Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Description of spatial datasets and multicollinearity.

More »

Table 1 Expand

Table 2.

Sample structure of the PU training dataset used for model development.

More »

Table 2 Expand

Fig 1.

Workflow of the PU learning framework for illegal dump risk mapping.

More »

Fig 1 Expand

Table 3.

ML models and corresponding hyperparameter ranges used for tuning.

More »

Table 3 Expand

Fig 2.

Spatial distribution of IDSs.

More »

Fig 2 Expand

Fig 3.

Spatial distribution of (a) population density, (b) poverty index, (c) household waste generation rate, (d) DEM, (e) LST, (f) STS, (g) road intersection, (h) buildings, (i) rail and road, (j) drain and waterbody.

More »

Fig 3 Expand

Table 4.

Descriptive statistics of the predictor variables.

More »

Table 4 Expand

Table 5.

Performance comparison of ML models.

More »

Table 5 Expand

Table 6.

Model ranking across different weighting schemes.

More »

Table 6 Expand

Fig 4.

ROC curves for seven models.

More »

Fig 4 Expand

Table 7.

Hold-out test set performance of RF.

More »

Table 7 Expand

Fig 5.

(a) Probability calibration curve and (b) prediction distribution of RF.

More »

Fig 5 Expand

Fig 6.

Illegal dump risk score across KCC.

More »

Fig 6 Expand

Fig 7.

Predictor importance analysis.

More »

Fig 7 Expand