Predicting Soil Particulate Organic Mattter Using Artificial Neural Network with Wavelet Function

Baligh, Paria; Honarjoo, Naser; Totonchi, Arash; Jalalian, Ahmad

doi:10.1080/00103624.2020.1808012

Cited by 5 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN, analog to the biological neural network, is more complex and uses synaptic weights to establish a connection among predictor variables through multiple layers of networks and predicts the classification (Grunwald, 2022). Some of the features of the neural network such as no assumption of a prior relationship, availability of multiple training algorithm detections of complex nonlinear relationships, and detection of all possible interactions between predictor variables (Tu, 1996), made it another popular soil classification model (Alvarez et al, 2011;Ayoubi & Karchegani, 2012;Baligh et al, 2020;Hossein Alavi et al, 2010;Koekkoek & Booltink, 1999;Minasny et al, 2004Minasny et al, , 2016Ozturk et al, 2011). Application of multiple models for the classification of soil can be useful in arriving at more robust prediction as well providing a comparison among different models.…”

Section: Introductionmentioning

confidence: 99%

Characterization and classification of fine-resolution soil profile for precision agriculture using random forest and self-organizing map

Elias,

Sharma,

Goel

2024

Preprint

View full text Add to dashboard Cite

The availability of high throughput soil profile information is an important component in precision agriculture to perform efficient soil management for sustainable production. We collected 14 soil physiochemical features from Nagpur, Pune, and Haveri, representing target environments of safflower cultivation, and also from our experiment station at Delhi, at fine resolution and created graphical maps to depict the variability. Additionally, we evaluated the predictive ability of two statistical learning models, random forest (RF) and self-organizing maps (SOM) against multinomial regression models for correctly classifying the soil profile. Clustering was performed around the medoids produced from the dissimilarity matrices of these models using partitioning around medoids (PAM) model. The robustness, versatility, and predictive ability of models in correctly classifying the soil profile to clusters were then tested using cross-validation which was repeated 100 times. This study was performed using training data with proportionate size varying from 60 to 95%, and increasing the unit area of observation up to nine times (or decreasing the total number of observations up to a ninth). RF model was found to be the best performing with average prediction accuracy above 85% in all settings which reached close to 100% in some settings. The predictive ability of all the models was maintained even when only the most influencing six variables were used for classification. The optimal training population size for prediction was found to be 70 to 80%. Based on our study, it is recommended to i) collect fine resolution edaphic features from a marginal farm before crop season, ii) use RF or SOM model to identify the most influencing features distinguishing the soil samples iii) expand the area of sample collection, find values for the most influencing features, and use RF model to correctly predict the class to which the new set of the soil belongs to.

show abstract

Section: Introductionmentioning

confidence: 99%

Characterization and classification of fine-resolution soil profile for precision agriculture using random forest and self-organizing map

Elias,

Sharma,

Goel

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Different parameters can affect land specifications, among which the chemical and biological properties, including soil microbial activities, are the most important ones. Soil microbes can profoundly affect land properties by (1) recycling organic matter into available nutrients for plant use, (2) interacting with other soil microbes affecting plant growth, (3) controlling pathogens, and (4) alleviating soil stresses [20,27].…”

Section: Introductionmentioning

confidence: 99%

“…For example, soil organic carbon is affected by land use [28,48]. Soil organic carbon can considerably alter soil physicochemical and biological characteristics [2,36], determining the composition of the soil microbial communities. Increasing soil organic matter, as a source of food for the soil microbes, increases the population of soil decomposing microbes [12,37].…”

Section: Introductionmentioning

confidence: 99%

Soil chemical and microbial properties affected by land use type in a unique ecosystem (Fars, Iran)

Baligh

Honarjoo

Jalalian

et al. 2021

Biomass Conv. Bioref.

Self Cite

View full text Add to dashboard Cite

Land use type is an important parameter, affecting soil physicochemical and biological properties. Accordingly, it is important to find how land use type may affect soil properties in an ecosystem to avoid further environmental degradation. The objective was to investigate how different land use types including forest, rangeland, and dry and irrigated farming may alter soil chemical and biological properties including organic carbon (C), total nitrogen (N), potentially mineralizable N (PMN), particulate organic matter (POM), microbial respiration (MR), soil basal respiration (BR), and microbial biomass C (MBC) and N (MBN). The research was conducted in a unique ecosystem (having all types of the abovementioned land use), namely the Zanian region (17,000 ha, altitude of 1952-2657 m) of Fars province, Iran. A total of 130 samples (0-10 cm), collected from different stations across the research area, were analyzed. Geographical properties of the region including topography, slope, and altitude were also determined and presented by maps. POM, PMN, MBC, MBN, MR, and BR averaged to 0.48%, 53.44, 65.72 mg kg −1 soil, 8.85 mg N kg −1 soil, 0.118 mg CO 2 g −1 soil day −1 , and 41.22 mg CO 2 day −1 g −1 soil, respectively. Land use change from forest to farming (dry and irrigated) significantly decreased soil chemical and biological activities. Following forest, rangeland was the second most chemically and biologically active type of land. There were significant differences between rangeland and irrigated farming. Just POM was not different under rangeland and dry and irrigated farming. Land use change can profoundly alter soil chemical and biological properties.

show abstract

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

et al. 2021

View full text Add to dashboard Cite

Predicting Soil Particulate Organic Mattter Using Artificial Neural Network with Wavelet Function

Cited by 5 publications

References 31 publications

Characterization and classification of fine-resolution soil profile for precision agriculture using random forest and self-organizing map

Characterization and classification of fine-resolution soil profile for precision agriculture using random forest and self-organizing map

Soil chemical and microbial properties affected by land use type in a unique ecosystem (Fars, Iran)

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

Contact Info

Product

Resources

About