scholarly journals A Data-Driven Method for the Temporal Estimation of Soil Water Potential and Its Application for Shallow Landslides Prediction

Water ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1208
Author(s):  
Massimiliano Bordoni ◽  
Fabrizio Inzaghi ◽  
Valerio Vivaldi ◽  
Roberto Valentino ◽  
Marco Bittelli ◽  
...  
Keyword(s):  
Machine Learning ◽  
Water Potential ◽  
Soil Water ◽  
Temporal Trends ◽  
Soil Water Potential ◽  
Shallow Landslides ◽  
Water Dynamics ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Physically Based

Soil water potential is a key factor to study water dynamics in soil and for estimating the occurrence of natural hazards, as landslides. This parameter can be measured in field or estimated through physically-based models, limited by the availability of effective input soil properties and preliminary calibrations. Data-driven models, based on machine learning techniques, could overcome these gaps. The aim of this paper is then to develop an innovative machine learning methodology to assess soil water potential trends and to implement them in models to predict shallow landslides. Monitoring data since 2012 from test-sites slopes in Oltrepò Pavese (northern Italy) were used to build the models. Within the tested techniques, Random Forest models allowed an outstanding reconstruction of measured soil water potential temporal trends. Each model is sensitive to meteorological and hydrological characteristics according to soil depths and features. Reliability of the proposed models was confirmed by correct estimation of days when shallow landslides were triggered in the study areas in December 2020, after implementing the modeled trends on a slope stability model, and by the correct choice of physically-based rainfall thresholds. These results confirm the potential application of the developed methodology to estimate hydrological scenarios that could be used for decision-making purposes.

Soil water dynamics in forested and irrigated sites in Cyprus 

2021 ◽  
Author(s):  
Marinos Eliades ◽  
Adriana Bruggeman ◽  
Hakan Djuma ◽  
Melpomeni Siakou ◽  
Panagiota Venetsanou ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Water Potential ◽  
Soil Water ◽  
Water Flow ◽  
Water Retention ◽  
Soil Depth ◽  
Soil Water Potential ◽  
Water Dynamics ◽  
Annual Rainfall ◽  
Irrigation Amount

<p>The water storage in soil is a dynamic process that changes with soil, vegetation and climate properties. Water retention curves, that describe the relationship between the soil water content (θ) and the soil water potential (ψ), are used to model soil water flow and root water uptake by the plants. The overall objective of this study is to derive the retention curves of soils at two forested (Agia Marina, Platania) and two irrigated (Galata, Strakka) sites in Cyprus from in-situ soil moisture and soil water potential observations. <br>The long-term (1980 – 2010) average annual rainfall at Strakka olive grove (255 m elevation), Agia Marina P. brutia forest (640 m), Galata peach orchard (784 m) and Platania P. brutia forest (1160 m) is 298, 425, 502 and 839 mm, respectively.  The average soil depth at Agia Marina is 14 cm, while at other sites it is around 1 m. We installed a total of 18 TEROS21 soil water potential sensors, 37 5TM and 19 SMT100 soil moisture sensors, at different soil depths at the four sites. <br>Results from January 2019 to January 2021 show differences in the water retention curves of the four sites due to different soil textures. At the forested sites, θ reached wilting point at the summer period, indicating that trees extend their roots beyond the soil profile, to the bedrock in order to survive. At the irrigated sites, θ exceeds field capacity during irrigation, indicating over-irrigation. We found different water retention relations after rainfall and after irrigation, indicating that irrigation has an uneven spatial distribution. These findings suggest that the irrigation in these fields is not optimal and farmers may need to increase the number of irrigation drippers, while reducing the irrigation amount per dripper. From a monitoring perspective, increasing the number of sensors may give a better representation of the soil moisture conditions. <br>The research has received financial support from the ERANETMED3 program, as part of the ISOMED project (Environmental Isotope Techniques for Water Flow Accounting), funded through the Cyprus Research and Innovation Foundation.</p>

scholarly journals A framework for accurate geospatial modeling using image ranking and machine learning

2010 ◽  
Vol 13 (3) ◽  
pp. 443-460
Author(s):  
Peter Bajcsy ◽  
Yu-Feng Lin ◽  
Alex Yahja ◽  
Chulyun Kim
Keyword(s):  
Machine Learning ◽  
Visual Exploration ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Computer Assisted ◽  
Geospatial Modeling ◽  
Learning Techniques ◽  
Physically Based ◽  
Using Data ◽  
High Level

