The possibility of preparing soil texture class map by artificial neural networks, inverse distance weighting, and geostatistical methods in Gavoshan dam basin, Kurdistan Province, Iran

Khanbabakhani, Elnaz; ‎Torkashvand, Ali Mohammadi; Mahmoodi, Mohammad Ali

doi:10.1007/s12517-020-5134-1

Cited by 8 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The use of ML models has become increasingly prevalent for predicting the spatial distribution of soil properties. When predicting soil PSFs, various ML-based DSM studies have included the use of artificial neural networks (ANNs) [17][18][19][20][21], boosted regression tree (BRT) [19,22,23], Random Forest (RF) [18,24], and artificial neuro-fuzzy inference system (ANFIS) [16,25]. Despite the variety of ML models that a DSM practitioner may apply, existing literature does not seem to suggest that one model is universally better than others; furthermore, model comparison studies have shown that different models have the potential to generate drastically different outputs when given the same input data [26].…”

Section: Introductionmentioning

confidence: 99%

“…When predicting PSFs, however, ANNs have been shown to be particularly effective, and they are the most widespread approach due to their accuracy and flexibility [17][18][19][20][21]. However, this model has several considerable shortcomings, such as inconsistent architectures for different applications, coupled with the process required to tune and fit a neural network, which is a time-consuming procedure that is largely based on trial and error [27,28].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bio-Inspired Hybridization of Artificial Neural Networks: An Application for Mapping the Spatial Distribution of Soil Texture Fractions

et al. 2021

View full text Add to dashboard Cite

Soil texture and particle size fractions (PSFs) are a critical characteristic of soil that influences most physical, chemical, and biological properties of soil; furthermore, reliable spatial predictions of PSFs are crucial for agro-ecological modeling. Here, series of hybridized artificial neural network (ANN) models with bio-inspired metaheuristic optimization algorithms such as a genetic algorithm (GA-ANN), particle swarm optimization (PSO-ANN), bat (BAT-ANN), and monarch butterfly optimization (MBO-ANN) algorithms, were built for predicting PSFs for the Mazandaran Province of northern Iran. In total, 1595 composite surficial soil samples were collected, and 64 environmental covariates derived from terrain, climatic, remotely sensed, and categorical datasets were used as predictors. Models were tested using a repeated 10-fold nested cross-validation approach. The results indicate that the hybridized ANN methods were far superior to the reference approach using ANN with a backpropagation training algorithm (BP-ANN). Furthermore, the MBO-ANN approach was consistently determined to be the best approach and yielded the lowest error and uncertainty. The MBO-ANN model improved the predictions in terms of RMSE by 20% for clay, 10% for silt, and 24% for sand when compared to BP-ANN. The physiographical units, soil types, geology maps, rainfall, and temperature were the most important predictors of PSFs, followed by the terrain and remotely sensed data. This study demonstrates the effectiveness of bio-inspired algorithms for improving ANN models. The outputs of this study will support and inform sustainable soil management practices, agro-ecological modeling, and hydrological modeling for the Mazandaran Province of Iran.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bio-Inspired Hybridization of Artificial Neural Networks: An Application for Mapping the Spatial Distribution of Soil Texture Fractions

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Visualmente, os mapas apresentaram padrões que diferenciaram relativamente pouco entre si, e permitiram a identificação de regiões com diferentes frações texturais. Tem-se a expectativa de que o solo nas porções central e direita mapeada apresente maior retenção hídrica e baixa condutividade hidráulica devido à maior fração argila, enquanto que aquela à esquerda possua maior capacidade de drenagem hídrica em virtude da característica arenosa (JOZEFACIUK et al, 2020;KHANBABAKHANI;TORKASHVAND;MAHMOODI, 2020;LI;WAN;SHANG, 2020;WANG et al, 2020).…”

Section: Krigagemunclassified

“…A análise granulométrica do solo permite interpretações texturais, relacionadas ao tamanho de partículas, identificando a fração fina constituída por areia (diâmetros entre 0,02 mm e 2 mm), silte (diâmetros entre 0,002 e 0,02 mm) e argila (diâmetros menores que 0,002 mm). Informações das frações de argila, silte e areia auxiliam a classificação de solos e a realização de inferências sobre a Capacidade de Trocadora de Cátions (CTC), drenagem, curva de retenção de água, fertilidade, resistência ao cisalhamento, porosidade, teor de Matéria Orgânica (MO) e outras métricas do solo (CENTENO et al, 2017;ABU-HAMDEH et al, 2019;BEVINGTON et al, 2019;SHAHRIARI et al, 2019;UYANIK et al, 2019;JOZEFACIUK et al, 2020;KHANBABAKHANI;TORKASHVAND;MAHMOODI, 2020;LI;WAN;SHANG, 2020;WANG et al, 2020). Solos mais argilosos tendem a exibir maiores valores de CTC, capacidade de retenção de umidade, microporosidade e MO.…”

