All

Vis NIR Spectra for Soil Salinity Estimation

Soil salinization is an important threat for agriculture and environment in the eastern coast of Urmia hyper saline Lake. Predicting soil salinization requires rapid and low-cost measurement tools of soil salinity. It is hypothesized that remote sensing and visible near-infrared spectroscopy may offer a feasible method for that purpose.

Mapping of SOC Using Deep ANNs

The objective of this study was to determine a reliable algorithm for predicting the SOC contents through consideration of six different ML algorithms and using 105 environmental auxiliary variables derived from terrain attributes, remote sensing, and climatic data. The results show that the DNN algorithm outperformed other ML algorithms in terms of the power of the prediction uncertainty at the province scale.

Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran

The objective of this study was to determine a reliable algorithm for predicting the SOC contents through consideration of six different ML algorithms and using 105 environmental auxiliary variables derived from terrain attributes, remote sensing, and climatic data. The results show that the DNN algorithm outperformed other ML algorithms in terms of the power of the prediction uncertainty at the province scale.

Improving the Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions by Stacking Machine Learning Models and Rescanning Covariate Space

In this study, we introduced stacking ML models in two modes (standard mode and rescan mode) in order to improve the spatial prediction of SOC content at two contrasting climatic regions (arid and sub-humid). The stacking ensemble modeling in both modes indicated the higher performance in comparison to the individual models.

Prediction of SOC by Stacking of Models

In this study, we introduced stacking ML models in two modes (standard mode and rescan mode) in order to improve the spatial prediction of SOC content at two contrasting climatic regions (arid and sub-humid). The stacking ensemble modeling in both modes indicated the higher performance in comparison to the individual models.

Soil Enzyme Activity in Riparian Forests

Riparian forests are important ecosystems especially in arid zones but no information is available about soil enzyme activity in this ecosystem. Therefore, the objectives of this study were to explore some soil enzyme activities and investigate which soil physico-chemical factors affect these soil enzyme activities in riparian forests the most.

Soil enzyme activity variations in riparian forests in relation to plant species and soil depth

Riparian forests are important ecosystems especially in arid zones but no information is available about soil enzyme activity in this ecosystem. Therefore, the objectives of this study were to explore some soil enzyme activities and investigate which soil physico-chemical factors affect these soil enzyme activities in riparian forests the most.

Assessing soil organic carbon stocks under land-use change scenarios using random forest models

In the area, approximately 18.48% of forestland and 17.39% of wetland has been brought into cultivation. The authors estimate that this has led to a loss of SOCS from forestland topsoil of 22,860 Mg C. The SOCS loss from wetland topsoil was not as great, at 4193 Mg C, but this was due to the area not being as large.

SOC Stocks under Land-Use Changes

In the area, approximately 18.48% of forestland and 17.39% of wetland has been brought into cultivation. The authors estimate that this has led to a loss of SOCS from forestland topsoil of 22,860 Mg C. The SOCS loss from wetland topsoil was not as great, at 4193 Mg C, but this was due to the area not being as large.

Disaggregation of Conventional Soil Map

To increase detail in the polygon of conventional soil maps, we have produced a spatially disaggregated soil class map of a relatively flat agricultural plain using DSMART algorithm. DSMART works through resampled classification trees to estimate the probability of the existence of each possible soil classes and also to prepare the maps of the most probable soil class, second most probable, and so on in raster format.