Deep Learning-based Soil Property Prediction for Remediation of Radioactive Contamination in Agriculture

2021 ◽  
Author(s):  
Franck Albinet ◽  
Gerd Dercon ◽  
Tetsuya Eguchi
Keyword(s):  
Deep Learning ◽  
Soil Properties ◽  
Radioactive Contamination ◽  
The United States ◽  
Soil Survey ◽  
United States Department ◽  
Least Squares Regression ◽  
Transfer Factors ◽  
Wide Range ◽  
Plant Transfer

<p>The Joint IAEA/FAO Division of Nuclear Techniques in Food and Agriculture, through its Soil and Water Management & Crop Nutrition Laboratory (SWMCNL), launched in October 2019, a new Coordinated Research Project (D15019) called “Monitoring and Predicting Radionuclide Uptake and Dynamics for Optimizing Remediation of Radioactive Contamination in Agriculture''. Within this context, the high-throughput characterization of soil properties in general and the estimation of soil-to-plant transfer factors of radionuclides are of critical importance.</p><p>For several decades, soil researchers have been successfully using near and mid-infrared spectroscopy (MIRS) techniques to estimate a wide range of soil physical, chemical and biological properties such as carbon (C), Cation Exchange Capacities (CEC), among others. However, models developed were often limited in scope as only small and region-specific MIR spectra libraries of soils were accessible.</p><p>This situation of data scarcity is changing radically today with the availability of large and growing library of MIR-scanned soil samples maintained by the National Soil Survey Center (NSSC) Kellogg Soil Survey Laboratory (KSSL) from the United States Department of Agriculture (USDA-NRCS) and the Global Soil Laboratory Network (GLOSOLAN) initiative of the Food Agency Organization (FAO). As a result, the unprecedented volume of data now available allows soil science researchers to increasingly shift their focus from traditional modeling techniques such as PLSR (Partial Least Squares Regression) to classes of modeling approaches, such as Ensemble Learning or Deep Learning, that have proven to outperform PLSR on most soil properties prediction in a large data regime.</p><p>As part of our research, the opportunity to train higher capacity models on the KSSL large dataset (all soil taxonomic orders included ~ 50K samples) makes it possible to reach a quality of prediction for exchangeable potassium so far unsurpassed with a Residual Prediction Deviation (RPD) around 3. Potassium is known for its difficulty of being predicted but remains extremely important in the context of remediation of radioactive contamination after a nuclear accident. Potassium can help reduce the uptake of radiocaesium by crops, as it competes with radiocaesium in soil-to-plant transfer.</p><p>To ensure informed decision making, we also guarantee that (i) individual predictions uncertainty is estimated (using Monte Carlo Dropout) and (ii) individual predictions can be interpreted (i.e. how much specific MIRS wavenumber regions contribute to the prediction) using methods such as Shapley Additive exPlanations (SHAP) values.</p><p>SWMCNL is now a member of the GLOSOLAN network, which helps enhance the usability of MIRS for soil monitoring worldwide. SWMCNL is further developing training packages on the use of traditional and advanced mathematical techniques to process MIRS data for predicting soil properties. This training package has been tested in October 2020 with thirteen staff members of the FAO/IAEA Laboratories in Seibersdorf, Austria.</p>

Exploring the Applicability of Deep Learning Methods in Mid-infrared Spectroscopy for Soil Property Predictions

2020 ◽  
Author(s):  
Franck Albinet ◽  
Amelia Lee Zhi Yi ◽  
Petra Schmitter ◽  
Romina Torres Astorga ◽  
Gerd Dercon
Keyword(s):  
Deep Learning ◽  
Mathematical Models ◽  
Partial Least Square ◽  
Soil Survey ◽  
High Spectral Resolution ◽  
United States Department ◽  
Soil Composition ◽  
Mid Infrared ◽  
Wide Range ◽  
Soil Sciences

