scholarly journals Application of artificial neural networks to estimate soil organic carbon in a high-organic-matter Mollisol

2017 ◽  
Vol 7 ◽  
Author(s):  
Rocío Moreno ◽  
Andrea Inés Irigoyen ◽  
María Gloria Monterubbianesi ◽  
Guillermo Alberto Studdert
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Crop Yields ◽  
Categorical Variables ◽  
Buenos Aires Province ◽  
Organic C ◽  
C Cycle ◽  
Artificial Neural

Soil organic carbon (SOC) has a key role in the global carbon (C) cycle. The complex relationships among the components of C cycle makes difficult the modelling of SOC variation. Artificial neural networks (ANN) are models capable to determine interrelationships based on information. The objective was to develop and evaluate models based on the ANN technique to estimate the SOC in Mollisols of the Southeastern of Buenos Aires Province, Argentina (SEBA). Data from three long term experiments was used. Management and meteorological variables were selected as input. Management information included numerical variables (initial SOC (SOCI); number of years from the beginning of the experiment (Year), proportion of soybean in the crop sequence; (Prop soybean); crop yields (Yield), proportion of cropping in the crop rotation (Prop agri), and categorical variables (Crop, Tillage). In addition, two meteorological inputs (minimum (Tmin) and mean air temperature (Tmed)), were selected. The ANNs were adequate to estimate SOC in the upper 0.20 m of Mollisols of the SEBA. The model with the best performance included six management variables (SOCI, Year, Prop soybean, Tillage, Yield, Prop agri) and one meteorological variable (Tmin), all of them easily available and with low level of uncertainty. Soil organic C changes related to soil use in the SEBA could be satisfactorily estimated using an ANN developed with simple and easily available input variables. Artificial neural network technique appears as a valuable tool to develop robust models to help predicting SOC changes.

Estimating soil organic carbon of sown biodiverse permanent pastures in Portugal using near infrared spectral data and artificial neural networks

Geoderma ◽  
2021 ◽  
Vol 404 ◽  
pp. 115387
Author(s):  
Tiago G. Morais ◽  
Camila Tufik ◽  
Ana E. Rato ◽  
Nuno R. Rodrigues ◽  
Ivo Gama ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Spectral Data ◽  
Near Infrared ◽  
Infrared Spectral ◽  
Artificial Neural

Long-term effects of fertilisers and organic sources on soil organic carbon fractions under a rice–wheat system in the Indo-Gangetic Plains of north-west India

Soil Research ◽  
2017 ◽  
Vol 55 (3) ◽  
pp. 296 ◽  
Author(s):  
D. Das ◽  
B. S. Dwivedi ◽  
V. K. Singh ◽  
S. P. Datta ◽  
M. C. Meena ◽  
...  
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Crop Yields ◽  
Soil Depth ◽  
Farmyard Manure ◽  
Microbial Biomass C ◽  
Gangetic Plain ◽  
Organic C ◽  
Labile C ◽  
Labile C Fractions

Decline in soil organic carbon (SOC) content is considered a key constraint for sustenance of rice–wheat system (RWS) productivity in the Indo-Gangetic Plain region. We, therefore, studied the effects of fertilisers and manures on SOC pools, and their relationships with crop yields after 18 years of continuous RWS. Total organic C increased significantly with the integrated use of fertilisers and organic sources (from 13 to 16.03gkg–1) compared with unfertilised control (11.5gkg–1) or sole fertiliser (NPKZn; 12.17gkg–1) treatment at 0–7.5cm soil depth. Averaged across soil depths, labile fractions like microbial biomass C (MBC) and permanganate-oxidisable C (PmOC) were generally higher in treatments that received farmyard manure (FYM), sulfitation pressmud (SPM) or green gram residue (GR) along with NPK fertiliser, ranging from 192 to 276mgkg–1 and from 0.60 to 0.75gkg–1 respectively compared with NPKZn and NPK+cereal residue (CR) treatments, in which MBC and PmOC ranged from 118 to 170mgkg–1 and from 0.43 to 0.57gkg–1 respectively. Oxidisable organic C fractions revealed that very labile C and labile C fractions were much larger in the NPK+FYM or NPK+GR+FYM treatments, whereas the less-labile C and non-labile C fractions were larger under control and NPK+CR treatments. On average, Walkley–Black C, PmOC and MBC contributed 29–46%, 4.7–6.6% and 1.16–2.40% towards TOC respectively. Integrated plant nutrient supply options, except NPK+CR, also produced sustainable high yields of RWS.

