A Random Forest approach to predict the spatial distribution of sediment pollution in an estuarine system

Walsh, Eric S.; Kreakie, Betty J.; Cantwell, Mark G.; Nacci, Diane

doi:10.1371/journal.pone.0179473

Cited by 33 publications

(14 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, predictor variables that describe the spatial location rather than the environmental properties are commonly included. Spatial coordinates are used especially often (Li et al, 2011;Langella et al, 2010;Shi et al, 2015;Janatian et al, 2017;Walsh et al, 2017;Jing et al, 2016;Wang et al, 2017;Georganos et al, 2019). Distances to certain points (e.g.…”

Section: Introductionmentioning

confidence: 99%

Importance of spatial predictor variable selection in machine learning applications – Moving from data reproduction to spatial prediction

Meyer

Reudenbach

Wöllauer

et al. 2019

Ecological Modelling

278

158

View full text Add to dashboard Cite

Machine learning algorithms find frequent application in spatial prediction of biotic and abiotic environmental variables. However, the characteristics of spatial data, especially spatial autocorrelation, are widely ignored. We hypothesize that this is problematic and results in models that can reproduce training data but are unable to make spatial predictions beyond the locations of the training samples. We assume that not only spatial validation strategies but also spatial variable selection is essential for reliable spatial predictions.We introduce two case studies that use remote sensing to predict land cover and the leaf area index for the "Marburg Open Forest", an open research and education site of Marburg University, Germany. We use the machine learning algorithm Random Forests to train models using non-spatial and spatial cross-validation strategies to understand how spatial variable selection affects the predictions.Our findings confirm that spatial cross-validation is essential in preventing overoptimistic model performance. We further show that highly autocorrelated predictors (such as geolocation variables, e.g. latitude, longitude) can lead to considerable overfitting and result in models that can reproduce the training data but fail in making spatial predictions. The problem becomes apparent in the visual assessment of the spatial predictions that show clear artefacts that can be traced back to a misinterpretation of the spatially autocorrelated predictors by the algorithm. Spatial variable selection could automatically detect and remove such variables that lead to overfitting, resulting in reliable spatial prediction patterns and improved statistical spatial model performance.We conclude that in addition to spatial validation, a spatial variable selection must be considered in spatial predictions of ecological data to produce reliable predictions.

show abstract

Section: Introductionmentioning

confidence: 99%

Importance of spatial predictor variable selection in machine learning applications – Moving from data reproduction to spatial prediction

Meyer

Reudenbach

Wöllauer

et al. 2019

Ecological Modelling

278

158

View full text Add to dashboard Cite

show abstract

“…The RBF‐SVM algorithm in this research seeks the best compromise between model complexity and learning capacity based on limited samples, and achieves global optimality, which could effectively analyze complex data and distinguish between MRSA and MSSA 43 . The reason that the RF model is chosen for comparison is that, just like the RBF‐SVM model, it is used to solve a large number of binary classification problems in biological research, and it is also non‐linear 44 …”

Section: Discussionmentioning

confidence: 99%

“…43 The reason that the RF model is chosen for comparison is that, just like the RBF-SVM model, it is used to solve a large number of binary classification problems in biological research, and it is also non-linear. 44 A caveat that occurred to us during this study is that the accuracy of the classification was capped around 86%, implying that the classification model needs to be further optimized. On the other hand,…”

Section: The Rbf-svm Model Outperformed the Rf Model At The Low Falmentioning

confidence: 93%

Rapid identification and discrimination of methicillin‐resistant Staphylococcus aureus strains via matrix‐assisted laser desorption/ionization time‐of‐flight mass spectrometry

