A Systematic Approach for Variable Selection With Random Forests: Achieving Stable Variable Importance Values

Behnamian, Amir; Millard, Koreen; Banks, Sarah N.; White, Lori; Richardson, Murray; Pasher, Jon

doi:10.1109/lgrs.2017.2745049

Cited by 97 publications

(56 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the majority of studies, MDA is used [47] because it is considered as more straightforward, reliable, and easier to understand [51]. However, Behnamian et al [52] claimed that MDG is slightly more stable. Thus, we decided to use both methodologies.…”

Section: Variable Importance and Assessment Of Temporal Patternsmentioning

confidence: 99%

Forest Stand Species Mapping Using the Sentinel-2 Time Series

et al. 2019

View full text Add to dashboard Cite

Accurate information regarding forest tree species composition is useful for a wide range of applications, both for forest management and scientific research. Remote sensing is an efficient tool for collecting spatially explicit information on forest attributes. With the launch of the Sentinel-2 mission, new opportunities have arisen for mapping tree species owing to its spatial, spectral, and temporal resolution. The short revisit cycle (five days) is crucial in vegetation mapping because of the reflectance changes caused by phenological phases. In our study, we evaluated the utility of the Sentinel-2 time series for mapping tree species in the complex, mixed forests of the Polish Carpathian Mountains. We mapped the following nine tree species: common beech, silver birch, common hornbeam, silver fir, sycamore maple, European larch, grey alder, Scots pine, and Norway spruce. We used the Sentinel-2 time series from 2018, with 18 images included in the study. Different combinations of Sentinel-2 imagery were selected based on mean decrease accuracy (MDA) and mean decrease Gini (MDG) measures, in addition to temporal phonological pattern analysis. Tree species discrimination was performed using the Random Forest classification algorithm. Our results showed that the use of the Sentinel-2 time series instead of single date imagery significantly improved forest tree species mapping, by approximately 5–10% of overall accuracy. In particular, combining images from spring and autumn resulted in better species discrimination.

show abstract

Section: Variable Importance and Assessment Of Temporal Patternsmentioning

confidence: 99%

Forest Stand Species Mapping Using the Sentinel-2 Time Series

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Then, an increasing number of variables were removed in steps (i.e., r > 0.9, r > 0.8, r > 0.7, r > 0.6, and r > 0.5) assuming that a decrease in accuracy would occur if a given variable, or set of variables, provided valuable information (and thus should be retained). Note that we assumed that the Mean Decrease in Accuracy correctly identified the most important input, among sets of correlated variables [64], thus this value (averaged across 10 model runs to achieve stable variable importance measures [65]) was used to identify which variable to retain, while all others were removed. After having created a set of uncorrelated variables, the 10 with the highest Mean Decrease in Accuracy ranking were used as inputs to a model.…”

Section: Applying the Random Forests Algorithmmentioning

confidence: 99%

“…These were then used as inputs to a model. Similar to (i) and (iii), 10 model runs were used to achieve a stable variable importance ranking [65]. (iii) Ten remaining variables following backward selection process.…”

Section: Applying the Random Forests Algorithmmentioning

confidence: 99%

“…(iii) Ten remaining variables following backward selection process. Following the same approach used by [16], a detailed assessment of Mean Decrease in Accuracy and Gini Index values averaged across 10 model runs [65] was used in combination with expert knowledge to determine the five variables (of all predictor variables) with the lowest importance. These variables were then set aside, and new importance values were calculated.…”

Section: Applying the Random Forests Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Contributions of Actual and Simulated Satellite SAR Data for Substrate Type Differentiation and Shoreline Mapping in the Canadian Arctic

