We obtained accurate predictions of clay, silt, sand, OC, pH and CCE for the middle eastern topsoils, with correct pedological correspondences, realistic spatial representations, and satisfactory levels of uncertainties.
We implemented a ML algorithm using SVR with wavelet transformation of the covariates within a DSM framework to map and predict soil salinity in central Iran. Here, using a soil database and a full suite of covariates— derived from remote sensing data, terrain attributes, and climatic data—SVR and W-SVR models were built for each of the standard soil depth increments.
The spatial pattern of SAR and EC suggested that the contribution of salt domes in soil salinization varied significantly according to their hydraulic behaviour in relation to adjacent aquifers and their activity. In general, the model averaging approach showed the potential to improve the estimates of EC and SAR.
The spatial pattern of SAR and EC suggested that the contribution of salt domes in soil salinization varied significantly according to their hydraulic behaviour in relation to adjacent aquifers and their activity. In general, the model averaging approach showed the potential to improve the estimates of EC and SAR.
We implemented a ML algorithm using SVR with wavelet transformation of the covariates within a DSM framework to map and predict soil salinity in central Iran. Here, using a soil database and a full suite of covariates— derived from remote sensing data, terrain attributes, and climatic data—SVR and W-SVR models were built for each of the standard soil depth increments.
In this study, soil phosphorus, electrical conductivity and sodium adsorption ratio were determined in longitudinal and transverse directions from an interceptor drain in cultivated and uncultivated field plots. Results showed that P content of points close to the drain was lower than points far from the drain.
In this study, soil phosphorus, electrical conductivity and sodium adsorption ratio were determined in longitudinal and transverse directions from an interceptor drain in cultivated and uncultivated field plots. Results showed that P content of points close to the drain was lower than points far from the drain.
This study our aim was to develop a model to predict soil adsorbable heavy metals in arid regions from 1986 to 2016. The overall trends indicated that the concentration and spatial distribution of these heavy metals have historically increased from 1986 to 2016.
This study our aim was to develop a model to predict soil adsorbable heavy metals in arid regions from 1986 to 2016. The overall trends indicated that the concentration and spatial distribution of these heavy metals have historically increased from 1986 to 2016.
Here, series of hybridized artificial neural network models with bio-inspired metaheuristic optimization algorithms such as a genetic algorithm, particle swarm optimization, bat, and monarch butterfly optimization algorithms, were built for predicting particle size fractions.