There is a large class of modeling problems where the complexity of the underlying phenomena is overwhelming and hence the accuracy of mathematical models is limited. Our approach to this class of problems is to design frameworks that bring together physically based and data-driven models, and incorporate the tacit knowledge of experts by providing visual exploration and feedback capabilities. This paper presents such a novel computer-assisted framework for accurate geospatial modeling applied to improve groundwater recharge and discharge (R/D) patterns. The novelty of our work is in designing a methodology for ranking and extracting relationships, as well as in developing a general framework for building accurate geospatial models. The framework combines variables derived using physically based inverse modeling with auxiliary geospatial variables directly sensed, ranks variables and extracts variable relationships using data-driven (“machine learning”) techniques, and supports partially expert-driven trial-and-error experimentation and more rigorous optimization, as well as visual explorations, to derive more accurate models for R/D pattern estimation. When the framework was tested by experts, it led to a high level of consistency between the machine-learning-based knowledge and the experts' knowledge about R/D distribution. The prototype solution of the framework is available for downloading at http://isda.ncsa.uiuc.edu/Sp2Learn/.

scholarly journals Horizontal soil water potential heterogeneity: simplifying approaches for crop water dynamics models

2014 ◽  
Vol 11 (1) ◽  
pp. 1203-1252 ◽  
Author(s):  
V. Couvreur ◽  
J. Vanderborght ◽  
L. Beff ◽  
M. Javaux
Keyword(s):  
Analytical Solution ◽  
Winter Wheat ◽  
Water Potential ◽  
Soil Water ◽  
Soil Water Potential ◽  
Water Dynamics ◽  
Implicit Assumption ◽  
Plant Water ◽  
Row Crops ◽  
D Model

Abstract. Soil water potential (SWP) is known to affect plant water status, and even though observations demonstrate that SWP distribution around roots may limit plant water availability, its horizontal heterogeneity within the root zone is often neglected in hydrological models. As motive, using a horizontal discretisation significantly larger than one centimetre is often essential for computing time considerations, especially for large scale hydrodynamics models. In this paper, we simulate soil and root system hydrodynamics at the centimetre scale and evaluate approaches to upscale variables and parameters related to root water uptake (RWU) for two crop systems: a densely seeded crop with an average uniform distribution of roots in the horizontal direction (winter wheat) and a wide-row crop with lateral variations in root density (maize). In a first approach, the upscaled water potential at soil–root interfaces was assumed to equal the bulk SWP of the upscaled soil element. Using this assumption, the 3-D high resolution model could be accurately upscaled to a 2-D model for maize and a 1-D model for wheat. The accuracy of the upscaled models generally increased with soil hydraulic conductivity, lateral homogeneity of root distribution, and low transpiration rate. The link between horizontal upscaling and an implicit assumption on soil water redistribution was demonstrated in quantitative terms, and explained upscaling accuracy. In a second approach, the soil–root interface water potential was estimated by using a constant rate analytical solution of the axisymmetric soil water flow towards individual roots. In addition to the theoretical model properties, effective properties were tested in order to account for unfulfilled assumptions of the analytical solution: non-uniform lateral root distributions and transient RWU rates. Significant improvements were however only noticed for winter wheat, for which the first approach was already satisfying. This study confirms that the use of 1-D spatial discretisation to represent soil-plant water dynamics is a worthy choice for densely seeded crops. For wide-row crops, e.g. maize, further theoretical developments that better account for horizontal SWP heterogeneity might be needed in order to properly predict soil-plant hydrodynamics in 1-D.

scholarly journals Horizontal soil water potential heterogeneity: simplifying approaches for crop water dynamics models

2014 ◽  
Vol 18 (5) ◽  
pp. 1723-1743 ◽  
Author(s):  
V. Couvreur ◽  
J. Vanderborght ◽  
L. Beff ◽  
M. Javaux
Keyword(s):  
Analytical Solution ◽  
Winter Wheat ◽  
Water Potential ◽  
Soil Water ◽  
Soil Water Potential ◽  
Water Dynamics ◽  
Implicit Assumption ◽  
Plant Water ◽  
Row Crops ◽  
D Model