scholarly journals Soil organic carbon stabilization mechanisms and temperature sensitivity in old terraced soils

2021 ◽  
Vol 18 (23) ◽  
pp. 6301-6312
Author(s):  
Pengzhi Zhao ◽  
Daniel Joseph Fallu ◽  
Sara Cucchiaro ◽  
Paolo Tarolli ◽  
Clive Waddington ◽  
...  
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Temperature Sensitivity ◽  
Land Surface ◽  
C:N Ratio ◽  
Temperature Sensitive ◽  
Organic C ◽  
Fraction Composition ◽  
Soil Burial ◽  
C Cycle

Abstract. Being the most common human-created landforms, terrace construction has resulted in an extensive perturbation of the land surface. However, our mechanistic understanding of soil organic carbon (SOC) (de-)stabilization mechanisms and the persistence of SOC stored in terraced soils is far from complete. Here we explored the factors controlling SOC stability and the temperature sensitivity (Q10) of abandoned prehistoric agricultural terrace soils in NE England using soil fractionation and temperature-sensitive incubation combined with terrace soil burial-age measurements. Results showed that although buried terrace soils contained 1.7 times more unprotected SOC (i.e., coarse particulate organic carbon) than non-terraced soils at comparable soil depths, a significantly lower potential soil respiration was observed relative to a control (non-terraced) profile. This suggests that the burial of former topsoil due to terracing provided a mechanism for stabilizing SOC. Furthermore, we observed a shift in SOC fraction composition from particulate organic C towards mineral-protected C with increasing burial age. This clear shift to more processed recalcitrant SOC with soil burial age also contributes to SOC stability in terraced soils. Temperature sensitivity incubations revealed that the dominant controls on Q10 depend on the terrace soil burial age. At relatively younger ages of soil burial, the reduction in substrate availability due to SOC mineral protection with aging attenuates the intrinsic Q10 of SOC decomposition. However, as terrace soil becomes older, SOC stocks in deep buried horizons are characterized by a higher temperature sensitivity, potentially resulting from the poor SOC quality (i.e., soil C:N ratio). In conclusion, terracing in our study site has stabilized SOC as a result of soil burial during terrace construction. The depth–age patterns of Q10 and SOC fraction composition of terraced soils observed in our study site differ from those seen in non-terraced soils, and this has implications when assessing the effects of climate warming and terrace abandonment on the terrestrial C cycle.

Generation of Optimal Artificial Neural Networks Using a Pattern Search Algorithm: Application to Approximation of Chemical Systems

2008 ◽  
Vol 20 (2) ◽  
pp. 573-601 ◽  
Author(s):  
Matthias Ihme ◽  
Alison L. Marsden ◽  
Heinz Pitsch
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Source Term ◽  
Transfer Functions ◽  
Search Algorithm ◽  
Optimization Method ◽  
Pattern Search ◽  
Memory Storage ◽  
Categorical Variables ◽  
Artificial Neural

A pattern search optimization method is applied to the generation of optimal artificial neural networks (ANNs). Optimization is performed using a mixed variable extension to the generalized pattern search method. This method offers the advantage that categorical variables, such as neural transfer functions and nodal connectivities, can be used as parameters in optimization. When used together with a surrogate, the resulting algorithm is highly efficient for expensive objective functions. Results demonstrate the effectiveness of this method in optimizing an ANN for the number of neurons, the type of transfer function, and the connectivity among neurons. The optimization method is applied to a chemistry approximation of practical relevance. In this application, temperature and a chemical source term are approximated as functions of two independent parameters using optimal ANNs. Comparison of the performance of optimal ANNs with conventional tabulation methods demonstrates equivalent accuracy by considerable savings in memory storage. The architecture of the optimal ANN for the approximation of the chemical source term consists of a fully connected feedforward network having four nonlinear hidden layers and 117 synaptic weights. An equivalent representation of the chemical source term using tabulation techniques would require a 500 × 500 grid point discretization of the parameter space.