Section: Introductionunclassified

“…O levantamento de dados texturais e sua espacialização por meio de tratamento geoestatístico são úteis para a identificação de setores na área de cultivo que requerem cuidados específicos de manejo e conservação de solo (SHAHRIARI et al, 2019;WANG et al, 2020). A maioria das pesquisas sobre a interpolação de dados físicos do solo é incipiente ou recente (SHAHRIARI et al, 2019;KHANBABAKHANI;TORKASHVAND;MAHMOODI, 2020;LI;WAN;SHANG, 2020). Estas pesquisas permitem a definição de um raio mínimo para a coleta de amostras compostas para se evitar problemas de enviesamento estatístico proveniente de dependência espacial.…”

Section: Introductionunclassified

See 1 more Smart Citation

Dependência espacial e krigagem para a estimativa textural de solos em São João Evangelista

et al. 2022

View full text Add to dashboard Cite

Investigações científicas sobre a distribuição espacial de atributos texturais de solo subsidiam o planejamento da coleta de amostras para análise granulométrica, importante para a definição de tratos culturais. O objetivo foi avaliar o desempenho de diferentes métodos de krigagem e modelos matemáticos de semivariograma teórico na estimativa textural em uma área de Latossolo Vermelho-Amarelo Distrófico. O estudo foi conduzido em uma área de 41,07ha no Instituto Federal de Educação, Ciência e Tecnologia de Minas Gerais, campus São João Evangelista. Estabeleceu-se uma grade amostral regular de 130 × 130m, totalizando 33 pontos amostrais georreferenciados. A análise de interpolação espacial adotou dois métodos de krigagem (simples e ordinária) e três modelos de semivariograma teórico (esférico, exponencial e gaussiano). A intensidade da dependência espacial das frações silte e argila tenderam a ser menores que aquela da fração areia. Para fins texturais, estimou-se o tamanho ideal de glebas circulares de 18,48ha para a obtenção de amostras compostas de solo. Conclui-se que a krigagem simples associada ao modelo de semivariograma gaussiano é eficiente para análises de interpolação espacial de frações de areia e argila. A combinação desse método de krigagem com o modelo de semivariograma esférico é preciso para a estimativa da fração silte. Palavras-chave: Areia. Silte. Argila. Geoestatística. Método probabilístico. Space dependence and kriging for soils texture estimate in São João Evangelista, Minas Gerais, Brazil Abstract Scientific investigations concerning the spatial distribution of soil textural attributes support planning of sample collection for granulometric analysis, important for definition of cultural tracts. This work aimed to evaluate the performance of different kriging methods and mathematical models of theoretical semivariogram in textural estimation of adystrophic Red Yellow Latosol. The study area has 41.07ha at the Federal Institute of Education, Science and Technology of Minas Gerais, campus São João Evangelista. A regular sampling grid of 130 × 130m was established, totaling 33 georeferenced sample points. Spatial interpolation analysis adopted two kriging methods (simple and ordinary) and three theoretical semivariogram models (spherical, exponential and Gaussian). Spatial dependence intensity of the silt and clay fractions tended to be less than that of the sand fraction. For textural purposes, the ideal size of 18.48 ha circular plots was estimated for obtaining samples of soil. It is concluded that the simple kriging associated with gaussian semivariogram model is efficient for spatial interpolation analyzes of sand and clay fractions. The combination of this kriging method with spherical semivariogram model is required for estimating the silt fraction. Keywords: Sand. Silt. Clay. Geostatistics. Probabilistic method.

show abstract

Correcting correlation quality of portable X-ray fluorescence to better map heavy metal contamination by spatial co-kriging interpolation

Zhao,

Chen,

Qian

et al. 2024

Ecotoxicology and Environmental Safety

View full text Add to dashboard Cite

The possibility of preparing soil texture class map by artificial neural networks, inverse distance weighting, and geostatistical methods in Gavoshan dam basin, Kurdistan Province, Iran

Cited by 8 publications

References 21 publications

Bio-Inspired Hybridization of Artificial Neural Networks: An Application for Mapping the Spatial Distribution of Soil Texture Fractions

Bio-Inspired Hybridization of Artificial Neural Networks: An Application for Mapping the Spatial Distribution of Soil Texture Fractions

Dependência espacial e krigagem para a estimativa textural de solos em São João Evangelista

Correcting correlation quality of portable X-ray fluorescence to better map heavy metal contamination by spatial co-kriging interpolation

Contact Info

Product

Resources

About