<p> </p><p>The usage of mathematical models and mid-infrared (MIR) spectral databases to predict the elemental composition of soil allows for rapid and high-throughput characterization of soil properties. The Partial Least Square Regression (PLSR) is a pervasive statistical method that is used for such predictive mathematical models due to a large existing knowledge base paired with standardized best practices in model application. Despite its ability to transform data in the high-dimensional space (high spectral resolution) to a space of fewer dimensions that captures the correlation between the input space (spectra) and the response variables (elemental soil composition), this popular approach fails to capture non-linear patterns. Further, PLSR has poor prediction capacities for a wide range of soil analytes such as Potassium and Phosphorus, just to mention a few. In addition, prediction is highly sensitive to pre-processing steps in data derivation that can also be tainted by human biases based on the empirical selection of wavenumber regions. Thus, the usage of PLSR as a methodology for elemental prediction of soil remains time-consuming and limited in scope.</p><p>With major breakthroughs in the area of Deep Learning (DL) in the past decade, soil science researchers are increasingly shifting their focus from traditional techniques such as PLSR to using DL models such as Convolutional Neural Networks. Promising results of this shift have been showcased, including increased prediction accuracy, reduced needs for data pre-processing, and improved evaluation of explanatory factors. Increasingly, studies are also looking to expand beyond the regional scope and support higher resolution and more accurate databases for global modelling efforts. However, the setup of a DL model is notoriously data intensive and often said to be less applicable when there is limited data available. While a MIR spectra database has been recently publicly released by the Kellog Soil Survey Laboratory, United States Department of Agriculture, such large-scale initiative remains a niche and focus only on specific regions and/or ecosystem types.</p><p>This research is a first effort in applying DL techniques in a relative data scarce environment (approximately 1000 labelled spectra) using transfer learning and domain-specific data augmentation techniques. In particular, we assess the potential of unsupervised feature learning approaches as a key enabler for broader applicability of DL techniques in the context of MIR spectroscopy and soil sciences. A better understanding of potential for DL methods in soil composition prediction will greatly advance the work of soil sciences and natural resource management. Improvements to overcome its associated challenges will be a step forward in creating a universal soil modelling technique through reusable models and contribute to a large world-wide soil MIR spectral database.</p>

Conceptual Analysis of the Economic Feasibility of Fission Electric Cell Reactors

2002 ◽  
Author(s):  
C. Morrow ◽  
G. Rochau ◽  
J. Cash ◽  
D. King
Keyword(s):  
Energy Conversion ◽  
Cost Model ◽  
The United States ◽  
Capital Cost ◽  
Economic Feasibility ◽  
United States Department ◽  
Value Analysis ◽  
Direct Energy Conversion ◽  
Wide Range ◽  
Direct Energy

The United States Department of Energy, Nuclear Energy Research Initiative (NERI) Direct Energy Conversion (DEC) project began in August of 1998 with the goal of developing a direct energy conversion process suitable for commercial development. With roughly two thirds of the project completed, we believe a viable direct energy device could be economic. This paper describes the financial basis behind that belief for one proposed DEC reactor, the magnetically insulated fission electric cell (FEC). It also illustrates the value of economic analysis even in these early phases of a research project. The financial basis consists of a conceptual level Economic Model comprised of five modules. The Design Model provides technical specification to other modules. The Fuel Cost Model estimates fuel expenses based on current spot market prices applied over a wide range of fuel enrichment. The Operating Cost Model uses published correlations to provide rough order of magnitude non-fuel operating costs. The Capital Cost model uses analogy and parametric estimating techniques to generate capital cost estimates for a DEC power plant. Finally, the financial model combines output from the other models to produce a Net Present Value analysis with cost of generation as the independent variable. Model results indicate that several FEC geometric configurations could be economic. Within these configurations, optimums exist. Finally, the model demonstrates that the most efficient design is not necessarily the most economic.

