Measurement error-filtered machine learning in digital soil mapping
Explore this paper's citation graph
Summary
This presentation discusses how to incorporate measurement error into some popular ML models, starting with incorporating weights into the objective function of ML models that implicitly assume a Gaussian error.
- Type
- article
- Published
- 2021-03-03
- Cited by
- 30
- References
- 28
- Access
- Open access
- OpenAlex
- https://openalex.org/W3164098031
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:236750999
Keywords
Property (philosophy), Covariate, Property value, Random forest, Observational error
References
- Can citizen science assist digital soil mapping
- Measurement Error: Models, Methods, and Applications
- On spatial prediction of soil properties in the presence of a spatial trend: the empirical best linear unbiased predictor (E‐BLUP) with REML
- Quantile Regression Forests
- An error budget for different sources of error in digital soil mapping
- Maximum Likelihood Approaches to Variance Component Estimation and to Related Problems
- Estimation of saturated hydraulic conductivity of soils from particle size distribution and bulk density data
- Filtered Kriging for Spatial Data with Heterogeneous Measurement Error Variances
- Pollution source apportionment using a priori information and positive matrix factorization
- Kriging in the hydrosciences
- Projection Pursuit Regression
- Geostatistics in soil science: state-of-the-art and perspectives
- ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R
- Estimation and implications of instrumental drift, random measurement error and nugget variance of soil attributes-a case study for soil pH.
- The land‐potential knowledge system (landpks): mobile apps and collaboration for optimizing climate change investments
- A concordance correlation coefficient to evaluate reproducibility.
- Recent Advances in the Measurement Error Literature
- Accounting for the measurement error of spectroscopically inferred soil carbon data for improved precision of spatial predictions.
- Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables
- Multi-source data integration for soil mapping using deep learning
Cited by
- Tier 4 maps of soil pH at 25 m resolution for the Netherlands
- Global mapping of volumetric water retention at 100, 330 and 15 000 cm suction using the WoSIS database
- Comparing the prediction performance, uncertainty quantification and extrapolation potential of regression kriging and random forest while accounting for soil measurement errors
- Global review and state-of-the-art of biomass and carbon stock in the Amazon.
- Probabilistic prediction by means of the propagation of response variable uncertainty through a Monte Carlo approach in regression random forest: Application to soil moisture regionalization
- Integrating additional spectroscopically inferred soil data improves the accuracy of digital soil mapping
- Uncertainty of spatial averages and totals of natural resource maps
- Consequences of spatial structure in soil–geomorphic data on the results of machine learning models
- Uncovering the effects of Urmia Lake desiccation on soil chemical ripening using advanced mapping techniques
- Uncertainty Quantification of Soil Organic Carbon Estimation from Remote Sensing Data with Conformal Prediction
- Effect of measurement error in wet chemistry soil data on the calibration and model performance of pedotransfer functions
- High-resolution digital soil mapping of amorphous iron- and aluminium-(hydr)oxides to guide sustainable phosphorus and carbon management
- Three-dimensional space and time mapping reveals soil organic matter decreases across anthropogenic landscapes in the Netherlands
- A spatial machine learning model developed from noisy data requires multiscale performance evaluation: Predicting depth to bedrock in the Delaware river basin, USA
- BIS-4D: mapping soil properties and their uncertainties at 25 m resolution in the Netherlands
- A nature‐inclusive future with healthy soils? Mapping soil organic matter in 2050 in the Netherlands
- An improved digital soil mapping approach to predict total N by combining machine learning algorithms and open environmental data
- Applications and challenges of digital soil mapping in Africa
- Mapping soil thickness by accounting for right‐censored data with survival probabilities and machine learning
- Biplots for understanding machine learning predictions in digital soil mapping
Related papers
- Regression calibration to correct correlated errors in outcome and exposure
- On Using Summary Statistics From an External Calibration Sample to Correct for Covariate Measurement Error
- Accounting for Response Misclassification and Covariate Measurement Error Using a Random Effects Logit Model
- A comparison of regression calibration, moment reconstruction and imputation for adjusting for covariate measurement error in regression
- Covariate measurement error and the estimation of random effect parameters in a mixed model for longitudinal data.
- Reducing Bias Due to Exposure Measurement Error Using Disease Risk Scores.
- Correcting for Measurement Error in Segmented Cox Model