scholarly journals ASSESSING ALTERNATIVES TO ESTIMATE THE STEM VOLUME OF A SEASONAL SEMI-DECIDUOUS FOREST

FLORESTA ◽  
2017 ◽  
Vol 47 (4) ◽  
pp. 375
Author(s):  
Jadson Coelho De Abreu ◽  
Carlos Pedro Boechat Soares ◽  
Helio Garcia Leite
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Support Vector Machines ◽  
Linear Models ◽  
Deciduous Forest ◽  
Stem Volume ◽  
Categorical Variables ◽  
Support Vector ◽  
Vector Machines ◽  
Artificial Neural

AbstractThe objective of this study was to evaluate the use of linear and hybrid linear models, artificial neural networks (ANN) and support vector machine (SVM) in the estimation of the stem volume in a Seasonal Semi-deciduous Forest. Cubing data of 99 sample-trees of 15 species were used for this purpose. After analysis, we verified that the inclusion of the species as random effect did not contribute to increase the accuracy of the estimates in the structure of a hybrid model. Artificial neural networks and support vector machines, including species as input categorical variables, were the best alternatives to estimate the stem volume of trees of the Seasonal Semi-deciduous Forest.Keywords: Stem volume; artificial neural networks; support vector machines; hybrid linear models; uneven-aged forest. ResumoAvaliando alternativas para estimar o volume do fuste de uma Floresta Estacional Semidecidual. O objetivo desse estudo foi   avaliar o uso de modelos lineares e lineares mistos, redes neurais   artificiais (RNA) e máquina de vetor de suporte (MVS) na estimação dos   volumes dos fustes de árvores em uma Floresta Estacional Semidecidual. Dados de cubagem de 99 árvores-amostra   de 15 espécies foram utilizados para esta finalidade. Após análises, verificou-se que   a inclusão das espécies como efeito aleatório não contribuiu para aumentar a   exatidão das estimativas na estrutura de um modelo misto. As redes neurais artificiais e   as máquinas de vetores de suporte, incluindo as espécies como variáveis   categóricas de entrada, foram as melhores alternativas para estimar o volume   dos fustes das árvores da Floresta Estacional Semidecidual.Palavras-chaves: Volume do   fuste; redes neurais artificiais; máquinas de vetor de suporte; modelos   lineares mistos; floresta inequiânea. 

Novel Empirical Correlation for Estimation of the Total Organic Carbon in Devonian Shale from the Spectral Gamma-Ray and Based on the Artificial Neural Networks

2021 ◽  
pp. 1-28
Author(s):  
Ahmed Abdulhamid Mahmoud ◽  
Salaheldin Elkatatny
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Organic Carbon ◽  
Total Organic Carbon ◽  
Gamma Ray ◽  
Linear Regression Analysis ◽  
Empirical Correlation ◽  
Training Data ◽  
Validation Data ◽  
Artificial Neural

Abstract Evaluation of the quality of unconventional hydrocarbon resources becomes a critical stage toward characterizing these resources, this evaluation requires evaluation of the total organic carbon (TOC). Generally, TOC is determined from laboratory experiments, however, it is hard to obtain a continuous profile for the TOC along the drilled formations using these experiments. Another way to evaluate the TOC is through the use of empirical correlation, the currently available correlations lack the accuracy especially when used in formations other than the ones used to develop these correlations. This study introduces an empirical equation for evaluation of the TOC in Devonian Duvernay shale from only gamma-ray and spectral gamma-ray logs of uranium, thorium, and potassium as well as a newly developed term that accounts for the TOC from the linear regression analysis. This new correlation was developed based on the artificial neural networks (ANN) algorithm which was learned on 750 datasets from Well-A. The developed correlation was tested and validated on 226 and 73 datasets from Well-B and Well-C, respectively. The results of this study indicated that for the training data, the TOC was predicted by the ANN with an AAPE of only 8.5%. Using the developed equation, the TOC was predicted with an AAPE of only 11.5% for the testing data. For the validation data, the developed equation overperformed the previous models in estimating the TOC with an AAPE of only 11.9%.

Sign in / Sign up

Export Citation Format

Share Document