A new approach for extrapolating soil information from reference to target areas is proposed in the current research. We evaluated the ability of a semi-supervised learning approach compared to a supervised learning approach for extrapolating soil classes in two areas.
A new approach for extrapolating soil information from reference to target areas is proposed in the current research. We evaluated the ability of a semi-supervised learning approach compared to a supervised learning approach for extrapolating soil classes in two areas.
This study evaluated the super learning approach by combining 12 ML models, which ultimately improved the accuracy of the predicted soil maps in comparison to when the individual base learners were used. Furthermore, a PFI analysis was used to identify the contribution of each covariate on the final prediction.
This study evaluated the super learning approach by combining 12 ML models, which ultimately improved the accuracy of the predicted soil maps in comparison to when the individual base learners were used. Furthermore, a PFI analysis was used to identify the contribution of each covariate on the final prediction.
Although conventional machine learning algorithms, such as random forest or support vector machine, have been extensively used in digital soil mapping to predict the PSF, less research examined the potential of state-of-the-art deep learning approaches for such processing.
Although conventional machine learning algorithms, such as random forest or support vector machine, have been extensively used in digital soil mapping to predict the PSF, less research examined the potential of state-of-the-art deep learning approaches for such processing.
In this research, we investigate the predictive power of six data mining classifiers to estimate USDA soil groups. Our results showed that no improvement was obtained in prediction accuracy of DTA algorithm with minimizing taxonomic distance compared to minimizing misclassification error.
In this research, we investigate the predictive power of six data mining classifiers to estimate USDA soil groups. Our results showed that no improvement was obtained in prediction accuracy of DTA algorithm with minimizing taxonomic distance compared to minimizing misclassification error.
We attempt in this study to investigate soil salinity variation (vertical and lateral) for a study area within Iran. Here, using soil data base and the full suite of auxiliary data— including the predicted maps of ECav and ECah, ETM+ images, geomorphology map, and terrain parameters—regression tree models were built for each of the standard depths.
We attempt in this study to investigate soil salinity variation (vertical and lateral) for a study area within Iran. Here, using soil data base and the full suite of auxiliary data— including the predicted maps of ECav and ECah, ETM+ images, geomorphology map, and terrain parameters—regression tree models were built for each of the standard depths.