGE AS THE CLIMATE WARMS – SHORT COMMUNICATION

2020 ◽  
Vol 23 (1) ◽  
Author(s):  
Juha Karvonen ◽  
Keyword(s):  
Soil Temperature ◽  
Climate Warming ◽  
Short Communication ◽  
Soil Depth ◽  
Temperature Regimes ◽  
Soil Temperatures ◽  
Agricultural Use

Finnish soil temperature regimes have been pergelic, cryic, and frigid, where pergelic is coldest and unsuitable for agricultural use. The study monitored soil temperatures at a soil depth of 50 cm in 2010, 2013, 2016 and 2019 to look at how the soil temperature regimes have changed. Probably, as a result of climate warming the soil temperature regimes in Southern Finland in the Helsinki region at a latitude of 60–61°N have raised from cryic and pergelic to warmer mesic over a period of ten years.

Measurements and APSIM modelling of soil C and N dynamics

Soil Research ◽  
2020 ◽  
Vol 58 (1) ◽  
pp. 41
Author(s):  
C. J. Smith ◽  
B. C. T. Macdonald ◽  
H. Xing ◽  
O. T. Denmead ◽  
E. Wang ◽  
...  
Keyword(s):  
Soil Temperature ◽  
Soil Water ◽  
Soil Depth ◽  
Soil Evaporation ◽  
15N Balance ◽  
N Dynamics ◽  
Soil C ◽  
Ammonium N ◽  
Balance Technique ◽  
Using Data

Process-based models capture our understanding of key processes that interact to determine productivity and environmental outcomes. Combining measurements and modelling together help assess the consequences of these interactions, identify knowledge gaps and improve understanding of these processes. Here, we present a dataset (collected in a two-month fallow period) and list potential issues related to use of the APSIM model in predicting fluxes of soil water, heat, nitrogen (N) and carbon (C). Within the APSIM framework, two soil water modules (SoilWat and SWIM3) were used to predict soil evaporation and soil moisture content. SWIM3 tended to overestimate soil evaporation immediately after rainfall events, and SoilWat provided better predictions of evaporation. Our results highlight the need for testing the modules using data that includes wetting and drying cycles. Two soil temperature modules were also evaluated. Predictions of soil temperature were better for SoilTemp than the default module. APSIM configured with different combinations of soil water and temperature modules predicted nitrate dynamics well, but poorly predicted ammonium-N dynamics. The predicted ammonium-N pool empties several weeks after fertilisation, which was not observed, indicating that the processes of mineralisation and nitrification in APSIM require improvements. The fluxes of soil respiration and nitrous oxide, measured by chamber and micrometeorological methods, were roughly captured by APSIM. Discrepancies between the fluxes measured with chamber and micrometeorological techniques highlight difficulties in obtaining accurate measurements for evaluating performance of APSIM to predict gaseous fluxes. There was uncertainty associated with soil depth, which contributed to surface emissions. Our results showed that APSIM performance in simulating N2O fluxes should be considered in relation to data precision and uncertainty, especially the soil depths included in simulations. Finally, there was a major disconnection between the predicted N loss from denitrification (N2 + N2O) and that measured using the 15N balance technique.

A weighted coefficient model for estimation of Australian daily soil temperature at depths of 5cm to 100cm based on air temperature and rainfall

Soil Research ◽  
2011 ◽  
Vol 49 (4) ◽  
pp. 305 ◽  
Author(s):  
Brian Horton ◽  
Ross Corkrey
Keyword(s):  
Soil Temperature ◽  
Air Temperature ◽  
Cross Validation ◽  
Soil Depth ◽  
Mean Square ◽  
Air Temperatures ◽  
Proposed Model ◽  
Soil Temperatures ◽  
Weather Stations ◽  
Fold Cross Validation

Soil temperatures are related to air temperature and rainfall on the current day and preceding days, and this can be expressed in a non-linear relationship to provide a weighted value for the effect of air temperature or rainfall based on days lag and soil depth. The weighted minimum and maximum air temperatures and weighted rainfall can then be combined with latitude and a seasonal function to estimate soil temperature at any depth in the range 5–100 cm. The model had a root mean square deviation of 1.21–1.85°C for minimum, average, and maximum soil temperature for all weather stations in Australia (mainland and Tasmania), except for maximum soil temperature at 5 and 10 cm, where the model was less precise (3.39° and 2.52°, respectively). Data for this analysis were obtained from 32–40 Bureau of Meteorology weather stations throughout Australia and the proposed model was validated using 5-fold cross-validation.

Artificial neural network model for estimating the soil temperature

2011 ◽  
Vol 91 (4) ◽  
pp. 551-562 ◽  
Author(s):  
Murat Ozturk ◽  
Ozlem Salman ◽  
Murat Koc
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Soil Temperature ◽  
Network Model ◽  
Neural Network Model ◽  
Artificial Neural Network Model ◽  
Soil Depth ◽  
Sunshine Duration ◽  
Artificial Neural ◽  
Monitoring Stations

Ozturk, M., Salman, O. and Koc, M. 2011. Artificial neural network model for estimating the soil temperature. Can. J. Soil Sci. 91: 551–562. Although soil temperature is a critically important agricultural and environmental factor, it is typically monitored with low spatial resolution and, as a result, methods are required to estimate soil temperature at locations remote from monitoring stations. In this study, cost-effective, feed-forward artificial neural network (ANN) models are developed and tested for estimating soil temperature at 5-, 10-, 20-, 50- and 100-cm depths using standard geographical and meteorological data (i.e., altitude, latitude, longitude, month, year, monthly solar radiation, monthly sunshine duration and monthly mean air temperature). These data plus measured monthly mean soil temperature were collected for 2006–2008 from 66 monitoring stations distributed throughout Turkey to obtain a total of 2376 data records (36 months×66 monitoring stations) for each of the five soil depths. At each soil depth, 1800 randomly selected data records were used to develop and train a separate ANN model, and the remaining 576 records at each depth were used to test and validate the resulting models. Good agreement was obtained between ANN-estimated soil temperature and measured soil temperature, as evidenced by correlation coefficients of 98.91, 97.99, 99.03, 98.26 and 95.37% for the 5-, 10-, 20-, 50- and 100-cm soil depths, respectively. It was concluded that ANN modeling is a reliable method for predicting monthly mean soil temperature in regions of Turkey where soil temperature monitoring stations are not present.

Sign in / Sign up

Export Citation Format

Share Document