1
|
Adhikari K, Mancini M, Libohova Z, Blackstock J, Winzeler E, Smith DR, Owens PR, Silva SHG, Curi N. Heavy metals concentration in soils across the conterminous USA: Spatial prediction, model uncertainty, and influencing factors. Sci Total Environ 2024; 919:170972. [PMID: 38360318 DOI: 10.1016/j.scitotenv.2024.170972] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/28/2023] [Revised: 02/11/2024] [Accepted: 02/12/2024] [Indexed: 02/17/2024]
Abstract
Assessment and proper management of sites contaminated with heavy metals require precise information on the spatial distribution of these metals. This study aimed to predict and map the distribution of Cd, Cu, Ni, Pb, and Zn across the conterminous USA using point observations, environmental variables, and Histogram-based Gradient Boosting (HGB) modeling. Over 9180 surficial soil observations from the Soil Geochemistry Spatial Database (SGSD) (n = 1150), the Geochemical and Mineralogical Survey of Soils (GMSS) (n = 4857), and the Holmgren Dataset (HD) (n = 3400), and 28 covariates (100 m × 100 m grid) representing climate, topography, vegetation, soils, and anthropic activity were compiled. Model performance was evaluated on 20 % of the data not used in calibration using the coefficient of determination (R2), concordance correlation coefficient (ρc), and root mean square error (RMSE) indices. Uncertainty of predictions was calculated as the difference between the estimated 95 and 5 % quantiles provided by HGB. The model explained up to 50 % of the variance in the data with RMSE ranging between 0.16 (mg kg-1) for Cu and 23.4 (mg kg-1) for Zn, respectively. Likewise, ρc ranged between 0.55 (Cu) and 0.68 (Zn), respectively, and Zn had the highest R2 (0.50) among all predictions. We observed high Pb concentrations near urban areas. Peak concentrations of all studied metals were found in the Lower Mississippi River Valley. Cu, Ni, and Zn concentrations were higher on the West Coast; Cd concentrations were higher in the central USA. Clay, pH, potential evapotranspiration, temperature, and precipitation were among the model's top five important covariates for spatial predictions of heavy metals. The combined use of point observations and environmental covariates coupled with machine learning provided a reliable prediction of heavy metals distribution in the soils of the conterminous USA. The updated maps could support environmental assessments, monitoring, and decision-making with this methodology applicable to other soil databases, worldwide.
Collapse
Affiliation(s)
- Kabindra Adhikari
- USDA-ARS, Grassland, Soil and Water Research Laboratory, Temple, TX 76502, USA.
| | - Marcelo Mancini
- University of Arkansas, Department of Crop, Soil, and Environmental Sciences, Fayetteville, AR 72701, USA; Federal University of Lavras, Department of Soil Science, 37200-900 Lavras, Minas Gerais, Brazil
| | - Zamir Libohova
- USDA-ARS, Dale Bumpers Small Farms Research Center, Booneville, AR 72927, USA
| | - Joshua Blackstock
- USDA-ARS, Dale Bumpers Small Farms Research Center, Booneville, AR 72927, USA
| | - Edwin Winzeler
- USDA-ARS, Dale Bumpers Small Farms Research Center, Booneville, AR 72927, USA
| | - Douglas R Smith
- USDA-ARS, Grassland, Soil and Water Research Laboratory, Temple, TX 76502, USA
| | - Phillip R Owens
- USDA-ARS, Dale Bumpers Small Farms Research Center, Booneville, AR 72927, USA
| | - Sérgio H G Silva
- Federal University of Lavras, Department of Soil Science, 37200-900 Lavras, Minas Gerais, Brazil
| | - Nilton Curi
- Federal University of Lavras, Department of Soil Science, 37200-900 Lavras, Minas Gerais, Brazil
| |
Collapse
|
2
|
Levi D, Gispan L, Giladi N, Fetaya E. Evaluating and Calibrating Uncertainty Prediction in Regression Tasks. Sensors (Basel) 2022; 22:s22155540. [PMID: 35898047 PMCID: PMC9330317 DOI: 10.3390/s22155540] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/09/2022] [Revised: 07/13/2022] [Accepted: 07/18/2022] [Indexed: 05/30/2023]
Abstract
Predicting not only the target but also an accurate measure of uncertainty is important for many machine learning applications, and in particular, safety-critical ones. In this work, we study the calibration of uncertainty prediction for regression tasks which often arise in real-world systems. We show that the existing definition for the calibration of regression uncertainty has severe limitations in distinguishing informative from non-informative uncertainty predictions. We propose a new definition that escapes this caveat and an evaluation method using a simple histogram-based approach. Our method clusters examples with similar uncertainty prediction and compares the prediction with the empirical uncertainty on these examples. We also propose a simple, scaling-based calibration method that preforms as well as much more complex ones. We show results on both a synthetic, controlled problem and on the object detection bounding-box regression task using the COCO and KITTI datasets.