Clathrate Hydrates for Production of Potable Water

2006 ◽  
Vol 930 ◽  
Author(s):  
Robert W. Bradshaw ◽  
Blake A. Simmons ◽  
Eric H Majzoub ◽  
W. Miles Clift ◽  
Daniel E. Dedrick
Keyword(s):  
Structural Characterization ◽  
Potable Water ◽  
Hydrate Formation ◽  
The United States ◽  
Clathrate Hydrate ◽  
Department Of Energy ◽  
Clathrate Hydrates ◽  
Crystalline Inclusion ◽  
United States Department ◽  
Wide Range

ABSTRACTClathrate hydrates are crystalline inclusion compounds of water and a guest molecule (e.g., methane) that form at temperatures below ambient but above the freezing point of water. There are three known crystalline structures of hydrates (structure I, II, and H) in which cavities within the hydrogen bonded water molecule lattice trap the hydrate-forming species. The clathrate structure excludes dissolved solutes, such as sodium chloride, from the aqueous phase and thereby offers a possible means to produce potable water from seawater or brackish water. The concept of using clathrate hydrates for desalination is not new. However, before clathrate hydrate desalination becomes a viable technology, fundamental issues of controlled hydrate formation, hydrate size and morphology, agglomeration, amount of entrapped salt, and the efficient recovery of hydrates must be understood. This paper will report structural characterization of hydrates formed with several guest molecules over a wide range of conditions in an attempt to further the physicochemical insight needed to address these issues.Clathrate hydrate formation experiments were performed using a variety of host molecules, including R141b, a commercial refrigerant, C2FCl2H3. Hydrates of R141b were formed at temperatures from 2°C to 6°C and atmospheric pressure from deionized water and 2% - 7% NaCl solutions. Samples of the hydrates were characterized by cold-stage x-ray diffraction and Raman spectroscopy and determined to be structure II. Additional experiments were conducted with a gaseous hydrate former, ethylene, which readily formed hydrates with deionized or saline water at 2°C and several atmospheres of pressure. Experiments with several other hydrate forming molecules were conducted and the results obtained from their structural characterization will be reported. We will also present proof-of-concept experiments demonstrating a novel technique of desalination using these hydrate formers.Sandia National Laboratories is a multiprogram laboratory operated by Sandia Corporation, a Lockheed Martin company, for the United States Department of Energy under contract DE-AC04-94AL85000.

Airborne DIAL (Differential Absorption Lidar) for Broad Area Hazardous Liquid Leak Detection

2006 ◽  
Author(s):  
Steven V. Stearns ◽  
Trevis J. Gigliotti ◽  
Darryl G. Murdock
Keyword(s):  
Natural Gas ◽  
Field Tests ◽  
The United States ◽  
Airborne Lidar ◽  
United States Department ◽  
Differential Absorption ◽  
Broad Area ◽  
Differential Absorption Lidar ◽  
Observation Study ◽  
Wide Range

Over the summer of 2005 ITT Space Systems Division successfully detected, measured, and imaged a range of different hazardous liquids from an airborne platform during a series of field tests in Texas and New York. Under contract from the United States Department of Transportation Pipeline and Hazardous Materials Safety Administration (DOT/PHMSA), ITT examined the ability of its Airborne Natural Gas Emission Lidar (ANGEL) Service’s system to detect, measure, and image a wide range of different hydrocarbons from a remote sensing airborne platform. The objectives of the DOT/PHMSA contract were to: 1) develop an understanding of hazardous liquid pipeline leaks, 2) demonstrate that ITT’s DIAL (differential absorption lidar) technology can detect and measure hazardous liquid emissions over a broad area and in real world conditions, and 3) use this information to design a “next generation” airborne sensor system optimized for the detection of both natural gas and hazardous liquid emissions. Hazardous liquids examined in this study included propane, gas condensates, crude oil, and refined hydrocarbons like gasoline, aviation gas, diesel fuel, Jet A, and kerosene. As part of this study, ITT, in cooperation with El Paso Production and Texas A&M–Corpus Christi, completed two separate sets of overflights of a hazardous liquid storage facility. During each set of overflights, data was collected with the storage facility’s vapor recovery unit (VRU) operating and again after the VRU was turned off. In addition, hatches on each of the tanks were opened to create further emission sources. Additional aerial collections of gasoline vapors, propane, and natural gas were also completed. Data from each of the overflights was processed and the results analyzed. The ITT ANGEL Service technology was shown to be capable of rapidly detecting, measuring, and imaging a wide range of different hydrocarbons while flying at an altitude of 1,000 feet and speeds of up to 150 mph. An overview of the results from these flight tests and a discussion of the DOT/PHMSA Hazardous-Liquid Airborne Lidar Observation Study findings will be discussed.

