scholarly journals A comparison of numerical and machine-learning modeling of soil water content with limited input data

2016 ◽  
Vol 543 ◽  
pp. 892-909 ◽  
Author(s):  
Fatemeh Karandish ◽  
Jiří Šimůnek
Keyword(s):  
Machine Learning ◽  
Water Content ◽  
Soil Water ◽  
Soil Water Content ◽  
Input Data ◽  
Limited Input Data

scholarly journals The use of machine learning algorithms to design a generalized simplified denitrification model

2010 ◽  
Vol 7 (10) ◽  
pp. 3311-3332 ◽  
Author(s):  
F. Oehler ◽  
J. C. Rutherford ◽  
G. Coco
Keyword(s):  
Machine Learning ◽  
Water Content ◽  
Soil Water ◽  
Soil Water Content ◽  
Nitrate Concentration ◽  
Machine Learning Algorithms ◽  
Boosted Regression Trees ◽  
Simplified Model ◽  
Nitrogen Emissions ◽  
Denitrification Potential

Abstract. We propose to use machine learning (ML) algorithms to design a simplified denitrification model. Boosted regression trees (BRT) and artificial neural networks (ANN) were used to analyse the relationships and the relative influences of different input variables towards total denitrification, and an ANN was designed as a simplified model to simulate total nitrogen emissions from the denitrification process. To calibrate the BRT and ANN models and test this method, we used a database obtained collating datasets from the literature. We used bootstrapping to compute confidence intervals for the calibration and validation process. Both ML algorithms clearly outperformed a commonly used simplified model of nitrogen emissions, NEMIS, which is based on denitrification potential, temperature, soil water content and nitrate concentration. The ML models used soil organic matter % in place of a denitrification potential and pH as a fifth input variable. The BRT analysis reaffirms the importance of temperature, soil water content and nitrate concentration. Generalization, although limited to the data space of the database used to build the ML models, could be improved if pH is used to differentiate between soil types. Further improvements in model performance and generalization could be achieved by adding more data.

scholarly journals The use of machine learning algorithms to design a generalized simplified denitrification model

2010 ◽  
Vol 7 (2) ◽  
pp. 2313-2360 ◽  
Author(s):  
F. Oehler ◽  
J. C. Rutherford ◽  
G. Coco
Keyword(s):  
Machine Learning ◽  
Water Content ◽  
Soil Water ◽  
Soil Water Content ◽  
Nitrate Concentration ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Boosted Regression Trees ◽  
Nitrogen Emissions ◽  
Denitrification Potential

Abstract. We designed generalized simplified models using machine learning algorithms (ML) to assess denitrification at the catchment scale. In particular, we designed an artificial neural network (ANN) to simulate total nitrogen emissions from the denitrification process. Boosted regression trees (BRT, another ML) was also used to analyse the relationships and the relative influences of different input variables towards total denitrification. To calibrate the ANN and BRT models, we used a large database obtained by collating datasets from the literature. We developed a simple methodology to give confidence intervals for the calibration and validation process. Both ML algorithms clearly outperformed a commonly used simplified model of nitrogen emissions, NEMIS. NEMIS is based on denitrification potential, temperature, soil water content and nitrate concentration. The ML models used soil organic matter % in place of a denitrification potential and pH as a fifth input variable. The BRT analysis reaffirms the importance of temperature, soil water content and nitrate concentration. Generality of the ANN model may also be improved if pH is used to differentiate between soil types. Further improvements in model performance can be achieved by lessening dataset effects.

SOIL WATER CONTENT AFFECTS THE AVAILABILITY OF PHOSPHATE

1985 ◽  
pp. 185-189
Author(s):  
M.C.H.Mouat Pieter Nes
Keyword(s):  
Water Content ◽  
Soil Water ◽  
Soil Water Content ◽  
Soil Solution ◽  
Equivalent Reduction

Reduction in water content of a soil increased the concentration of ammonium and nitrate in solution, but had no effect on the concentration of phosphate. The corresponding reduction in the quantity of phosphate in solution caused an equivalent reduction in the response of ryegrass to applied phosphate. Keywords: soil solution, soil water content, phosphate, ryegrass, nutrition.