Abstract. Soil water potential (SWP) is known to affect plant water status, and even though observations demonstrate that SWP distribution around roots may limit plant water availability, its horizontal heterogeneity within the root zone is often neglected in hydrological models. As motive, using a horizontal discretisation significantly larger than one centimetre is often essential for computing time considerations, especially for large-scale hydrodynamics models. In this paper, we simulate soil and root system hydrodynamics at the centimetre scale and evaluate approaches to upscale variables and parameters related to root water uptake (RWU) for two crop systems: a densely seeded crop with an average uniform distribution of roots in the horizontal direction (winter wheat) and a wide-row crop with lateral variations in root density (maize). In a first approach, the upscaled water potential at soil–root interfaces was assumed to equal the bulk SWP of the upscaled soil element. Using this assumption, the 3-D high-resolution model could be accurately upscaled to a 2-D model for maize and a 1-D model for wheat. The accuracy of the upscaled models generally increased with soil hydraulic conductivity, lateral homogeneity of root distribution, and low transpiration rate. The link between horizontal upscaling and an implicit assumption on soil water redistribution was demonstrated in quantitative terms, and explained upscaling accuracy. In a second approach, the soil–root interface water potential was estimated by using a constant rate analytical solution of the axisymmetric soil water flow towards individual roots. In addition to the theoretical model properties, effective properties were tested in order to account for unfulfilled assumptions of the analytical solution: non-uniform lateral root distributions and transient RWU rates. Significant improvements were however only noticed for winter wheat, for which the first approach was already satisfying. This study confirms that the use of 1-D spatial discretisation to represent soil–plant water dynamics is a worthy choice for densely seeded crops. For wide-row crops, e.g. maize, further theoretical developments that better account for horizontal SWP heterogeneity might be needed in order to properly predict soil–plant hydrodynamics in 1-D.

Effect of Soil Water Potential of Two Soils on Soybean Emergence 1

1979 ◽  
Vol 71 (6) ◽  
pp. 980-982 ◽  
Author(s):  
L. G. Heatherly ◽  
W. J. Russell
Keyword(s):  
Water Potential ◽  
Soil Water ◽  
Soil Water Potential

NITROGEN TRANSFORMATIONS NEAR UREA IN SOIL WITH DIFFERENT WATER POTENTIALS

1988 ◽  
Vol 68 (3) ◽  
pp. 569-576 ◽  
Author(s):  
YADVINDER SINGH ◽  
E. G. BEAUCHAMP
Keyword(s):  
Water Potential ◽  
Soil Water ◽  
Incubation Period ◽  
Relative Rate ◽  
Soil Water Potential ◽  
Nitrification Inhibitor ◽  
Silt Loam ◽  
Nitrogen Transformations ◽  
Water Potentials ◽  
Initial Soil

Two laboratory incubation experiments were conducted to determine the effect of initial soil water potential on the transformation of urea in large granules to nitrite and nitrate. In the first experiment two soils varying in initial soil water potentials (− 70 and − 140 kPa) were incubated with 2 g urea granules with and without a nitrification inhibitor (dicyandiamide) at 15 °C for 35 d. Only a trace of [Formula: see text] accumulated in a Brookston clay (pH 6.0) during the transformation of urea in 2 g granules. Accumulation of [Formula: see text] was also small (4–6 μg N g−1) in Conestogo silt loam (pH 7.6). Incorporation of dicyandiamide (DCD) into the urea granule at 50 g kg−1 urea significantly reduced the accumulation of [Formula: see text] in this soil. The relative rate of nitrification in the absence of DCD at −140 kPa water potential was 63.5% of that at −70 kPa (average of two soils). DCD reduced the nitrification of urea in 2 g granules by 85% during the 35-d period. In the second experiment a uniform layer of 2 g urea was placed in the center of 20-cm-long cores of Conestogo silt loam with three initial water potentials (−35, −60 and −120 kPa) and the soil was incubated at 15 °C for 45 d. The rate of urea hydrolysis was lowest at −120 kPa and greatest at −35 kPa. Soil pH in the vicinity of the urea layer increased from 7.6 to 9.1 and [Formula: see text] concentration was greater than 3000 μg g−1 soil. There were no significant differences in pH or [Formula: see text] concentration with the three soil water potential treatments at the 10th day of the incubation period. But, in the latter part of the incubation period, pH and [Formula: see text] concentration decreased with increasing soil water potential due to a higher rate of nitrification. Diffusion of various N species including [Formula: see text] was probably greater with the highest water potential treatment. Only small quantities of [Formula: see text] accumulated during nitrification of urea – N. Nitrification of urea increased with increasing water potential. After 35 d of incubation, 19.3, 15.4 and 8.9% of the applied urea had apparently nitrified at −35, −60 and −120 kPa, respectively. Nitrifier activity was completely inhibited in the 0- to 2-cm zone near the urea layer for 35 days. Nitrifier activity increased from an initial level of 8.5 to 73 μg [Formula: see text] in the 3- to 7-cm zone over the 35-d period. Nitrifier activity also increased with increasing soil water potential. Key words: Urea transformation, nitrification, water potential, large granules, nitrifier activity, [Formula: see text] production

Sign in / Sign up

Export Citation Format

Share Document