Transfer of natural radionuclides from soil to plants in Savar Dhaka

2017 ◽  
Vol 7 ◽  
Author(s):  
M. Haque ◽  
J. Ferdous
Keyword(s):  
Soil Properties ◽  
Nuclear Reactor ◽  
Gamma Ray ◽  
Natural Radionuclides ◽  
Gamma Ray Spectrometry ◽  
Free Access ◽  
Transfer Factors ◽  
The Public ◽  
Activity Concentrations ◽  
Plant Transfer

The radioactivity of environmental samples from nuclear reactor sites must be analyzed before the public is given free access to the plants grown in these soils. Plant and corresponding soil samples were collected from a sample site around the Savar research reactor near Dhaka (Bangladesh) and the activity concentrations of natural radionuclides <sup>226</sup>Ra (<sup>238</sup>U-chain), <sup>228</sup>Ra (<sup>232</sup>Th-chain) and non-chained <sup>40</sup>K were measured using gamma ray spectrometry. Soils of Savar contained more radioactive <sup>40</sup>K than <sup>226</sup>Ra and <sup>228</sup>Ra. The influence of certain soil properties on the activity concentrations and transfer factors (TF) of natural radionuclides were investigated by correlating the observed data with those of soil properties. The activity concentrations of <sup>40</sup>K were much higher than those of <sup>226</sup>Ra and <sup>228</sup>Ra in plants due to higher uptake from soils. The transfer factors for <sup>226</sup>Ra, <sup>228</sup>Ra and <sup>40</sup>K were found to range from 0.04 to 0.10, 0.12 to 0.32, and 0.24 to 0.72, respectively. The soil to plant transfer factors for <sup>40</sup>K was found to be much higher in plants, which might be due to this element being vital in plants. This study showed that activity concentrations of these radionuclides in plants and their plant transfer factors seem to depend on the activity concentrations of the same radionuclides in soil.</p><p><strong> </strong>

scholarly journals A Soil Bioassay for Predicting the Risk of Spinach Fusarium wilt

Plant Disease ◽  
2015 ◽  
Vol 99 (4) ◽  
pp. 512-526 ◽  
Author(s):  
Emily W. Gatch ◽  
Lindsey J. du Toit
Keyword(s):  
Soil Properties ◽  
Fusarium Wilt ◽  
Inbred Line ◽  
The United States ◽  
Inbred Lines ◽  
Soil Samples ◽  
Soil Bioassay ◽  
Inbred Parent ◽  
Wide Range ◽  
Seed Crops

The maritime Pacific Northwest is the only region of the United States suitable for production of spinach seed, a cool-season, daylength-sensitive crop. However, the acidic soils of this region are highly conducive to spinach Fusarium wilt, caused by Fusarium oxysporum f. sp. spinaciae. Rotations of at least 10 to 15 years between spinach seed crops are necessary to reduce the high risk of losses to this disease. The objectives of this study were to develop a greenhouse soil bioassay to assess the relative risk of Fusarium wilt in fields intended for spinach seed production, and to identify soil chemical and physical properties associated with conduciveness to this disease. Preliminary bioassays established a protocol for growing spinach plants in a greenhouse environment and inducing Fusarium wilt symptoms so that the bioassay can be completed in <2 months. Test soils with a range of Fusarium wilt inoculum potentials, and three spinach inbred parent lines (highly susceptible, moderately susceptible, and moderately resistant to Fusarium wilt) were used to evaluate sensitivity of the bioassay to different levels of risk of Fusarium wilt. Then, from 2010 to 2013, spinach seed growers and stakeholders submitted soil samples from 147 fields for evaluation with the bioassay. The fields were each under consideration for planting a spinach seed crop, yet the bioassay revealed a wide range in Fusarium wilt inoculum potential among soil samples. Differences in susceptibility to Fusarium wilt of the three inbred lines were key to detecting differences in wilt risk among soils. Visits to spinach seed crops planted in fields evaluated in the bioassay, as well as test plots of the three inbred lines planted in growers’ seed crops, confirmed the predictive value of the bioassay for Fusarium wilt risk. Correlation analyses for 23 soil properties revealed significant relationships of 15 soil properties with the Fusarium wilt potential of a soil, but the correlations were influenced significantly by susceptibility of the inbred line to Fusarium wilt (13, 10, and 8 soil properties correlated significantly with Fusarium wilt risk for the susceptible, moderate, and partially resistant inbreds, respectively). Multiple regression analyses identified different statistical models for prediction of Fusarium wilt risk depending on the spinach inbred line, but the best fitting model explained <34% of the variability in Fusarium wilt risk among 121 fields evaluated in the soil bioassay. Thus, no model was robust enough to replace the bioassay for the purpose of predicting Fusarium wilt risk.