et al. 2017

Self Cite

View full text Add to dashboard Cite

Detailed information on the land cover types present and the horizontal position of the land-water interface is needed for sensitive coastal ecosystems throughout the Arctic, both to establish baselines against which the impacts of climate change can be assessed and to inform response operations in the event of environmental emergencies such as oil spills. Previous work has demonstrated potential for accurate classification via fusion of optical and SAR data, though what contribution either makes to model accuracy is not well established, nor is it clear what shorelines can be classified using optical or SAR data alone. In this research, we evaluate the relative value of quad pol RADARSAT-2 and Landsat 5 data for shoreline mapping by individually excluding both datasets from Random Forest models used to classify images acquired over Nunavut, Canada. In anticipation of the RADARSAT Constellation Mission (RCM), we also simulate and evaluate dual and compact polarimetric imagery for shoreline mapping. Results show that SAR data is needed for accurate discrimination of substrates as user's and producer's accuracies were 5-24% higher for models constructed with quad pol RADARSAT-2 and DEM data than models constructed with Landsat 5 and DEM data. Models based on simulated RCM and DEM data achieved significantly lower overall accuracies (71-77%) than models based on quad pol RADARSAT-2 and DEM data (80%), with Wetland and Tundra being most adversely affected. When classified together with Landsat 5 and DEM data, however, model accuracy was less affected by the SAR data type, with multiple polarizations and modes achieving independent overall accuracies within a range acceptable for operational mapping, at 89-91%. RCM is expected to contribute positively to ongoing efforts to monitor change and improve emergency preparedness throughout the Arctic.

show abstract

“…Fourth, RF is not easy to fall into overfitting compared with the Boosting method [18]. Moreover, RF measures the importance of variables automatically [25]. Finally, RF can obtain a higher classification accuracy compared to other well-known classifiers such as SVM [5,6] and maximum likelihood (ML) [17,23], with fewer parameters.Active learning is a kind of iterative method that queries the most informative samples for manual labeling at each iteration [14].…”

mentioning

confidence: 99%

Active Semi-Supervised Random Forest for Hyperspectral Image Classification

Zhang

Cao

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Random forest (RF) has obtained great success in hyperspectral image (HSI) classification. However, RF cannot leverage its full potential in the case of limited labeled samples. To address this issue, we propose a unified framework that embeds active learning (AL) and semi-supervised learning (SSL) into RF (ASSRF). Our aim is to utilize AL and SSL simultaneously to improve the performance of RF. The objective of the proposed method is to use a small number of manually labeled samples to train classifiers with relative high classification accuracy. To achieve this goal, a new query function is designed to query the most informative samples for manual labeling, and a new pseudolabeling strategy is introduced to select some samples for pseudolabeling. Compared with other AL-and SSL-based methods, the proposed method has several advantages. First, ASSRF utilizes the spatial information to construct a query function for AL, which can select more informative samples. Second, in addition to providing more labeled samples for SSL, the proposed pseudolabeling method avoids bias caused by AL-labeled samples. Finally, the proposed model retains the advantages of RF. To demonstrate the effectiveness of ASSRF, we conducted experiments on three real hyperspectral data sets. The experimental results have shown that our proposed method outperforms other state-of-the-art methods.Random forest, proposed by Breiman [16], is one of the most important machine learning methods. Compared with other machine learning methods, RF has the following advantages [9][10][11][17][18][19][20][21][22][23][24]. First, RF is suitable for high-dimensional data, which can alleviate the influence of curse of dimensionality [20]. Second, RF is very fast because it is implemented in parallel [9]. Third, RF is effective to handle data with imbalanced class labels or missing values [21]. Fourth, RF is not easy to fall into overfitting compared with the Boosting method [18]. Moreover, RF measures the importance of variables automatically [25]. Finally, RF can obtain a higher classification accuracy compared to other well-known classifiers such as SVM [5,6] and maximum likelihood (ML) [17,23], with fewer parameters.Active learning is a kind of iterative method that queries the most informative samples for manual labeling at each iteration [14]. Initially, the data set consists of two parts: a small number of labeled samples and a large number of unlabeled samples. At each iteration, a query function is adopted to investigate the unlabeled samples and select the most informative samples for manual labeling. After multiple iterations, the performance of the classifier improves along with the increase in the number of manually labeled samples. The query function plays an important role in determining the samples selected for manual labeling, which directly affects the classification performance [15].Semi-supervised learning, another way to tackle the issue of limited samples, trains a classifier with the labeled and unlabeled samples together, which does not r...

show abstract

A Systematic Approach for Variable Selection With Random Forests: Achieving Stable Variable Importance Values

Cited by 97 publications

References 20 publications

Forest Stand Species Mapping Using the Sentinel-2 Time Series

Forest Stand Species Mapping Using the Sentinel-2 Time Series

Contributions of Actual and Simulated Satellite SAR Data for Substrate Type Differentiation and Shoreline Mapping in the Canadian Arctic

Active Semi-Supervised Random Forest for Hyperspectral Image Classification

Contact Info

Product

Resources

About