Liu

Hsu

et al. 2020

Rapid Comm Mass Spectrometry

View full text Add to dashboard Cite

Rationale Methicillin‐resistant Staphylococcus aureus (MRSA) is one of major clinical pathogens responsible for both hospital‐ and community‐acquired infections worldwide. A delay in targeted antibiotic treatment contributes to longer hospitalization stay, higher costs, and increasing in‐hospital mortality. Matrix‐assisted laser desorption/ionization time‐of‐flight mass spectrometry (MALDI‐TOF MS) has been integrated into the routine workflow for microbial identification over the past decade, and it has also shown promising functions in the detection of bacterial resistance. Therefore, we describe a rapid MALDI‐TOF MS‐based methodology for MRSA screening with machine‐learning algorithms. Methods A total of 452 clinical S. aureus isolates were included in this study, of which 194 were MRSA and 258 were methicillin‐sensitive S. aureus (MSSA). The mass‐to‐charge ratio (m/z) features from MRSA and MSSA strains were binned and selected through Lasso regression. These features were then used to train a non‐linear support vector machine (SVM) with radial basis function (RBF) kernels to evaluate the discrimination performance. The classifiers' accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC) were evaluated and compared with those from the random forest (RF) model. Results A total of 2601 unique spectral peaks of all isolates were identified and 38 m/z features were selected for the classifying model. The AUCs of the non‐linear RBF‐SVM model and the RF model were 0.89 and 0.87, respectively, and the accuracy ranged between 0.86 (RBF‐SVM) and 0.82 (RF). Conclusions Our study demonstrates that MALDI‐TOF MS coupled with machine‐learning algorithms could be used to develop a rapid and easy‐to‐use method to discriminate MRSA from MSSA. Considering that this method is easy to implement in routine microbiology laboratories, it suggests a cost‐effective and time‐efficient alternative to conventional resistance detection in the future to improve clinical treatment.

show abstract

“…While image classification is one of the most prominent predictive applications in urban geography, there are of course other important predictive questions that can be answered in the era of "big" data: small area estimation and interpolation for socioeconomic data (Singleton and Arribas-Bel 2019), spatial patterns in large, open, georeferenced municipal data sets such as crimes, "311" calls, and parking violations (Gao et al 2019), spatiotemporal patterns in disease outbreaks using georeferenced sentiment data from social media (e.g., Allen et al 2016), the spatial distribution of pollution (Walsh et al 2017), the prediction of housing prices and rents (Mu, Wu, and Zhang 2014;Fan, Cui, and Zhong 2018;Phan 2018;Truong et al 2020), and gentrification (Alejandro and Palafox 2019; Knorr 2019), among others. In an urban planning context, predicting the future distribution of population and land use with greater precision is an area of significant opportunity for predictive model applications (Feng et al 2018).…”

Section: Literaturementioning

confidence: 99%

Spatial Models or Random Forest? Evaluating the Use of Spatially Explicit Machine Learning Methods to Predict Employment Density around New Transit Stations in Los Angeles

Credit

2021

Geographical Analysis

View full text Add to dashboard Cite

The increasing use of "new" machine learning techniques, such as random forest, provides an impetus to researchers to better understand the role of space in these models. Thus, this article develops an approach for constructing spatially explicit random forest models by including spatially lagged variables to mirror various spatial econometric specifications in order to test their comparative performance against traditional spatial and nonspatial regression models for predicting block-level employment density around new transit stations in Los Angeles. This article employs a "post hoc" testing approach to isolate the impact of a particular variable (transit proximity)-and supplemental diagnostics (such as partial dependence plots and permutation importances)-to help inform explanatory relationships. The results indicate that random forest models slightly outperform spatial econometric models, and the inclusion of spatial lag parameters modestly improves random forest model accuracy-the best-fit spatial random forest model demonstrates 84.61% accuracy in predicting post-construction employment density around newly built transit stations, compared to 81.88% for the best-fit spatial econometric model and 84.37% for the nonspatial random forest model. However, given these somewhat small differences, it is not possible to conclude that the random forest approach is clearly superior to traditional spatial econometric models from these results alone.

show abstract

A Random Forest approach to predict the spatial distribution of sediment pollution in an estuarine system

Cited by 33 publications

References 60 publications

Importance of spatial predictor variable selection in machine learning applications – Moving from data reproduction to spatial prediction

Importance of spatial predictor variable selection in machine learning applications – Moving from data reproduction to spatial prediction

Rapid identification and discrimination of methicillin‐resistant Staphylococcus aureus strains via matrix‐assisted laser desorption/ionization time‐of‐flight mass spectrometry

Spatial Models or Random Forest? Evaluating the Use of Spatially Explicit Machine Learning Methods to Predict Employment Density around New Transit Stations in Los Angeles

Contact Info

Product

Resources

About