scholarly journals The Heat Pulse Method for Soil Physical Measurements: A Bibliometric Analysis

2020 ◽  
Vol 10 (18) ◽  
pp. 6171 ◽  
Author(s):  
Hailong He ◽  
Miles Dyck ◽  
Jialong Lv
Keyword(s):  
Bibliometric Analysis ◽  
Agricultural Research ◽  
Pulse Method ◽  
The United States ◽  
Heat Pulse ◽  
Soil Science ◽  
United States Department ◽  
Soil Science Society ◽  
Physical Measurements ◽  
Wide Range

Heat pulse method is a transient method that estimates soil thermal properties by characterizing the radial transport of short-duration line-source heat applied to soils. It has been widely used to measure a wide range of soil physical properties including soil thermal conductivity, thermal diffusivity, heat capacity, water content, ice content, bulk density, water flux and evaporation in laboratory and field environments. Previous studies generally focus on the scientific aspects of heat pulse method based on selected publications, and there is a lack of study investigating the heat pulse publication as a whole. The objective of this study was to give an overall view of the use of heat pulse method for soil physical measurements from the bibliometric perspectives. The analyses were based on the Web of Science Core Collection data between 1992 and 2019 using HistCite Pro and VOSviewer. The results showed an increasing trend in the volume of publications on this field and Dr. Robert Horton was the most productive researcher coauthoring papers on the heat pulse method. The co-authorship analysis revealed that researchers from soil science are closely collaborated, but this is not true for researchers in other fields. There is a lack of new young scientists committing to this field while the older generation of researchers are retiring. The United States Department of Agriculture Agricultural Research Servics (USDA-ARS), the China Agriculture University and the Chinese Academy of Science were the top three organizations applying the heat pulse method, while the USA, China and Canada were the top three countries. The Soil Science Society of America Journal, Water Resources Research and Agricultural and Forestry Meteorology were the most widely used journals. The con-occurrence and citation analysis could be used to map the development of the field and identify the most influential publications. The study showed that the bibliometric analysis is a useful tool to visualize research status as well as to provide the general information of novices and experts alike on the heat pulse method for soil physical measurements.

scholarly journals Is Standardization Necessary for Sharing of a Large Mid-Infrared Soil Spectral Library?

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6729
Author(s):  
Shree R. S. Dangal ◽  
Jonathan Sanderman
Keyword(s):  
Soil Properties ◽  
Predictive Models ◽  
Soil Samples ◽  
Soil Survey ◽  
Least Squares Regression ◽  
Spectral Library ◽  
Calibration Transfer ◽  
Mid Infrared ◽  
Calibration Models ◽  
Spectral Libraries

Recent developments in diffuse reflectance soil spectroscopy have increasingly focused on building and using large soil spectral libraries with the purpose of supporting many activities relevant to monitoring, mapping and managing soil resources. A potential limitation of using a mid-infrared (MIR) spectral library developed by another laboratory is the need to account for inherent differences in the signal strength at each wavelength associated with different instrumental and environmental conditions. Here we apply predictive models built using the USDA National Soil Survey Center–Kellogg Soil Survey Laboratory (NSSC-KSSL) MIR spectral library (n = 56,155) to samples sets of European and US origin scanned on a secondary spectrometer to assess the need for calibration transfer using a piecewise direct standardization (PDS) approach in transforming spectra before predicting carbon cycle relevant soil properties (bulk density, CaCO3, organic carbon, clay and pH). The European soil samples were from the land use/cover area frame statistical survey (LUCAS) database available through the European Soil Data Center (ESDAC), while the US soil samples were from the National Ecological Observatory Network (NEON). Additionally, the performance of the predictive models on PDS transfer spectra was tested against the direct calibration models built using samples scanned on the secondary spectrometer. On independent test sets of European and US origin, PDS improved predictions for most but not all soil properties with memory based learning (MBL) models generally outperforming partial least squares regression and Cubist models. Our study suggests that while good-to-excellent results can be obtained without calibration transfer, for most of the cases presented in this study, PDS was necessary for unbiased predictions. The MBL models also outperformed the direct calibration models for most of the soil properties. For laboratories building new spectroscopy capacity utilizing existing spectral libraries, it appears necessary to develop calibration transfer using PDS or other calibration transfer techniques to obtain the least biased and most precise predictions of different soil properties.