Effect of inter-row cultivation on soil carbon dioxide emission in a peach plantation

2010 ◽  
Vol 59 (1) ◽  
pp. 157-164 ◽  
Author(s):  
E. Tóth ◽  
Cs. Farkas
Keyword(s):  
Water Content ◽  
Soil Water ◽  
Soil Water Content ◽  
Carbon Dioxide Emission ◽  
Nutrient Content ◽  
Soil Disturbance ◽  
Biological Properties ◽  
Soil Tillage ◽  
Favourable Effect ◽  
Volumetric Soil Water Content

Soil biological properties and CO2emission were compared in undisturbed grass and regularly disked rows of a peach plantation. Higher nutrient content and biological activity were found in the undisturbed, grass-covered rows. Significantly higher CO2fluxes were measured in this treatment at almost all the measurement times, in all the soil water content ranges, except the one in which the volumetric soil water content was higher than 45%. The obtained results indicated that in addition to the favourable effect of soil tillage on soil aeration, regular soil disturbance reduces soil microbial activity and soil CO2emission.

Evaluation of a Multi-Rod Probe Performance for Accurate Measurements of Soil Water Content

2020 ◽  
Author(s):  
Justyna Szerement ◽  
Aleksandra Woszczyk ◽  
Agnieszka Szyplowska ◽  
Marcin Kafarski ◽  
Arkadiusz Lewandowski ◽  
...  
Keyword(s):  
Water Content ◽  
Soil Water ◽  
Soil Water Content

Effects of soil water content and temperature on Bt protein degradation in leaves at thinning stage and buds of Bt cotton

2014 ◽  
Vol 22 (3) ◽  
pp. 300-307
Author(s):  
Meijun ZHANG ◽  
Wude YANG ◽  
Meichen FENG ◽  
Yun DUAN ◽  
Mingming TANG ◽  
...  
Keyword(s):  
Protein Degradation ◽  
Water Content ◽  
Soil Water ◽  
Soil Water Content ◽  
Bt Cotton ◽  
Bt Protein

Evapotranspiration Measurement and Irrigation Scheduling for Several Tropical Fruit Crops Using the EnviroScan System

HortScience ◽  
1998 ◽  
Vol 33 (3) ◽  
pp. 549f-550
Author(s):  
Mongi Zekri ◽  
Bruce Schaffer ◽  
Stephen K. O'Hair ◽  
Roberto Nunez-Elisea ◽  
Jonathan H. Crane
Keyword(s):  
Water Content ◽  
Soil Water ◽  
Soil Water Content ◽  
Water Use ◽  
National Parks ◽  
Quantitative Information ◽  
Irrigation Scheduling ◽  
Management Tool ◽  
Fruit Crops ◽  
Tropical Fruit

In southern Florida, most tropical fruit crops between Biscayne and Everglades National Parks are irrigated at rates and frequencies based on experience and observations of tree growth and fruit yield rather than on reliable quantitative information of actual water use. This approach suggests that irrigation rates may be excessive and could lead to leaching of agricultural chemicals into the groundwater in this environmentally sensitive area. Therefore, a study is being conducted to increase water use efficiency and optimize irrigation by accurately scheduling irrigation using a very effective management tool (EnviroScan, Sentek Environmental Innovations, Pty., Kent, Australia) that continuously monitors soil water content with highly accurate capacitance multi-sensor probes installed at several depths within the soil profile. The system measures crop water use by monitoring soil water depletion rates and allows the maintenance of soil water content within the optimum range (below field capacity and well above the onset of plant water stress). The study is being conducted in growers' orchards with three tropical fruit crops (avocado, carambola, and `Tahiti' lime) to facilitate rapid adoption and utilization of research results.

Sign in / Sign up

Export Citation Format

Share Document