Object-oriented mapping of landslides using Random Forests

Stumpf, André; Kerle, N.

doi:10.1016/j.rse.2011.05.013

Cited by 621 publications

(459 citation statements)

References 45 publications

Supporting

Mentioning

414

Contrasting

Unclassified

Order By: Relevance

“…A Random Forest Classifier, built-up of 5000 single classification trees (as recommended by Diaz-Uriarte and Alvarez de Andrés, 2006 andStumpf andKerle, 2011), was first initialized and trained with the 23 features (dates) of the 2002 NDVI dataset. During the training stage, the FI and error estimates (out-of-bag error) were calculated and stored internally.…”

Section: Random Forest Feature Importancementioning

confidence: 99%

“…Serpico and Bruzzone, 2001;Pal, 2006;Guo et al, 2008;Pal and Foody, 2010). Analogous to bioinformatics, different embedded approaches like Recursive Feature Elimination (RFE) for Support-VectorMachines (SVM) (Pal and Foody, 2010) and the Feature Importance measure within Random Forest (Stumpf and Kerle, 2011), as well as distance based measures, such as Bhattacharyya or JM (Guo et al, 2008) have been widely used.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

Nitze

Barrett

Cawkwell

2015

International Journal of Applied Earth Observation and Geoinfor

120

View full text Add to dashboard Cite

Abstract:The analysis and classification of land cover is one of the principal applications in terrestrial remote sensing. Due to the seasonal variability of different vegetation types, the ability to discriminate different land cover types changes over time. Multi-temporal classification can help to improve the classification accuracies, but different constraints, such as financial restrictions or atmospheric conditions, may limit their application. The optimisation of image acquisition timing and frequencies can help to increase the effectiveness of the classification process. For this purpose, the Feature Importance measure of the state-of-the art machine learning method Random Forest was used to determine the optimal image acquisition periods for a general (Grassland, Forest, Water, Settlement, Peatland) and grassland specific (Improved Grassland, Semi-Improved Grassland) land cover classification in central Ireland on a 9-year time-series of MODIS Terra 16 day composite data (MOD13Q1). Feature Importances for each acquisition period of the Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI) were calculated for both classification scenarios. In the general land cover classification, the months December and January showed the highest, and July and August the lowest separability for both VIs over the entire nine-year period. This temporal separability was reflected in the classification accuracies, where the optimal choice of image dates outperformed the worst image date by 13% using NDVI and 5% using EVI on a mono-temporal analysis. With the addition of the next best image periods to the data input the classification accuracies converged quickly to their limit at around 8 to 10 images. The binary classification schemes, using two classes only, showed a stronger seasonal dependency with a higher intra-annual, but lower inter-annual variation. Nonetheless anomalous weather conditions, such as the cold winter of 2009/2010 can alter the temporal separability pattern significantly. Due to the extensive use of the NDVI for land cover discrimination, the findings of this study should be transferrable to data from other optical sensors. However, the high impact of outliers from the general climatic pattern highlights the limitation of spatial transferability to locations with different climatic and land cover conditions. The use of high-temporal, moderate resolution data such as MODIS in conjunction with machine-learning techniques proved to be a good base for the prediction of image acquisition timing for optimal land cover classification results.2

show abstract

Section: Random Forest Feature Importancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

Nitze

Barrett

Cawkwell

2015

International Journal of Applied Earth Observation and Geoinfor

120

View full text Add to dashboard Cite

show abstract

“…RF is a popular ensemble learning classification tree algorithm, which became very common for remote sensing data classification in the past few years [35,49,[68][69][70][71][72].…”

Section: Classification and Feature Selectionmentioning

confidence: 99%

“…All algorithms have advantages and disadvantages, and there is no perfect segmentation algorithm for defining object boundaries [44][45][46]. Many scientific studies rely on the Multiresolution Segmentation algorithm [9,30,34,37,[40][41][42][47][48][49][50]. This algorithm starts with one-pixel image segments, and merges neighboring segments together until a heterogeneity threshold is reached [51].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Guided Segmentation and Classification of Multi-Temporal Landsat 8 Images for Crop Type Mapping in Southeastern Brazil

et al. 2015

View full text Add to dashboard Cite

Only well-chosen segmentation parameters ensure optimum results of object-based image analysis (OBIA). Manually defining suitable parameter sets can be a time-consuming approach, not necessarily leading to optimum results; the subjectivity of the manual approach is also obvious. For this reason, in supervised segmentation as proposed by Stefanski et al. (2013) one integrates the segmentation and classification tasks. The segmentation is optimized directly with respect to the subsequent classification. In this contribution, we build on this work and developed a fully autonomous workflow for supervised object-based classification, combining image segmentation and random forest (RF) classification. Starting from a fixed set of randomly selected and manually interpreted training samples, suitable segmentation parameters are automatically identified. A sub-tropical study site located in São Paulo State (Brazil) was used to evaluate the OPEN ACCESSRemote Sens. 2015, 7 14483proposed approach. Two multi-temporal Landsat 8 image mosaics were used as input (from August 2013 and January 2014) together with training samples from field visits and VHR (RapidEye) photo-interpretation. Using four test sites of 15 × 15 km 2 with manually interpreted crops as independent validation samples, we demonstrate that the approach leads to robust classification results. On these samples (pixel wise, n ≈ 1 million) an overall accuracy (OA) of 80% could be reached while classifying five classes: sugarcane, soybean, cassava, peanut and others. We found that the overall accuracy obtained from the four test sites was only marginally lower compared to the out-of-bag OA obtained from the training samples. Amongst the five classes, sugarcane and soybean were classified best, while cassava and peanut were often misclassified due to similarity in the spatio-temporal feature space and high within-class variabilities. Interestingly, misclassified pixels were in most cases correctly identified through the RF classification margin, which is produced as a by-product to the classification map.

show abstract

Automatic classification of endogenous landslide seismicity using the Random Forest supervised classifier

Provost

Hibert

Malet

2017

Geophysical Research Letters

140

138

View full text Add to dashboard Cite

The deformation of slow‐moving landslides developed in clays induces endogenous seismicity of mostly low‐magnitude events (ML<1). Long seismic records and complete catalogs are needed to identify the type of seismic sources and understand their mechanisms. Manual classification of long records is time‐consuming and may be highly subjective. We propose an automatic classification method based on the computation of 71 seismic attributes and the use of a supervised classifier. No attribute was selected a priori in order to create a generic multi‐class classification method applicable to many landslide contexts. The method can be applied directly on the results of a simple detector. We developed the approach on the seismic network of eight sensors of the Super‐Sauze clay‐rich landslide (South French Alps) for the detection of four types of seismic sources. The automatic algorithm retrieves 93% of sensitivity in comparison to a manually interpreted catalog considered as reference.

show abstract

Object-oriented mapping of landslides using Random Forests

Cited by 621 publications

References 45 publications

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series

Self-Guided Segmentation and Classification of Multi-Temporal Landsat 8 Images for Crop Type Mapping in Southeastern Brazil

Automatic classification of endogenous landslide seismicity using the Random Forest supervised classifier

Contact Info

Product

Resources

About