Development of a GIS Database of Corrosion Hazards for Use in Pipeline Integrity Assessments

2008 ◽  
Author(s):  
David L. Slayter ◽  
Christopher S. Hitchcock
Keyword(s):  
The United States ◽  
Soil Survey ◽  
National Database ◽  
Soil Conditions ◽  
Pipeline System ◽  
United States Department ◽  
Soil Corrosion ◽  
Gis Database ◽  
Geologic Hazards ◽  
The U.S

Geologic hazards pose a significant threat to pipeline integrity. As an existing pipeline system ages, targeted analysis and positioning of maintenance resources become increasingly important to remediating problem pipeline sections and to ensure timely response to system failures. A geographic information system (GIS) now is commonly used to model pipeline systems. Significant geologic hazards can be mapped and effectively managed in a GIS database as a way to assess risk and to target pipeline remediation resources. In particular, the potential for soil corrosion is a significant threat to pipelines. In the U.S., digital soil maps from the United States Department of Agriculture, Natural Resources Conservation Service (USDA NRCS) have been compiled into the Soil Survey Geographic (SSURGO) database. Numerous soil attributes are stored in the database allowing for a detailed examination of soil characteristics. SSURGO data is largely consistent in quality and geographic extent across the U.S. and is the best available database for a national assessment of soil corrosion potential. We describe the development of a national database for the collection of locations of known corrosion from pipeline system managers. This database can be compared to soil conditions, as noted in SSURGO or other supporting soil data, for the development of a model of soil parameters that may indicate the future potential for buried pipeline corrosion. This paper outlines the need for such a database, significant design considerations and the proposed process for model development.

scholarly journals Neural Network Based Estimation of Service Life of Different Metal Culverts in Arkansas

2022 ◽  
Vol 2022 ◽  
pp. 1-10
Author(s):  
Zahid Hossain ◽  
MdAriful Hasan ◽  
Rouzbeh Ghabchi
Keyword(s):  
Neural Network ◽  
Survey Data ◽  
Water Environment ◽  
The United States ◽  
Soil Survey ◽  
United States Department ◽  
Geochemical Properties ◽  
Laboratory Test Results ◽  
Different Types ◽  
Metal Pipes

The Arkansas Department of Transportation (ARDOT) uses different types of metal culverts and cross-drains. Service lives of these culverts are largely influenced by the corrosion of the metals used in these culverts. Corrosion of metallic parts in any soil-water environment is governed by geochemical and electrochemical properties of the soils and waters. Many transportation agencies including ARDOT primarily focus on investigating the physical and mechanical properties of soils rather than their chemical aspects. The main objective of this study is to analyze the geotechnical and geochemical properties of soils in Arkansas to estimate the service lives of different metal pipes in different conditions. Soil resistivity values were predicted after analyzing the United States Department of Agriculture (USDA) soil survey data using neural network (NN) models. The developed NN models were trained and verified by using laboratory test results of soil samples collected from ARDOT, and survey data were obtained from the USDA. The service lives of metal culverts were then estimated based on the predicted soil properties and water quality parameters extracted from the data acquired from the Arkansas Department of Environmental Quality (ADEQ). Finally, Geographic Information System-based corrosion risk maps of three different types of metal pipes were developed based on their estimated service lives. The developed maps will help ARDOT engineers to assess the corrosion potential of the metal pipes before starting the new construction and repair projects and will allow using proper culvert materials to maximize their life spans.

Sign in / Sign up

Export Citation Format

Share Document