Soil erosion and associated sediment redistribution are key environmental problems in Central Argentina.Specific land uses and management practices,such as intensive grazing and crop cultivation,are considered to be s...Soil erosion and associated sediment redistribution are key environmental problems in Central Argentina.Specific land uses and management practices,such as intensive grazing and crop cultivation,are considered to be significantly driving and accelerating these processes.This research focuses on the identification of suitable soil tracers from hot spots of land degradation and sediment fate in an agricultural catchment of central Argentina with erodible loess soils.Using Energy Dispersive X-Ray Fluorescence(EDXRF),elemental concentrations were determined and later used as soil tracers for geochemical characterization.The best set of tracers were identified using two artificial mixtures composed of known proportions of soil sources collected from different lands having contrasting soil uses.Barium,calcium,iron,phosphorus,and titanium were identified for obtaining the best suitable reconstruction of source proportions in the laboratory-prepared artificial mixtures.Then,these elements,as well as the total organic carbon,were applied for pinpointing critical hot spots of erosion within the studied catchment.Feedlots were identified to be the main source of sediments,river banks and dirt roads together are the second most important source.This investigation provides key information for optimizing soil conservation strategies and selecting land management practices and land uses which do not generate great contribution of sediment,preventing pollution of the waterways of the region.展开更多
The ability to characterize rapidly and repeatedly exchangeable potassium(Kex)content in the soil is essential for optimizing remediation of radiocaesium contamination in agriculture.In this paper,we show how this can...The ability to characterize rapidly and repeatedly exchangeable potassium(Kex)content in the soil is essential for optimizing remediation of radiocaesium contamination in agriculture.In this paper,we show how this can be now achieved using a Convolutional Neural Network(CNN)model trained on a large Mid-Infrared(MIR)soil spectral library(40,000 samples with Kex determined with 1 M NH4OAc,pH 7),compiled by the National Soil Survey Center of the United States Department of Agriculture.Using Partial Least Squares Regression as a base-line,we found that our implemented CNN leads to a significantly higher prediction performance of Kex when a large amount of data is available(10000),increasing the coefficient of determination from 0.64 to 0.79,and reducing the Mean Absolute Percentage Error from 135%to 31%.Furthermore,in order to provide end-users with required interpretive keys,we implemented the GradientShap algorithm to identify the spectral regions considered important by the model for predicting Kex.Used in the context of the implemented CNN on various Soil Taxonomy Orders,it allowed(i)to relate the important spectral features to domain knowledge and(ii)to demonstrate that including all Soil Taxonomy Orders in CNN-based modeling is beneficial as spectral features learned can be reused across different,sometimes underrepresented orders.展开更多
基金CONICET,Argentina PROICO 22/F41 PIP 11220150100334Universidad Nacional de San Luis,Argentina RLA 5076 ARCAL RLA 5064 and ARCAI
文摘Soil erosion and associated sediment redistribution are key environmental problems in Central Argentina.Specific land uses and management practices,such as intensive grazing and crop cultivation,are considered to be significantly driving and accelerating these processes.This research focuses on the identification of suitable soil tracers from hot spots of land degradation and sediment fate in an agricultural catchment of central Argentina with erodible loess soils.Using Energy Dispersive X-Ray Fluorescence(EDXRF),elemental concentrations were determined and later used as soil tracers for geochemical characterization.The best set of tracers were identified using two artificial mixtures composed of known proportions of soil sources collected from different lands having contrasting soil uses.Barium,calcium,iron,phosphorus,and titanium were identified for obtaining the best suitable reconstruction of source proportions in the laboratory-prepared artificial mixtures.Then,these elements,as well as the total organic carbon,were applied for pinpointing critical hot spots of erosion within the studied catchment.Feedlots were identified to be the main source of sediments,river banks and dirt roads together are the second most important source.This investigation provides key information for optimizing soil conservation strategies and selecting land management practices and land uses which do not generate great contribution of sediment,preventing pollution of the waterways of the region.
基金carried out in the context of the IAEA funded Coordi-nated Research Project(CRPD1.50.19)titled“Remediation of Radioac-tive Contaminated Agricultural Land”,under IAEA Technical Contract n°23685.
文摘The ability to characterize rapidly and repeatedly exchangeable potassium(Kex)content in the soil is essential for optimizing remediation of radiocaesium contamination in agriculture.In this paper,we show how this can be now achieved using a Convolutional Neural Network(CNN)model trained on a large Mid-Infrared(MIR)soil spectral library(40,000 samples with Kex determined with 1 M NH4OAc,pH 7),compiled by the National Soil Survey Center of the United States Department of Agriculture.Using Partial Least Squares Regression as a base-line,we found that our implemented CNN leads to a significantly higher prediction performance of Kex when a large amount of data is available(10000),increasing the coefficient of determination from 0.64 to 0.79,and reducing the Mean Absolute Percentage Error from 135%to 31%.Furthermore,in order to provide end-users with required interpretive keys,we implemented the GradientShap algorithm to identify the spectral regions considered important by the model for predicting Kex.Used in the context of the implemented CNN on various Soil Taxonomy Orders,it allowed(i)to relate the important spectral features to domain knowledge and(ii)to demonstrate that including all Soil Taxonomy Orders in CNN-based modeling is beneficial as spectral features learned can be reused across different,sometimes underrepresented orders.