The characterization of soil profile distribution for nitrate leached in the paddy soil

Experiment was conducted for five successiveyears under large undisturbed monolith lysime-ters(2m×2m in square,l m in depth).Thesoil was silty clay loam texture and had a con-tent of total N 1.55 g/kg.The soil was flood-ed with penetration rate controlled at approxi-mate 3 mm per day in duration of double-riceseason and laid fallow and natural in winterand spring.Results showed that nitrate was the mainform of nitrogen in percolates.The change of

HVSR analysis of pumice sands for sediment depth characterization:A case study for Guadalajara,Mexico

The horizontal to vertical spectral ratio(HVSR)methodology is used here to characterize pumice soils and to image the three-dimensional surface geometry of Guadalajara,Mexico.Similar to other Latin American cities,Guadalajara is exposed to high seismic risk,with the particularity of being the largest urban settlement in Latin America built on pumice soils.Methodology has not yet been tested to characterize subsoil depths in pumice sands.Due to the questionable use of traditional geotechnical tests for the analysis of pumice soils,HVSR provides an alternative for its characterization without altering its fragile and porous structure.In this work,resonance frequency(F0)and peak amplitude(A0)are used to constrain the depth of the major impedance contrast that represents the interface between bedrock and pumice soil.Results were compared with borehole depths and other available geotechnical and geophysical data and show good agreement.One of the profiles estimated on the riverbanks that cross the city,reveals different subsoil thickness that could have an impact on different site responses on riverine areas to an eventual earthquake.Government and academic efforts are combined in this work to characterize depth sediments,an important parameter that impacts the regulations for construction in the city.

Prediction of exchangeable potassium in soil through mid-infrared spectroscopy and deep learning:From prediction to explainability

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.