Collapse
Affiliation(s)
- Dan Levi
- General Motors Israel, Herzliya 4672515, Israel; (L.G.); (N.G.)
| | - Liran Gispan
- General Motors Israel, Herzliya 4672515, Israel; (L.G.); (N.G.)
| | - Niv Giladi
- General Motors Israel, Herzliya 4672515, Israel; (L.G.); (N.G.)
- Faculty of Computer Science, Technion, Haifa 3200003, Israel
| | - Ethan Fetaya
- Faculty of Engineering, Bar-Ilan University, Ramat Gan 5290002, Israel;
| |
Collapse
|
3
|
Meiburg R, Huberts W, Rutten MCM, van de Vosse FN. Uncertainty in model-based treatment decision support: Applied to aortic valve stenosis. Int J Numer Method Biomed Eng 2020; 36:e3388. [PMID: 32691507 PMCID: PMC7583387 DOI: 10.1002/cnm.3388] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/24/2020] [Revised: 06/02/2020] [Accepted: 07/15/2020] [Indexed: 06/11/2023]
Abstract
Patient outcome in trans-aortic valve implantation (TAVI) therapy partly relies on a patient's haemodynamic properties that cannot be determined from current diagnostic methods alone. In this study, we predict changes in haemodynamic parameters (as a part of patient outcome) after valve replacement treatment in aortic stenosis patients. A framework to incorporate uncertainty in patient-specific model predictions for decision support is presented. A 0D lumped parameter model including the left ventricle, a stenotic valve and systemic circulatory system has been developed, based on models published earlier. The unscented Kalman filter (UKF) is used to optimize model input parameters to fit measured data pre-intervention. After optimization, the valve treatment is simulated by significantly reducing valve resistance. Uncertain model parameters are then propagated using a polynomial chaos expansion approach. To test the proposed framework, three in silico test cases are developed with clinically feasible measurements. Quality and availability of simulated measured patient data are decreased in each case. The UKF approach is compared to a Monte Carlo Markov Chain (MCMC) approach, a well-known approach in modelling predictions with uncertainty. Both methods show increased confidence intervals as measurement quality decreases. By considering three in silico test-cases we were able to show that the proposed framework is able to incorporate optimization uncertainty in model predictions and is faster and the MCMC approach, although it is more sensitive to noise in flow measurements. To conclude, this work shows that the proposed framework is ready to be applied to real patient data.
Collapse
Affiliation(s)
- Roel Meiburg
- Department of Biomedical EngineeringEindhoven University of TechnologyEindhoventhe Netherlands
| | - Wouter Huberts
- Department of Biomedical EngineeringEindhoven University of TechnologyEindhoventhe Netherlands
- School for Cardiovascular DiseaseMaastricht UniversityMaastrichtthe Netherlands
| | - Marcel C. M. Rutten
- Department of Biomedical EngineeringEindhoven University of TechnologyEindhoventhe Netherlands
| | - Frans N. van de Vosse
- Department of Biomedical EngineeringEindhoven University of TechnologyEindhoventhe Netherlands
| |
Collapse
|
4
|
Nolan BT, Malone RW, Doherty JE, Barbash JE, Ma L, Shaner DL. Data worth and prediction uncertainty for pesticide transport and fate models in Nebraska and Maryland, United States. Pest Manag Sci 2015; 71:972-985. [PMID: 25132142 DOI: 10.1002/ps.3875] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/09/2014] [Revised: 07/10/2014] [Accepted: 07/30/2014] [Indexed: 06/03/2023]
Abstract
BACKGROUND Complex environmental models are frequently extrapolated to overcome data limitations in space and time, but quantifying data worth to such models is rarely attempted. The authors determined which field observations most informed the parameters of agricultural system models applied to field sites in Nebraska (NE) and Maryland (MD), and identified parameters and observations that most influenced prediction uncertainty. RESULTS The standard error of regression of the calibrated models was about the same at both NE (0.59) and MD (0.58), and overall reductions in prediction uncertainties of metolachlor and metolachlor ethane sulfonic acid concentrations were 98.0 and 98.6% respectively. Observation data groups reduced the prediction uncertainty by 55-90% at NE and by 28-96% at MD. Soil hydraulic parameters were well informed by the observed data at both sites, but pesticide and macropore properties had comparatively larger contributions after model calibration. CONCLUSIONS Although the observed data were sparse, they substantially reduced prediction uncertainty in unsampled regions of pesticide breakthrough curves. Nitrate evidently functioned as a surrogate for soil hydraulic data in well-drained loam soils conducive to conservative transport of nitrogen. Pesticide properties and macropore parameters could most benefit from improved characterization further to reduce model misfit and prediction uncertainty.
Collapse
Affiliation(s)
| | | | - John E Doherty
- Watermark Numerical Computing, Corinda, Australia
- National Centre for Groundwater Research and Training, Flinders University, Australia
| | | | - Liwang Ma
- US Department of Agriculture, Fort Collins, CO, USA
| | | |
Collapse
|